diff --git a/lab-2/result.ipynb b/lab-2/result.ipynb
index ad7959c1e47a9784b6231f7fe08d23ac6df31988..c68c16e5971b49a31a2e73090b4472201111259b 100644
--- a/lab-2/result.ipynb
+++ b/lab-2/result.ipynb
@@ -536,12 +536,12 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 84,
+      "execution_count": 104,
       "metadata": {},
       "outputs": [
         {
           "data": {
-            "image/png": "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",
+            "image/png": "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",
             "text/plain": [
               "<Figure size 640x480 with 1 Axes>"
             ]
@@ -596,7 +596,7 @@
         "    plt.axis('off')\n",
         "    plt.show()\n",
         "\n",
-        "display_image_with_annotations(TRAIN_DIR, \"0002.jpg\")\n"
+        "display_image_with_annotations(VAL_DIR, \"0136.jpeg\")\n"
       ]
     },
     {
@@ -666,78 +666,583 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 86,
+      "execution_count": 96,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from ultralytics import YOLO\n",
+        "model = YOLO(\"yolov8s.pt\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 99,
       "metadata": {},
       "outputs": [
         {
           "name": "stdout",
           "output_type": "stream",
           "text": [
-            "Downloading https://github.com/ultralytics/assets/releases/download/v8.3.0/yolov8s.pt to 'yolov8s.pt'...\n"
+            "New https://pypi.org/project/ultralytics/8.3.20 available 😃 Update with 'pip install -U ultralytics'\n",
+            "Ultralytics 8.3.19 🚀 Python-3.12.7 torch-2.5.0 MPS (Apple M3)\n",
+            "\u001b[34m\u001b[1mengine/trainer: \u001b[0mtask=detect, mode=train, model=yolov8s.pt, data=/Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/data.yaml, epochs=50, time=None, patience=100, batch=16, imgsz=640, save=True, save_period=-1, cache=False, device=mps, workers=8, project=None, name=train, exist_ok=False, pretrained=True, optimizer=auto, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=10, resume=False, amp=True, fraction=1.0, profile=False, freeze=None, multi_scale=False, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, split=val, save_json=False, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, vid_stride=1, stream_buffer=False, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, embed=None, show=False, save_frames=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, show_boxes=True, line_width=None, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=True, opset=None, workspace=4, nms=False, lr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=7.5, cls=0.5, dfl=1.5, pose=12.0, kobj=1.0, label_smoothing=0.0, nbs=64, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, bgr=0.0, mosaic=1.0, mixup=0.0, copy_paste=0.0, copy_paste_mode=flip, auto_augment=randaugment, erasing=0.4, crop_fraction=1.0, cfg=None, tracker=botsort.yaml, save_dir=/Users/ischknv/Documents/GitHub/miem/aimm/runs/detect/train\n"
           ]
         },
         {
           "name": "stderr",
           "output_type": "stream",
           "text": [
-            "  0%|          | 0.00/21.5M [00:00<?, ?B/s]huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
+            "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
             "To disable this warning, you can either:\n",
             "\t- Avoid using `tokenizers` before the fork if possible\n",
-            "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n",
-            "100%|██████████| 21.5M/21.5M [00:00<00:00, 40.7MB/s]\n"
+            "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
           ]
-        }
-      ],
-      "source": [
-        "from ultralytics import YOLO\n",
-        "model = YOLO(\"yolov8s.pt\")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 88,
-      "metadata": {},
-      "outputs": [
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Overriding model.yaml nc=80 with nc=2\n",
+            "\n",
+            "                   from  n    params  module                                       arguments                     \n",
+            "  0                  -1  1       928  ultralytics.nn.modules.conv.Conv             [3, 32, 3, 2]                 \n",
+            "  1                  -1  1     18560  ultralytics.nn.modules.conv.Conv             [32, 64, 3, 2]                \n",
+            "  2                  -1  1     29056  ultralytics.nn.modules.block.C2f             [64, 64, 1, True]             \n",
+            "  3                  -1  1     73984  ultralytics.nn.modules.conv.Conv             [64, 128, 3, 2]               \n",
+            "  4                  -1  2    197632  ultralytics.nn.modules.block.C2f             [128, 128, 2, True]           \n",
+            "  5                  -1  1    295424  ultralytics.nn.modules.conv.Conv             [128, 256, 3, 2]              \n",
+            "  6                  -1  2    788480  ultralytics.nn.modules.block.C2f             [256, 256, 2, True]           \n",
+            "  7                  -1  1   1180672  ultralytics.nn.modules.conv.Conv             [256, 512, 3, 2]              \n",
+            "  8                  -1  1   1838080  ultralytics.nn.modules.block.C2f             [512, 512, 1, True]           \n",
+            "  9                  -1  1    656896  ultralytics.nn.modules.block.SPPF            [512, 512, 5]                 \n",
+            " 10                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']          \n",
+            " 11             [-1, 6]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+            " 12                  -1  1    591360  ultralytics.nn.modules.block.C2f             [768, 256, 1]                 \n",
+            " 13                  -1  1         0  torch.nn.modules.upsampling.Upsample         [None, 2, 'nearest']          \n",
+            " 14             [-1, 4]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+            " 15                  -1  1    148224  ultralytics.nn.modules.block.C2f             [384, 128, 1]                 \n",
+            " 16                  -1  1    147712  ultralytics.nn.modules.conv.Conv             [128, 128, 3, 2]              \n",
+            " 17            [-1, 12]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+            " 18                  -1  1    493056  ultralytics.nn.modules.block.C2f             [384, 256, 1]                 \n",
+            " 19                  -1  1    590336  ultralytics.nn.modules.conv.Conv             [256, 256, 3, 2]              \n",
+            " 20             [-1, 9]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
+            " 21                  -1  1   1969152  ultralytics.nn.modules.block.C2f             [768, 512, 1]                 \n",
+            " 22        [15, 18, 21]  1   2116822  ultralytics.nn.modules.head.Detect           [2, [128, 256, 512]]          \n",
+            "Model summary: 225 layers, 11,136,374 parameters, 11,136,358 gradients, 28.6 GFLOPs\n",
+            "\n",
+            "Transferred 349/355 items from pretrained weights\n",
+            "Freezing layer 'model.22.dfl.conv.weight'\n"
+          ]
+        },
         {
           "name": "stderr",
           "output_type": "stream",
           "text": [
-            "UserWarning: This is now an optional IPython functionality, setting dhist requires you to install the `pickleshare` library.\n"
+            "\u001b[34m\u001b[1mtrain: \u001b[0mScanning /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train... 565 images, 0 backgrounds, 426 corrupt: 100%|██████████| 565/565 [00:00<00:00, 5707.18it/s]"
           ]
         },
         {
           "name": "stdout",
           "output_type": "stream",
           "text": [
-            "/Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset\n",
-            "New https://pypi.org/project/ultralytics/8.3.20 available 😃 Update with 'pip install -U ultralytics'\n",
-            "Ultralytics 8.3.19 🚀 Python-3.12.7 torch-2.5.0 CPU (Apple M3)\n",
-            "\u001b[34m\u001b[1mengine/trainer: \u001b[0mtask=detect, mode=train, model=yolov8s.pt, data=data.yaml, epochs=50, time=None, patience=100, batch=16, imgsz=640, save=True, save_period=-1, cache=False, device=None, workers=8, project=None, name=train2, exist_ok=False, pretrained=True, optimizer=auto, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=10, resume=False, amp=True, fraction=1.0, profile=False, freeze=None, multi_scale=False, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, split=val, save_json=False, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, vid_stride=1, stream_buffer=False, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, embed=None, show=False, save_frames=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, show_boxes=True, line_width=None, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=True, opset=None, workspace=4, nms=False, lr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=7.5, cls=0.5, dfl=1.5, pose=12.0, kobj=1.0, label_smoothing=0.0, nbs=64, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, bgr=0.0, mosaic=1.0, mixup=0.0, copy_paste=0.0, copy_paste_mode=flip, auto_augment=randaugment, erasing=0.4, crop_fraction=1.0, cfg=None, tracker=botsort.yaml, save_dir=/Users/ischknv/Documents/GitHub/miem/aimm/runs/detect/train2\n"
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0140.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [350.84933 354.79907 289.42383 372.0351 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0141.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [323.44394 296.44553 503.64194 294.64856]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0142.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [335.13156 303.34567 388.2635  419.89862]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0143.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [293.34613 335.63205 207.43427 275.1614 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0144.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [310.80786 329.3498  508.07294 599.8754 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0145.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [315.05124 329.32086 551.5852  365.07025]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0146.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [444.5042  279.4409  195.31519 205.59256]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0147.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [421.55246 139.18092 223.48941 276.7925 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0148.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [310.81503 318.5168  392.1365  381.3409 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0149.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [203.34253 334.35803 249.88275 298.1533 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0150.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [246.48584 375.76923 159.29271 218.21562]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0151.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [312.6702  334.86755 507.5556  328.82388]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0152.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [390.29602 259.18323 385.5002  253.8147 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0153.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [319.76727 318.8007  637.187   412.79077]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0154.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [382.9257  311.38867 202.34465 221.34167]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0155.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [302.84848 286.64304 340.72754 519.7564 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0156.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [314.9271  333.9851  607.43726 480.29788]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0157.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [202.74046 305.86166 195.15564 359.77832]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0158.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [317.07532 319.97046 609.4284  458.7991 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0159.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [441.37976 286.81055 245.3206  293.5136 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0160.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [421.59885 317.0772  376.73047 313.95282]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0161.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [310.31506 316.74985 318.87363 394.4186 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0162.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [366.31824 320.53717 185.05612 285.91376]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0163.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [284.54865 389.95712 209.41252 215.77216]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0164.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [312.30008 320.40707 326.19907 555.7524 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0165.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [431.60825 370.27417 369.92072 255.24026]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0166.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [362.65814 313.7342  254.83232 237.50533]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0167.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [104.99803 283.0066  191.28204 143.96039]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0168.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [339.55225 340.29742 398.27856 407.42798]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0169.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [308.0685  365.06046 347.9958  237.14911]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0170.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [217.88223 425.8313  153.18188 188.89273]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0171.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [342.85852 312.1658  387.074   411.76648]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0172.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [318.6891  323.59085 606.8808  401.56522]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0173.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [326.12048 308.63354 521.5536  254.11713]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0174.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [297.60007 267.27206 411.7248  437.2238 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0175.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [294.69724 313.5403  308.02713 486.9817 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0176.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [329.913   399.9608  449.48846 256.48303]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0177.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [367.4862  300.44556 296.81433 426.93845]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0178.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [239.88751 401.77383 453.36395 332.61316]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0179.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [331.1511  335.96347 369.9211  555.4656 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0180.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [497.23972 415.82532 174.21738 288.68768]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0181.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [316.73203 297.62656 379.94055 591.13416]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0182.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [468.23392 278.0328  289.74512 550.2421 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0183.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [340.8226 313.1465 390.0595 412.7348]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0184.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [320.28455 312.09067 435.70682 606.3701 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0185.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [105.576706 296.88928  184.58733  260.64996 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0186.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [455.6714  303.99908 309.20413 276.85455]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0187.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [316.35666 317.35593 627.63416 632.04346]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0188.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [322.34448 315.60013 428.95297 601.21686]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0189.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [302.82318 364.6391  185.44464 189.39502]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0190.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [325.97223 304.53137 491.03027 332.26068]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0191.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [253.97711 293.92645  69.42512 156.08081]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0192.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [342.3535  319.95453 425.95245 536.46906]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0193.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [308.65573 325.56494 338.58902 348.73663]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0194.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [336.65564 328.89145 332.17804 222.08992]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0195.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [317.44232 362.67065 559.12    342.88223]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0196.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [337.96268 269.93774 350.3775  410.9676 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0197.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [477.36996 387.59668 192.26784 294.73798]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0198.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [311.89    344.69366 177.66064 171.44678]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0199.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [159.14612 367.30914 209.30038 148.72647]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0200.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [203.99664 250.58667 145.5332  142.96843]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0201.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [321.07437 312.36505 542.7735  380.95477]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0202.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [294.66974 313.5692  307.8706  487.13446]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0203.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [326.12927 322.5656  545.8755  389.4262 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0204.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [212.57205 286.10974 424.65387 550.9962 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0205.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [295.85266 325.16595 295.39447 357.23343]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0206.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [291.58215 317.84085 323.33188 223.01501]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0207.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [274.29956 369.4834  230.22137 235.43312]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0208.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [467.98718 278.6147  288.2067  548.8168 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0209.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [327.928   319.87454 501.07983 551.4227 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0210.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [321.7563  319.00134 285.12897 465.76355]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0211.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [487.4214  367.5083  143.04037 418.8165 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0212.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [315.13403 332.97504 286.57483 381.75168]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0213.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [354.4021  315.90723 396.43286 498.48376]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0214.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [323.5724  313.68875 399.61224 319.95642]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0215.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [345.3856  312.72348 426.98254 350.2386 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0216.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [397.09088 325.5421  226.22389 273.01617]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0217.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [338.84668 353.97382 201.19962 328.3826 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0218.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [325.3198  393.5056  371.5161  243.90196]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0219.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [473.83728 453.86127 112.90116 134.15514]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0220.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [288.8035  319.19995 269.11334 360.665  ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0221.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [496.51447 351.77777 140.78235 235.45775]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0222.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [301.85947 323.47595 245.05629 314.00204]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0223.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [320.29517 319.10117 609.8519  637.8457 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0224.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [279.34488 309.94553 201.71663 180.51744]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0225.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [315.50085 392.9498  242.87817 341.67783]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0226.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [272.72437  313.59918   75.967514  83.65532 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0227.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [316.38373 375.14203 195.67725 218.37236]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0228.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [275.83115 292.94705 193.24213 227.53036]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0229.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [239.62698 402.63577 452.96616 334.495  ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0230.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [294.2609   80.34127 210.19072 160.7953 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0231.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [433.60684 427.99927 325.17316 313.40616]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0232.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [299.92786 340.33078 384.43787 455.82608]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0233.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [280.28644 263.72034 288.78543 269.91904]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0234.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [301.82333 255.8359  209.2524  360.83115]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0235.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [509.3971  416.196   218.50305 163.1824 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0236.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [318.50684 348.7024  353.13885 286.29666]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0237.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [300.81317 313.45096 459.65173 361.91864]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0238.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [320.81506 318.59515 533.8433  339.20822]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0239.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [343.33038 356.26416 328.6411  199.80222]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0240.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [403.66797 356.00946 357.89932 565.19525]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0241.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [304.2177  333.24814 165.49704 218.25754]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0242.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [342.29846 319.9795  426.0636  536.6279 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0243.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [319.1401  316.39114 571.48737 506.1757 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0244.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [304.3412  333.48355 164.92018 218.70354]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0245.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [340.25745 328.41528 300.2774  408.67203]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0246.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [409.0681  324.04538 422.24506 372.57434]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0247.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [500.67868 322.05722 140.93677 233.01596]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0248.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [308.84    317.93668 581.2463  583.7235 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0249.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [319.25485 362.13208 479.36496 398.23672]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0250.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [214.81168 484.08188  79.59041 173.13148]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0251.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [319.1818  320.52487 426.32672 486.67325]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0252.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [327.39578 330.652   509.899   379.9593 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0253.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [286.01538 322.20416 314.35696 366.19934]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0254.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [397.22766 291.59067 310.8808  243.24236]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0255.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [322.11298 376.76407 245.20935 337.96814]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0256.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [254.18427 141.72453 297.24512 266.85666]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0257.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [301.88165 269.07004 126.99699 161.54955]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0258.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [173.21068 342.50848 199.63194 224.41776]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0259.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [320.37753 320.33813 576.6047  407.95514]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0260.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [284.5217  352.29443 243.72878 273.14853]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0261.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [460.95172 330.09097 356.60663 158.33327]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0262.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [339.3913  317.4317  349.12506 440.5539 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0263.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [326.14868 140.07907 125.16943 179.33052]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0264.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [166.84244 281.89786 190.945   275.31406]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0265.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [304.7352  317.34003 429.94128 541.31335]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0266.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [476.06503 355.74805 318.11163 287.39822]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0267.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 65.22345 251.4787  123.36419 102.93888]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0268.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [398.76398 460.34244 233.19202 265.11578]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0269.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [382.39355 310.46136 202.97891 219.05707]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0270.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [337.30786 270.285   349.46347 411.6727 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0271.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [306.65195 364.90665 263.38876 353.76215]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0272.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [457.0232   159.03      77.52279  122.061775]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0273.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [291.12225 355.56305 459.9131  356.0942 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0274.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [484.93555 342.90268 243.13535 280.49158]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0275.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [293.2037   323.29953   19.985043  24.973629]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0276.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [330.06046 324.55066 499.59094 307.61115]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0277.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [331.53946 311.0027  463.76862 611.6092 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0278.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [517.2517  414.38702  90.77785 153.64279]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0279.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [128.66556 353.00806 153.62608 237.10143]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0280.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [339.67053 298.19965 313.38437 353.3339 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0281.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [280.98898 309.1458  488.0727  455.59644]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0282.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [346.8988  355.1749  296.22342 373.06555]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0283.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [281.95444 354.71573 351.7885  563.0415 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0284.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [322.0964  313.1078  606.2688  363.55396]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0285.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [301.15894 251.57254 374.6814  433.257  ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0286.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [244.97406 286.3697  395.1599  321.22296]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0287.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [348.4862  298.00662 256.35495 545.12   ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0288.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [338.9582  328.32547 434.3191  323.23047]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0289.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [318.8231  315.93234 591.9439  392.60773]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0290.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [318.68945 306.11472 631.6857  559.67114]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0291.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [316.4478 319.5204 542.9983 597.468 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0292.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [376.1099  423.27533 114.53274 143.18513]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0293.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [338.208   320.1244  296.65042 333.89218]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0294.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [330.61682 360.79373 472.70816 277.18405]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0295.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [326.12573 296.1694  337.87347 403.78424]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0296.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [339.31793 418.98975 374.1086  244.0528 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0297.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [316.4081  320.26398 545.2462  424.39606]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0298.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [317.64285 319.28452 529.4823  545.2101 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0299.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [298.85474 294.09503 546.60516 375.42908]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0300.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [459.66443  366.97943   33.734314  40.101288]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0301.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [299.88925 275.86603 290.94144 467.8912 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0302.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [273.53326 363.19287 180.567   264.30606]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0303.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [321.02612 319.98022 453.0988  535.447  ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0304.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [481.69247 340.32214 242.55325 281.3479 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0305.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [337.21463 298.72696 361.1334  423.16113]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0306.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [514.77136 268.2734  188.12929 359.30173]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0307.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [187.28151 414.53857  82.14576 172.6153 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0308.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [295.53363 310.11887 434.1409  438.2138 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0309.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [300.69904 373.74893 185.467   217.2712 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0310.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [242.7143  334.25775 374.04285 451.42657]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0311.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [416.40973 309.4997  305.13538 151.37312]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0312.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [246.19615 369.72284 206.54056 233.38858]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0313.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [305.64542 326.39084 475.27664 394.34125]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0314.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [353.35492 310.53693 386.04846 327.30072]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0315.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [324.22235 351.66965 455.0199  360.92084]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0316.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [300.9236  390.04825 187.36403 218.12656]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0317.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [311.66135 344.06308 177.90631 171.64752]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0318.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [318.5539  317.6972  467.02222 386.2309 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0319.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [312.9211  344.35544 556.4284  419.18793]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0320.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [269.14288 263.69174 498.47058 399.4084 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0321.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [252.20789 365.8127  122.17511 167.56987]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0322.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [322.07822 376.53812 246.09735 338.16837]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0323.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [253.58298 323.2452  253.55518 303.6115 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0324.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [301.57867 339.07852 470.93225 337.02133]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0325.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [299.00037 316.74838 539.26874 373.52127]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0326.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [246.88812 322.37476 339.06766 407.81616]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0327.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [322.19846 307.86728 623.7777  607.82324]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0328.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [322.6546  333.19202 396.2454  430.21213]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0329.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [314.32437 276.803   101.95604  83.09897]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0330.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [346.1552  192.60048 164.96553 178.16185]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0331.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [433.44904 427.96576 325.16003 313.4735 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0332.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [481.14618 340.61652 241.98256 281.4358 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0333.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [294.6859  302.53613 316.90607 344.15543]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0334.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [312.88412 345.1687  556.5362  421.17062]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0335.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [339.365   317.7728  349.274   441.98196]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0336.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [320.19537 319.6364  588.9263  372.6328 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0337.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [365.90698 295.0829  108.83335 131.03706]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0338.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [371.25928 369.2279  301.4641  429.35974]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0339.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [319.0176  338.75858 359.00986 257.8135 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0340.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [405.98935 289.241   461.4587  558.30054]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0341.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [258.57156 351.94342 345.98022 548.7479 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0342.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [399.379   381.92725 338.55606 291.17044]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0343.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [310.2453  302.36533 502.86694 466.90506]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0344.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [264.28592 326.5545  428.56326 554.3166 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0345.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [327.02405 329.67657 443.9572  442.41208]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0346.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [311.48892 324.76587 522.34753 422.97733]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0347.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [431.68597 371.32227 370.64267 253.43082]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0348.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [298.6111  361.87952 223.15503 237.27846]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0349.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [265.71088 265.24847 492.69455 401.81107]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0350.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [301.24005 329.89978 146.02725 193.42073]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0351.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [451.14896 281.2805  308.67776 217.70784]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0352.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [310.37314 313.1081  518.60724 483.94373]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0353.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [287.31052 292.8507  242.08517 291.86676]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0354.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [195.36868 356.10593 191.96855 232.50555]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0355.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [318.01703 318.69098 585.0179  458.71066]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0356.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [318.95703 321.38245 457.2832  495.19315]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0357.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [399.26385 339.70624 313.66907 226.72623]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0358.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [315.0356  387.48163 382.17413 298.51495]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0359.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [306.3911  364.84158 242.5923  352.48615]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0360.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [448.12317 296.24774 247.59285 192.01308]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0361.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [322.27142 287.88132 248.64865 293.07977]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0362.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [319.3706  432.63565 455.9449  367.61703]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0363.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [448.66943 314.66962 193.72453 245.08218]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0364.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [321.64166 299.62405 490.83344 301.16064]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0365.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [475.67145 466.293   257.01718 276.8786 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0366.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [388.73865 332.5194  193.6399  168.23502]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0367.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [320.16943 320.17053 485.23267 520.39526]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0368.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [308.77704 318.8352  458.3661  386.65298]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0369.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [311.99777 319.20697 440.1518  411.20816]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0370.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [313.74625 496.23163 145.43234  89.74422]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0371.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [248.22874 312.01694 337.78406 327.62073]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0372.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [318.17712 322.3137  458.9191  314.81433]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0373.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [331.70825 315.15985 485.19363 356.70474]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0374.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [350.3553  334.14233 325.8803  343.81567]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0375.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [240.42055 403.01266 453.0624  335.54797]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0376.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [441.00012 391.65588 268.05057 197.0998 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0377.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [441.44092 355.4408  394.05856 318.39972]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0378.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [338.51392 323.0473  286.95883 186.10803]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0379.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [322.84912 394.74493 243.15102 272.90067]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0380.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [316.41855 331.39874 624.3194  447.55383]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0381.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [325.18604 319.3331  478.8341  580.0947 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0382.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [323.93387  90.22018 124.90876 140.26065]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0383.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [163.55417 376.92642 301.88083 362.53726]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0384.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [320.0304  297.23956 600.7394  436.52695]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0385.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [482.46246 297.10107 117.02875 426.00525]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0386.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [214.89832 472.53613 146.49527 166.85295]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0387.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [398.711   326.471   224.06836 273.12894]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0388.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [313.95123 371.77264 290.9222  391.5349 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0389.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [321.15887 318.45334 608.8381  421.9708 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0390.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [325.74582 308.80652 188.69598 373.30856]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0391.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [302.00836 323.71027 244.45471 313.37405]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0392.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [286.42215 236.33539 228.77264 206.61246]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0393.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [310.9123  364.80084 240.86142 352.92334]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0394.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [433.45944 428.0806  324.93518 313.72586]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0395.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [323.86105 427.84988 177.9042  228.87164]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0396.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [534.53253 286.85834 208.84033 357.20535]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0397.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [134.68481 271.94324 244.43842 263.96823]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0398.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [316.63657 315.28143 611.1172  452.02258]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0399.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [320.17822 319.27576 616.86194 346.80664]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0400.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [341.5998  362.5171  355.4317  399.93884]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0401.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [442.78052 447.25528 237.26465 243.26059]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0402.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [313.91837 331.96143  74.69832 108.25034]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0403.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [322.5221  394.7912  244.00298 272.56567]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0404.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [443.5747  326.8194  248.18321 276.90768]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0405.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [315.61603 447.51385 194.01111 189.62439]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0406.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [348.96835 241.72916 321.23444 405.5874 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0407.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [516.9095  411.34058 182.82585 291.11533]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0408.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [414.76245 460.93774 232.91971 264.77512]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0409.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [214.50665 345.73178 210.14223 154.37311]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0410.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [135.1049  274.44403 245.48578 269.52548]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0411.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [253.93451 369.2668  141.13708 192.79187]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0412.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [290.15417 337.54807  76.95313 106.97269]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0413.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [312.7921  372.97    264.0894  286.44055]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0414.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [468.45105 305.989   169.05667 422.4052 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0415.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [339.40277 318.1815  348.6433  442.03333]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0416.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [343.64575 309.5479  357.89233 421.23956]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0417.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [304.94147 308.0395  434.18546 284.72284]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0418.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [456.20905 241.25116 302.93158 364.21497]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0419.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [247.79219 320.21085 335.16995 398.79398]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0420.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 66.02456 251.67154 125.39938 102.72891]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0421.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [281.92264 320.62036 283.69922 295.7155 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0422.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [424.8117  400.774   169.93181 161.3229 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0423.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [332.7203  423.17627 224.29254 275.37982]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0424.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [275.6626  293.11743 192.54956 227.35446]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0425.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [315.71    297.8479  383.0533  590.76166]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0426.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [361.92816 290.08823 199.8468  223.84326]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0427.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [274.92932 267.2631  372.60846 437.2827 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0428.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [303.82806 286.5929  303.25748 380.63705]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0429.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [432.36267 377.76605 376.16718 449.87854]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0430.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [386.6333  303.89194 375.7563  305.55606]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0431.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [319.94336 329.52267 395.4683  439.00732]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0432.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [307.88815 375.97562 404.1717  262.26718]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0433.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [313.07617 321.06958 402.75903 479.39795]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0434.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [320.65253 372.34344 340.6452  321.98834]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0435.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [300.71188 373.75018 185.33644 217.31726]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0436.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [204.36136 288.56012 377.33258 355.71655]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0437.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [204.19127 324.76685 393.3659  469.02716]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0438.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [511.00555 466.03345 223.56789 272.8889 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0439.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [395.45285 298.16827 420.17957 289.76385]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0440.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [195.65225 356.40866 192.52776 234.39543]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0441.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [319.37762 320.38196 449.06552 542.26166]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0442.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [320.087   338.71472 620.60657 522.21014]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0443.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [103.92068 296.06348 185.13939 260.01392]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0444.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [316.62045 369.27548 370.69858 309.31546]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0445.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [347.29877 383.91992 334.87085 295.20197]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0446.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [316.83047 333.8199  472.6782  254.57181]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0447.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [307.7985  369.27496 280.61703 341.16043]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0448.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [441.16458 348.31635 220.79202 274.8817 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0449.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [321.33545 302.03558 356.76666 494.30322]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0450.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [342.74072 312.273   386.38837 410.9918 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0451.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [456.44324 292.03687 357.04352 268.04648]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0452.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [334.48517 303.0476  424.23053 392.47778]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0453.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [345.71558 350.79483 424.66446 364.38815]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0454.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [135.16696 278.35654 245.9065  278.87183]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0455.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [188.70346 348.5065   96.15699 139.44876]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0456.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [318.0138  320.25043 486.44098 543.3393 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0457.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [337.33444 324.36142 479.59418 446.6888 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0458.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [286.75656 364.9743  261.89197 339.81555]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0459.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [319.704   376.81595 482.09567 442.85077]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0460.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [547.8631  351.92844 157.23276 297.59464]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0461.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [327.14078 302.25247 241.42412 284.82974]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0462.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [348.60562 292.8539  256.1597  533.27203]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0463.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [308.02887 320.70813 550.3013  373.239  ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0464.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [347.01038 332.4019  468.07123 539.024  ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0465.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [303.92526 423.17062 335.97235 291.69083]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0466.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [298.3034  387.76178 234.21103 249.69937]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0467.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [292.74405 346.57132 465.9653  471.74384]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0468.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [496.49677 290.99207 274.99414 303.28986]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0469.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [299.1937  317.79218 538.95514 374.42737]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0470.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [512.5116  327.0149  178.14432 214.48529]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0471.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [287.3174  303.46887 341.67468 413.5945 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0472.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [321.4859  314.7742  498.39233 357.622  ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0473.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [322.45703 345.5656  427.4971  302.03387]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0474.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [415.99472 283.05328 351.87946 290.16095]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0475.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [351.0854  366.72986 104.16558 163.74527]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0476.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [296.5593 315.2104 581.2903 400.4852]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0477.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [430.70947 270.60547 227.15283 265.63824]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0478.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [392.53644 316.95767 329.76474 279.29385]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0479.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [105.595795 296.8437   188.17932  260.78815 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0480.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [530.18207 357.15094 157.89258 286.2882 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0481.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [279.68256 349.4788  315.02576 284.24557]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0482.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [333.38196 336.2019  332.415   411.7586 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0483.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [287.294   352.9345  351.0667  459.30182]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0484.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [350.73026 335.59726 289.24045 410.79504]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0485.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [337.5897  268.91406 347.35535 410.1728 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0486.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [336.67853 305.80582 522.993   406.3901 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0487.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [345.7733  392.80655 223.43172 340.85498]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0488.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [212.87712 393.5933  351.45288 242.88486]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0489.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [294.7273  303.707   323.6514  328.06888]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0490.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [330.56308 336.98383  80.19161 107.73114]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0491.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [282.30444 320.37744 284.49496 295.2056 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0492.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [321.63773 304.7276  613.92633 436.0255 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0493.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [401.75308 126.39724 131.85217 199.04166]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0494.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [319.58557 378.13824 482.17188 445.20572]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0495.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [336.65585 328.11914 531.35736 296.6305 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0496.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [315.73798 427.95142 194.38657 229.32648]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0497.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [361.8308  290.07928 200.1867  223.97401]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0498.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [328.31387 298.75433 568.6841  595.9212 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0499.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [345.0563  336.62616 222.22414 146.10542]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0500.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [349.32205 335.94965 256.11987 471.06766]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0501.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [280.38474 357.20828 271.11002 305.22275]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0502.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [145.38408 298.87677 252.78032 280.0924 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0503.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [342.67383 327.06476 241.93625 352.74933]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0504.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [325.5695  317.84146 574.6953  574.78674]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0505.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [319.3527  318.8608  443.67877 339.44946]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0506.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [337.4617  322.00494 383.60306 412.89984]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0507.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [461.46875 265.7127  314.59576 358.95535]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0508.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [187.74051 323.92972 285.49164 385.10526]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0509.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [330.9645  313.99512 431.8598  506.01703]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0510.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [305.02148 298.7344  330.38724 176.26645]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0511.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [484.3616   323.76825   59.072895  74.12784 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0512.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [299.7237  275.7569  290.75705 467.6981 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0513.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [273.09604 377.89667 216.69254 268.50528]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0514.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [318.7061  339.36957 611.60095 444.7375 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0515.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [300.07272 274.4075  274.51154 434.74927]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0516.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [302.4672  310.41562 529.34766 455.72705]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0517.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [312.98492 345.28265 556.48224 421.24695]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0518.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [361.41895 327.25555 356.69186 292.16907]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0519.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [402.60974 307.20215 424.3949  557.9231 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0520.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [442.76218 452.67392  71.28998 172.0983 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0521.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [173.02397 323.92715 199.3708  223.77115]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0522.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [328.86066 288.7605  462.08783 559.34393]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0523.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [394.28583 344.45145 365.4818  441.65674]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0524.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [318.5915  300.37137 487.1727  333.66187]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0525.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [343.0949  310.78574 440.4234  611.20447]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0526.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 92.20636 357.16437 167.21053 241.72685]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0527.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [231.94824 348.28278 440.30646 358.37512]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0528.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [336.45673 388.3087  407.70428 473.46988]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0529.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [289.60193 319.51132 301.83887 361.80966]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0530.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [340.03125 351.3196  202.98628 325.96423]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0531.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [326.80817 381.27792 296.65128 345.6009 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0532.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [208.15134 348.02332 301.8466  224.35513]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0533.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [298.30225 199.70398 378.4367  363.8533 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0534.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [319.34766 321.86386 620.2488  448.5164 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0535.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [305.1571  304.18546 250.31029 358.3995 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0536.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [312.16635 324.08057 413.47745 288.84134]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0537.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [183.59961 377.78226 144.78159 195.84358]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0538.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [480.64175 289.97498 273.5524  326.7865 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0539.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [375.26306 314.53387 458.093   510.1987 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0540.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [195.54594 356.69888 191.88614 234.39384]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0541.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [144.3475  278.57288 255.50586 206.5951 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0542.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [535.557   463.09967  91.6006  151.93575]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0543.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [283.07065 348.96393 506.5071  336.56787]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0544.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [316.66043 335.04156 609.0819  437.13882]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0545.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [302.11853 269.37894 127.10862 161.2967 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0546.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [316.36835 369.2885  370.67746 309.5699 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0547.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [315.46533 402.67288 471.11847 293.30875]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0548.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [316.5845  306.33548 621.67926 359.6198 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0549.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [320.10056 319.70676 518.3296  318.30176]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0550.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [399.9272  344.4255  289.76645 332.9579 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0551.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [365.16425 302.89026  74.01135 155.89238]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0552.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [408.8142  380.11005 174.98085 211.80559]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0553.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [280.36557 263.46225 288.65994 269.68936]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0554.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [450.13583 321.85635 287.07355 362.6974 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0555.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [474.98245 301.53387 233.89862 371.6502 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0556.jpeg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [422.80292 265.2317  149.86087 148.58524]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0557.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [197.55984 316.12482 394.83978 304.41443]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0558.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [355.92816 306.4464  241.48065 304.49252]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0559.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [328.31256 310.38855 251.58112 196.80351]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0560.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [481.01712 340.7845  242.73253 281.0235 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0561.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [411.51187 391.56213 368.50305 202.68378]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0562.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [281.94202 320.60397 283.82922 295.71454]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0563.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [427.65625 247.70584 222.36386 191.8538 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0564.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [469.84412 279.38965 285.4933  548.4157 ]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train/0565.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [330.82208 305.52722 374.75528 473.72696]\n",
+            "\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/train.cache\n"
+          ]
+        },
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "\n",
+            "\u001b[34m\u001b[1mval: \u001b[0mScanning /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/val... 139 images, 0 backgrounds, 0 corrupt: 100%|██████████| 139/139 [00:00<00:00, 5359.32it/s]"
+          ]
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /Users/ischknv/Documents/GitHub/miem/aimm/lab-2/dataset/val.cache\n"
+          ]
+        },
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "\n"
+          ]
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Plotting labels to /Users/ischknv/Documents/GitHub/miem/aimm/runs/detect/train/labels.jpg... \n",
+            "\u001b[34m\u001b[1moptimizer:\u001b[0m 'optimizer=auto' found, ignoring 'lr0=0.01' and 'momentum=0.937' and determining best 'optimizer', 'lr0' and 'momentum' automatically... \n",
+            "\u001b[34m\u001b[1moptimizer:\u001b[0m AdamW(lr=0.001667, momentum=0.9) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0005), 63 bias(decay=0.0)\n",
+            "Image sizes 640 train, 640 val\n",
+            "Using 0 dataloader workers\n",
+            "Logging results to \u001b[1m/Users/ischknv/Documents/GitHub/miem/aimm/runs/detect/train\u001b[0m\n",
+            "Starting training for 50 epochs...\n",
+            "\n",
+            "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
+          ]
+        },
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "  0%|          | 0/9 [00:10<?, ?it/s]\n"
           ]
         },
         {
-          "ename": "RuntimeError",
-          "evalue": "Dataset 'data.yaml' error ❌ \nDataset 'data.yaml' images not found ⚠️, missing path '/Users/ischknv/Documents/GitHub/miem/datasets/val/images'\nNote dataset download directory is '/Users/ischknv/Documents/GitHub/miem/datasets'. You can update this in '/Users/ischknv/Library/Application Support/Ultralytics/settings.json'",
+          "ename": "KeyboardInterrupt",
+          "evalue": "",
           "output_type": "error",
           "traceback": [
             "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-            "\u001b[0;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
-            "File \u001b[0;32m~/Documents/GitHub/miem/aimm/.venv/lib/python3.12/site-packages/ultralytics/engine/trainer.py:557\u001b[0m, in \u001b[0;36mBaseTrainer.get_dataset\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    551\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39margs\u001b[38;5;241m.\u001b[39mdata\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m)[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m] \u001b[38;5;129;01min\u001b[39;00m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124myaml\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124myml\u001b[39m\u001b[38;5;124m\"\u001b[39m} \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39margs\u001b[38;5;241m.\u001b[39mtask \u001b[38;5;129;01min\u001b[39;00m {\n\u001b[1;32m    552\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdetect\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m    553\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msegment\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m    554\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpose\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m    555\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mobb\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m    556\u001b[0m }:\n\u001b[0;32m--> 557\u001b[0m     data \u001b[38;5;241m=\u001b[39m \u001b[43mcheck_det_dataset\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43margs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdata\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    558\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124myaml_file\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m data:\n",
-            "File \u001b[0;32m~/Documents/GitHub/miem/aimm/.venv/lib/python3.12/site-packages/ultralytics/data/utils.py:329\u001b[0m, in \u001b[0;36mcheck_det_dataset\u001b[0;34m(dataset, autodownload)\u001b[0m\n\u001b[1;32m    328\u001b[0m     m \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124mNote dataset download directory is \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mDATASETS_DIR\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m. You can update this in \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mSETTINGS_FILE\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m--> 329\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mFileNotFoundError\u001b[39;00m(m)\n\u001b[1;32m    330\u001b[0m t \u001b[38;5;241m=\u001b[39m time\u001b[38;5;241m.\u001b[39mtime()\n",
-            "\u001b[0;31mFileNotFoundError\u001b[0m: \nDataset 'data.yaml' images not found ⚠️, missing path '/Users/ischknv/Documents/GitHub/miem/datasets/val/images'\nNote dataset download directory is '/Users/ischknv/Documents/GitHub/miem/datasets'. You can update this in '/Users/ischknv/Library/Application Support/Ultralytics/settings.json'",
-            "\nThe above exception was the direct cause of the following exception:\n",
-            "\u001b[0;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
-            "Cell \u001b[0;32mIn[88], line 2\u001b[0m\n\u001b[1;32m      1\u001b[0m get_ipython()\u001b[38;5;241m.\u001b[39mrun_line_magic(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcd\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{HOME}\u001b[39;00m\u001b[38;5;124m/dataset\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m----> 2\u001b[0m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrain\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mdata.yaml\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbatch\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m16\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mepochs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m50\u001b[39;49m\u001b[43m)\u001b[49m\n",
-            "File \u001b[0;32m~/Documents/GitHub/miem/aimm/.venv/lib/python3.12/site-packages/ultralytics/engine/model.py:796\u001b[0m, in \u001b[0;36mModel.train\u001b[0;34m(self, trainer, **kwargs)\u001b[0m\n\u001b[1;32m    793\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m args\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mresume\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[1;32m    794\u001b[0m     args[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mresume\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mckpt_path\n\u001b[0;32m--> 796\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtrainer \u001b[38;5;241m=\u001b[39m \u001b[43m(\u001b[49m\u001b[43mtrainer\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01mor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_smart_load\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtrainer\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\u001b[43m(\u001b[49m\u001b[43moverrides\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m_callbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    797\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m args\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mresume\u001b[39m\u001b[38;5;124m\"\u001b[39m):  \u001b[38;5;66;03m# manually set model only if not resuming\u001b[39;00m\n\u001b[1;32m    798\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtrainer\u001b[38;5;241m.\u001b[39mmodel \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtrainer\u001b[38;5;241m.\u001b[39mget_model(weights\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mckpt \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m, cfg\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel\u001b[38;5;241m.\u001b[39myaml)\n",
-            "File \u001b[0;32m~/Documents/GitHub/miem/aimm/.venv/lib/python3.12/site-packages/ultralytics/engine/trainer.py:133\u001b[0m, in \u001b[0;36mBaseTrainer.__init__\u001b[0;34m(self, cfg, overrides, _callbacks)\u001b[0m\n\u001b[1;32m    131\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel \u001b[38;5;241m=\u001b[39m check_model_file_from_stem(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39margs\u001b[38;5;241m.\u001b[39mmodel)  \u001b[38;5;66;03m# add suffix, i.e. yolov8n -> yolov8n.pt\u001b[39;00m\n\u001b[1;32m    132\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m torch_distributed_zero_first(LOCAL_RANK):  \u001b[38;5;66;03m# avoid auto-downloading dataset multiple times\u001b[39;00m\n\u001b[0;32m--> 133\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtrainset, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtestset \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_dataset\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    134\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mema \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    136\u001b[0m \u001b[38;5;66;03m# Optimization utils init\u001b[39;00m\n",
-            "File \u001b[0;32m~/Documents/GitHub/miem/aimm/.venv/lib/python3.12/site-packages/ultralytics/engine/trainer.py:561\u001b[0m, in \u001b[0;36mBaseTrainer.get_dataset\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    559\u001b[0m             \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39margs\u001b[38;5;241m.\u001b[39mdata \u001b[38;5;241m=\u001b[39m data[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124myaml_file\u001b[39m\u001b[38;5;124m\"\u001b[39m]  \u001b[38;5;66;03m# for validating 'yolo train data=url.zip' usage\u001b[39;00m\n\u001b[1;32m    560\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m--> 561\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mRuntimeError\u001b[39;00m(emojis(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDataset \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mclean_url(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39margs\u001b[38;5;241m.\u001b[39mdata)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m error ❌ \u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[1;32m    562\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdata \u001b[38;5;241m=\u001b[39m data\n\u001b[1;32m    563\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m data[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtrain\u001b[39m\u001b[38;5;124m\"\u001b[39m], data\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mval\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m data\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtest\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
-            "\u001b[0;31mRuntimeError\u001b[0m: Dataset 'data.yaml' error ❌ \nDataset 'data.yaml' images not found ⚠️, missing path '/Users/ischknv/Documents/GitHub/miem/datasets/val/images'\nNote dataset download directory is '/Users/ischknv/Documents/GitHub/miem/datasets'. You can update this in '/Users/ischknv/Library/Application Support/Ultralytics/settings.json'"
+            "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+            "Cell \u001b[0;32mIn[99], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrain\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mHOME\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m/dataset/data.yaml\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdevice\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmps\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbatch\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m16\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mepochs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m50\u001b[39;49m\u001b[43m)\u001b[49m\n",
+            "File \u001b[0;32m~/Documents/GitHub/miem/aimm/.venv/lib/python3.12/site-packages/ultralytics/engine/model.py:802\u001b[0m, in \u001b[0;36mModel.train\u001b[0;34m(self, trainer, **kwargs)\u001b[0m\n\u001b[1;32m    799\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtrainer\u001b[38;5;241m.\u001b[39mmodel\n\u001b[1;32m    801\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtrainer\u001b[38;5;241m.\u001b[39mhub_session \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msession  \u001b[38;5;66;03m# attach optional HUB session\u001b[39;00m\n\u001b[0;32m--> 802\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrainer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrain\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    803\u001b[0m \u001b[38;5;66;03m# Update model and cfg after training\u001b[39;00m\n\u001b[1;32m    804\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m RANK \u001b[38;5;129;01min\u001b[39;00m {\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m0\u001b[39m}:\n",
+            "File \u001b[0;32m~/Documents/GitHub/miem/aimm/.venv/lib/python3.12/site-packages/ultralytics/engine/trainer.py:207\u001b[0m, in \u001b[0;36mBaseTrainer.train\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    204\u001b[0m         ddp_cleanup(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28mstr\u001b[39m(file))\n\u001b[1;32m    206\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 207\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_do_train\u001b[49m\u001b[43m(\u001b[49m\u001b[43mworld_size\u001b[49m\u001b[43m)\u001b[49m\n",
+            "File \u001b[0;32m~/Documents/GitHub/miem/aimm/.venv/lib/python3.12/site-packages/ultralytics/engine/trainer.py:385\u001b[0m, in \u001b[0;36mBaseTrainer._do_train\u001b[0;34m(self, world_size)\u001b[0m\n\u001b[1;32m    383\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m autocast(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mamp):\n\u001b[1;32m    384\u001b[0m     batch \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpreprocess_batch(batch)\n\u001b[0;32m--> 385\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mloss, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mloss_items \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbatch\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    386\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m RANK \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m    387\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mloss \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m=\u001b[39m world_size\n",
+            "File \u001b[0;32m~/Documents/GitHub/miem/aimm/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py:1736\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1734\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1735\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1736\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+            "File \u001b[0;32m~/Documents/GitHub/miem/aimm/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py:1747\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1742\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1743\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1744\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1745\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1746\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1747\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1749\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   1750\u001b[0m called_always_called_hooks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mset\u001b[39m()\n",
+            "File \u001b[0;32m~/Documents/GitHub/miem/aimm/.venv/lib/python3.12/site-packages/ultralytics/nn/tasks.py:111\u001b[0m, in \u001b[0;36mBaseModel.forward\u001b[0;34m(self, x, *args, **kwargs)\u001b[0m\n\u001b[1;32m     97\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m     98\u001b[0m \u001b[38;5;124;03mPerform forward pass of the model for either training or inference.\u001b[39;00m\n\u001b[1;32m     99\u001b[0m \n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    108\u001b[0m \u001b[38;5;124;03m    (torch.Tensor): Loss if x is a dict (training), or network predictions (inference).\u001b[39;00m\n\u001b[1;32m    109\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    110\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(x, \u001b[38;5;28mdict\u001b[39m):  \u001b[38;5;66;03m# for cases of training and validating while training.\u001b[39;00m\n\u001b[0;32m--> 111\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mloss\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    112\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpredict(x, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
+            "File \u001b[0;32m~/Documents/GitHub/miem/aimm/.venv/lib/python3.12/site-packages/ultralytics/nn/tasks.py:293\u001b[0m, in \u001b[0;36mBaseModel.loss\u001b[0;34m(self, batch, preds)\u001b[0m\n\u001b[1;32m    290\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcriterion \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39minit_criterion()\n\u001b[1;32m    292\u001b[0m preds \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mforward(batch[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mimg\u001b[39m\u001b[38;5;124m\"\u001b[39m]) \u001b[38;5;28;01mif\u001b[39;00m preds \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m preds\n\u001b[0;32m--> 293\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcriterion\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpreds\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbatch\u001b[49m\u001b[43m)\u001b[49m\n",
+            "File \u001b[0;32m~/Documents/GitHub/miem/aimm/.venv/lib/python3.12/site-packages/ultralytics/utils/loss.py:253\u001b[0m, in \u001b[0;36mv8DetectionLoss.__call__\u001b[0;34m(self, preds, batch)\u001b[0m\n\u001b[1;32m    251\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m fg_mask\u001b[38;5;241m.\u001b[39msum():\n\u001b[1;32m    252\u001b[0m     target_bboxes \u001b[38;5;241m/\u001b[39m\u001b[38;5;241m=\u001b[39m stride_tensor\n\u001b[0;32m--> 253\u001b[0m     loss[\u001b[38;5;241m0\u001b[39m], loss[\u001b[38;5;241m2\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbbox_loss\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    254\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpred_distri\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpred_bboxes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43manchor_points\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtarget_bboxes\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtarget_scores\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtarget_scores_sum\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfg_mask\u001b[49m\n\u001b[1;32m    255\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    257\u001b[0m loss[\u001b[38;5;241m0\u001b[39m] \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhyp\u001b[38;5;241m.\u001b[39mbox  \u001b[38;5;66;03m# box gain\u001b[39;00m\n\u001b[1;32m    258\u001b[0m loss[\u001b[38;5;241m1\u001b[39m] \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhyp\u001b[38;5;241m.\u001b[39mcls  \u001b[38;5;66;03m# cls gain\u001b[39;00m\n",
+            "File \u001b[0;32m~/Documents/GitHub/miem/aimm/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py:1736\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1734\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m   1735\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1736\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+            "File \u001b[0;32m~/Documents/GitHub/miem/aimm/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py:1747\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m   1742\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m   1743\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m   1744\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m   1745\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m   1746\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1747\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1749\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   1750\u001b[0m called_always_called_hooks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mset\u001b[39m()\n",
+            "File \u001b[0;32m~/Documents/GitHub/miem/aimm/.venv/lib/python3.12/site-packages/ultralytics/utils/loss.py:103\u001b[0m, in \u001b[0;36mBboxLoss.forward\u001b[0;34m(self, pred_dist, pred_bboxes, anchor_points, target_bboxes, target_scores, target_scores_sum, fg_mask)\u001b[0m\n\u001b[1;32m    101\u001b[0m weight \u001b[38;5;241m=\u001b[39m target_scores\u001b[38;5;241m.\u001b[39msum(\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m)[fg_mask]\u001b[38;5;241m.\u001b[39munsqueeze(\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m)\n\u001b[1;32m    102\u001b[0m iou \u001b[38;5;241m=\u001b[39m bbox_iou(pred_bboxes[fg_mask], target_bboxes[fg_mask], xywh\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m, CIoU\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m--> 103\u001b[0m loss_iou \u001b[38;5;241m=\u001b[39m \u001b[43m(\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m1.0\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m-\u001b[39;49m\u001b[43m \u001b[49m\u001b[43miou\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mweight\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msum\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;241m/\u001b[39m target_scores_sum\n\u001b[1;32m    105\u001b[0m \u001b[38;5;66;03m# DFL loss\u001b[39;00m\n\u001b[1;32m    106\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdfl_loss:\n",
+            "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
           ]
         }
       ],
       "source": [
-        "%cd {HOME}/dataset\n",
-        "model.train(data=\"data.yaml\", device=\"mps\", batch=16, epochs=50)"
+        "model.train(data=f\"{HOME}/dataset/data.yaml\", device=\"mps\", batch=16, epochs=50)"
       ]
     }
   ],