File size: 76,852 Bytes
17af213 | 1 | {"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.12.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"colab":{"provenance":[],"gpuType":"T4"},"accelerator":"GPU","kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceType":"datasetVersion","sourceId":16128353,"datasetId":10341935,"databundleVersionId":17101598},{"sourceType":"modelInstanceVersion","sourceId":862260,"databundleVersionId":17123636,"modelInstanceId":655505,"modelId":667478}],"dockerImageVersionId":31329,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# YOLO_Pieces_Fine-Tuning\n\n","metadata":{"id":"YwNgvZP2lba6"}},{"cell_type":"code","source":"!pip install ultralytics","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"_g56Cc950VMz","outputId":"34f5b368-1fef-4960-bf2f-a69ed4656e1e"},"outputs":[{"output_type":"stream","name":"stdout","text":["Requirement already satisfied: ultralytics in /usr/local/lib/python3.12/dist-packages (8.4.46)\n","Requirement already satisfied: numpy>=1.23.0 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (2.0.2)\n","Requirement already satisfied: matplotlib>=3.3.0 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (3.10.0)\n","Requirement already satisfied: opencv-python>=4.6.0 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (4.13.0.92)\n","Requirement already satisfied: pillow>=7.1.2 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (12.2.0)\n","Requirement already satisfied: pyyaml>=5.3.1 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (6.0.3)\n","Requirement already satisfied: requests>=2.23.0 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (2.32.4)\n","Requirement already satisfied: scipy>=1.4.1 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (1.16.3)\n","Requirement already satisfied: torch>=1.8.0 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (2.9.0+cpu)\n","Requirement already satisfied: torchvision>=0.9.0 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (0.24.0+cpu)\n","Requirement already satisfied: psutil>=5.8.0 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (5.9.5)\n","Requirement already satisfied: polars>=0.20.0 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (1.40.1)\n","Requirement already satisfied: ultralytics-thop>=2.0.18 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (2.0.19)\n","Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->ultralytics) (1.3.3)\n","Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->ultralytics) (0.12.1)\n","Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->ultralytics) (4.62.1)\n","Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->ultralytics) (1.5.0)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->ultralytics) (26.1)\n","Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->ultralytics) (3.3.2)\n","Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->ultralytics) (2.9.0.post0)\n","Requirement already satisfied: polars-runtime-32==1.40.1 in /usr/local/lib/python3.12/dist-packages (from polars>=0.20.0->ultralytics) (1.40.1)\n","Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests>=2.23.0->ultralytics) (3.4.7)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests>=2.23.0->ultralytics) (3.13)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests>=2.23.0->ultralytics) (2.5.0)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests>=2.23.0->ultralytics) (2026.4.22)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (3.29.0)\n","Requirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (4.15.0)\n","Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (75.2.0)\n","Requirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (1.14.0)\n","Requirement already satisfied: networkx>=2.5.1 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (3.6.1)\n","Requirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (3.1.6)\n","Requirement already satisfied: fsspec>=0.8.5 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (2026.2.0)\n","Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.7->matplotlib>=3.3.0->ultralytics) (1.17.0)\n","Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy>=1.13.3->torch>=1.8.0->ultralytics) (1.3.0)\n","Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->torch>=1.8.0->ultralytics) (3.0.3)\n"]}],"execution_count":null},{"cell_type":"code","source":"!yolo segment train data=<path_to_carparts-seg.yaml> model=yolo11n-seg.pt epochs=30 imgsz=640","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Xw_peyZh0jna","outputId":"d81f16aa-b393-4113-cb27-440703993f2b"},"outputs":[{"output_type":"stream","name":"stdout","text":["\r\u001b[KDownloading https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo11n-seg.pt to 'yolo11n-seg.pt': 100% ━━━━━━━━━━━━ 5.9MB 120.5MB/s 0.0s\n","Ultralytics 8.4.41 🚀 Python-3.12.13 torch-2.10.0+cu128 CUDA:0 (Tesla T4, 14913MiB)\n","\u001b[34m\u001b[1mengine/trainer: \u001b[0magnostic_nms=False, amp=True, angle=1.0, augment=False, auto_augment=randaugment, batch=16, bgr=0.0, box=7.5, cache=False, cfg=None, classes=None, close_mosaic=10, cls=0.5, cls_pw=0.0, compile=False, conf=None, copy_paste=0.0, copy_paste_mode=flip, cos_lr=False, cutmix=0.0, data=carparts-seg.yaml, degrees=0.0, deterministic=True, device=None, dfl=1.5, dnn=False, dropout=0.0, dynamic=False, embed=None, end2end=None, epochs=30, erasing=0.4, exist_ok=False, fliplr=0.5, flipud=0.0, format=torchscript, fraction=1.0, freeze=None, half=False, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, imgsz=640, int8=False, iou=0.7, keras=False, kobj=1.0, line_width=None, lr0=0.01, lrf=0.01, mask_ratio=4, max_det=300, mixup=0.0, mode=train, model=yolo11n-seg.pt, momentum=0.937, mosaic=1.0, multi_scale=0.0, name=train, nbs=64, nms=False, opset=None, optimize=False, optimizer=auto, overlap_mask=True, patience=100, perspective=0.0, plots=True, pose=12.0, pretrained=True, profile=False, project=None, rect=False, resume=False, retina_masks=False, rle=1.0, save=True, save_conf=False, save_crop=False, save_dir=/content/runs/segment/train, save_frames=False, save_json=False, save_period=-1, save_txt=False, scale=0.5, seed=0, shear=0.0, show=False, show_boxes=True, show_conf=True, show_labels=True, simplify=True, single_cls=False, source=None, split=val, stream_buffer=False, task=segment, time=None, tracker=botsort.yaml, translate=0.1, val=True, verbose=True, vid_stride=1, visualize=False, warmup_bias_lr=0.1, warmup_epochs=3.0, warmup_momentum=0.8, weight_decay=0.0005, workers=8, workspace=None\n","\n","WARNING ⚠️ Dataset 'carparts-seg.yaml' images not found, missing path '/content/datasets/carparts-seg/images/val'\n","\u001b[KDownloading https://ultralytics.com/assets/carparts-seg.zip to '/content/datasets/carparts-seg.zip': 100% ━━━━━━━━━━━━ 133.1MB 79.1MB/s 1.7s\n","\u001b[KUnzipping /content/datasets/carparts-seg.zip to /content/datasets/carparts-seg...: 100% ━━━━━━━━━━━━ 7675/7675 4.4Kfiles/s 1.8s\n","Dataset download success ✅ (3.8s), saved to \u001b[1m/content/datasets\u001b[0m\n","\n","\u001b[KDownloading https://ultralytics.com/assets/Arial.ttf to '/root/.config/Ultralytics/Arial.ttf': 100% ━━━━━━━━━━━━ 755.1KB 27.7MB/s 0.0s\n","Overriding model.yaml nc=80 with nc=23\n","\n"," from n params module arguments \n"," 0 -1 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2] \n"," 1 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2] \n"," 2 -1 1 6640 ultralytics.nn.modules.block.C3k2 [32, 64, 1, False, 0.25] \n"," 3 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2] \n"," 4 -1 1 26080 ultralytics.nn.modules.block.C3k2 [64, 128, 1, False, 0.25] \n"," 5 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2] \n"," 6 -1 1 87040 ultralytics.nn.modules.block.C3k2 [128, 128, 1, True] \n"," 7 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2] \n"," 8 -1 1 346112 ultralytics.nn.modules.block.C3k2 [256, 256, 1, True] \n"," 9 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5] \n"," 10 -1 1 249728 ultralytics.nn.modules.block.C2PSA [256, 256, 1] \n"," 11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n"," 12 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1] \n"," 13 -1 1 111296 ultralytics.nn.modules.block.C3k2 [384, 128, 1, False] \n"," 14 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n"," 15 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1] \n"," 16 -1 1 32096 ultralytics.nn.modules.block.C3k2 [256, 64, 1, False] \n"," 17 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2] \n"," 18 [-1, 13] 1 0 ultralytics.nn.modules.conv.Concat [1] \n"," 19 -1 1 86720 ultralytics.nn.modules.block.C3k2 [192, 128, 1, False] \n"," 20 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2] \n"," 21 [-1, 10] 1 0 ultralytics.nn.modules.conv.Concat [1] \n"," 22 -1 1 378880 ultralytics.nn.modules.block.C3k2 [384, 256, 1, True] \n"," 23 [16, 19, 22] 1 687925 ultralytics.nn.modules.head.Segment [23, 32, 64, 16, None, [64, 128, 256]]\n","YOLO11n-seg summary: 204 layers, 2,847,093 parameters, 2,847,077 gradients, 9.8 GFLOPs\n","\n","Transferred 510/561 items from pretrained weights\n","Freezing layer 'model.23.dfl.conv.weight'\n","\u001b[34m\u001b[1mAMP: \u001b[0mrunning Automatic Mixed Precision (AMP) checks...\n","\u001b[KDownloading https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26n.pt to 'yolo26n.pt': 100% ━━━━━━━━━━━━ 5.3MB 108.1MB/s 0.0s\n","\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n","\u001b[34m\u001b[1mtrain: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 1171.4±481.3 MB/s, size: 35.2 KB)\n","\u001b[K\u001b[34m\u001b[1mtrain: \u001b[0mScanning /content/datasets/carparts-seg/labels/train... 3156 images, 116 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 3156/3156 1.4Kit/s 2.3s\n","\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /content/datasets/carparts-seg/labels/train.cache\n","\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01, method='weighted_average', num_output_channels=3), CLAHE(p=0.01, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8))\n","\u001b[34m\u001b[1mval: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 442.4±91.0 MB/s, size: 37.3 KB)\n","\u001b[K\u001b[34m\u001b[1mval: \u001b[0mScanning /content/datasets/carparts-seg/labels/val... 401 images, 12 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 401/401 778.4it/s 0.5s\n","\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /content/datasets/carparts-seg/labels/val.cache\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=0.00037, momentum=0.9) with parameter groups 90 weight(decay=0.0), 101 weight(decay=0.0005), 100 bias(decay=0.0)\n","Plotting labels to /content/runs/segment/train/labels.jpg... \n","Image sizes 640 train, 640 val\n","Using 2 dataloader workers\n","Logging results to \u001b[1m/content/runs/segment/train\u001b[0m\n","Starting training for 30 epochs...\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 1/30 3.18G 1.272 2.63 3.988 1.372 0 31 640: 100% ━━━━━━━━━━━━ 198/198 1.8it/s 1:47\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 1.1it/s 12.1s\n"," all 401 2042 0.562 0.151 0.15 0.109 0.584 0.148 0.155 0.105\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 2/30 3.79G 1.12 1.991 2.582 1.224 0 24 640: 100% ━━━━━━━━━━━━ 198/198 2.3it/s 1:25\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.1it/s 6.1s\n"," all 401 2042 0.473 0.455 0.336 0.247 0.473 0.449 0.337 0.229\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 3/30 3.79G 1.022 1.801 1.816 1.155 0 54 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:22\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.0it/s 6.5s\n"," all 401 2042 0.368 0.568 0.441 0.33 0.37 0.57 0.445 0.31\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 4/30 3.79G 0.9665 1.706 1.554 1.115 0 26 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:22\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.2it/s 5.8s\n"," all 401 2042 0.537 0.535 0.481 0.368 0.539 0.539 0.484 0.342\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 5/30 3.79G 0.922 1.629 1.419 1.094 0 27 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:23\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.3it/s 5.7s\n"," all 401 2042 0.51 0.619 0.521 0.401 0.508 0.614 0.518 0.378\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 6/30 3.79G 0.8909 1.547 1.281 1.072 0 31 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:22\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 1.9it/s 6.8s\n"," all 401 2042 0.464 0.718 0.572 0.451 0.466 0.719 0.582 0.421\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 7/30 3.79G 0.8667 1.5 1.224 1.055 0 31 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:22\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.1it/s 6.1s\n"," all 401 2042 0.444 0.7 0.545 0.426 0.44 0.702 0.551 0.408\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 8/30 3.79G 0.851 1.463 1.178 1.049 0 43 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:21\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.2it/s 5.8s\n"," all 401 2042 0.433 0.714 0.5 0.395 0.434 0.711 0.506 0.375\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 9/30 3.79G 0.8328 1.437 1.125 1.043 0 30 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:22\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.0it/s 6.5s\n"," all 401 2042 0.458 0.662 0.525 0.417 0.459 0.664 0.532 0.402\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 10/30 3.79G 0.8119 1.387 1.074 1.031 0 33 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:22\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.1it/s 6.2s\n"," all 401 2042 0.45 0.684 0.528 0.423 0.453 0.679 0.529 0.406\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 11/30 3.79G 0.805 1.382 1.058 1.027 0 54 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:22\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.4it/s 5.3s\n"," all 401 2042 0.518 0.772 0.61 0.497 0.516 0.772 0.619 0.475\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 12/30 3.79G 0.7904 1.346 1.006 1.02 0 45 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:21\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.1it/s 6.2s\n"," all 401 2042 0.559 0.784 0.653 0.527 0.562 0.78 0.655 0.505\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 13/30 3.79G 0.7852 1.332 0.9949 1.014 0 40 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:21\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.5it/s 5.2s\n"," all 401 2042 0.577 0.787 0.652 0.527 0.579 0.785 0.653 0.5\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 14/30 3.79G 0.7741 1.315 0.9612 1.011 0 39 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:23\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.4it/s 5.5s\n"," all 401 2042 0.538 0.688 0.609 0.497 0.541 0.688 0.612 0.48\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 15/30 3.79G 0.7625 1.286 0.9468 1.001 0 42 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:22\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.0it/s 6.4s\n"," all 401 2042 0.577 0.773 0.66 0.538 0.578 0.774 0.664 0.522\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 16/30 3.79G 0.7518 1.271 0.9141 0.9958 0 56 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:21\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.5it/s 5.3s\n"," all 401 2042 0.591 0.816 0.68 0.549 0.59 0.819 0.685 0.531\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 17/30 3.79G 0.7426 1.248 0.8917 0.9965 0 35 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:21\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.0it/s 6.5s\n"," all 401 2042 0.56 0.775 0.645 0.527 0.561 0.774 0.645 0.509\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 18/30 3.79G 0.7329 1.237 0.864 0.9881 0 45 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:21\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.3it/s 5.5s\n"," all 401 2042 0.554 0.804 0.644 0.53 0.555 0.789 0.652 0.515\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 19/30 3.79G 0.7275 1.225 0.8615 0.9867 0 46 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:22\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.3it/s 5.6s\n"," all 401 2042 0.558 0.744 0.656 0.542 0.562 0.747 0.66 0.522\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 20/30 3.79G 0.7136 1.206 0.8378 0.9821 0 49 640: 100% ━━━━━━━━━━━━ 198/198 2.4it/s 1:22\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.1it/s 6.3s\n"," all 401 2042 0.615 0.812 0.708 0.581 0.621 0.815 0.714 0.567\n","Closing dataloader mosaic\n","\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01, method='weighted_average', num_output_channels=3), CLAHE(p=0.01, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8))\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 21/30 3.79G 0.6475 1.072 0.7589 0.9619 0 18 640: 100% ━━━━━━━━━━━━ 198/198 2.8it/s 1:11\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.2it/s 6.0s\n"," all 401 2042 0.567 0.789 0.645 0.538 0.576 0.8 0.654 0.521\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 22/30 3.79G 0.6374 1.034 0.717 0.9582 0 33 640: 100% ━━━━━━━━━━━━ 198/198 2.9it/s 1:07\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.5it/s 5.1s\n"," all 401 2042 0.591 0.824 0.683 0.56 0.591 0.822 0.681 0.544\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 23/30 3.79G 0.6236 1.005 0.6925 0.95 0 12 640: 100% ━━━━━━━━━━━━ 198/198 2.9it/s 1:07\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.1it/s 6.2s\n"," all 401 2042 0.545 0.841 0.645 0.539 0.55 0.847 0.653 0.526\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 24/30 3.79G 0.61 0.9819 0.6705 0.9393 0 25 640: 100% ━━━━━━━━━━━━ 198/198 2.9it/s 1:08\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.5it/s 5.1s\n"," all 401 2042 0.607 0.813 0.69 0.577 0.613 0.815 0.699 0.565\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 25/30 3.79G 0.6004 0.9691 0.6591 0.932 0 22 640: 100% ━━━━━━━━━━━━ 198/198 2.9it/s 1:08\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.1it/s 6.1s\n"," all 401 2042 0.537 0.793 0.637 0.533 0.544 0.801 0.641 0.518\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 26/30 3.79G 0.5877 0.9532 0.6382 0.9275 0 20 640: 100% ━━━━━━━━━━━━ 198/198 2.9it/s 1:08\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.6it/s 5.0s\n"," all 401 2042 0.586 0.779 0.679 0.574 0.597 0.807 0.691 0.561\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 27/30 3.79G 0.5814 0.9493 0.6295 0.9258 0 24 640: 100% ━━━━━━━━━━━━ 198/198 2.9it/s 1:08\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.2it/s 5.9s\n"," all 401 2042 0.603 0.857 0.701 0.582 0.613 0.846 0.707 0.568\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 28/30 3.79G 0.5725 0.9262 0.6156 0.9223 0 29 640: 100% ━━━━━━━━━━━━ 198/198 2.9it/s 1:08\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.4it/s 5.4s\n"," all 401 2042 0.561 0.841 0.668 0.562 0.563 0.842 0.673 0.545\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 29/30 3.79G 0.5632 0.9212 0.6044 0.9155 0 20 640: 100% ━━━━━━━━━━━━ 198/198 2.9it/s 1:09\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.4it/s 5.4s\n"," all 401 2042 0.566 0.853 0.688 0.574 0.572 0.859 0.698 0.56\n","\n"," Epoch GPU_mem box_loss seg_loss cls_loss dfl_loss sem_loss Instances Size\n","\u001b[K 30/30 3.79G 0.5642 0.92 0.6024 0.9137 0 24 640: 100% ━━━━━━━━━━━━ 198/198 2.9it/s 1:08\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 2.1it/s 6.1s\n"," all 401 2042 0.585 0.841 0.695 0.581 0.604 0.813 0.707 0.568\n","\n","30 epochs completed in 0.708 hours.\n","Optimizer stripped from /content/runs/segment/train/weights/last.pt, 6.0MB\n","Optimizer stripped from /content/runs/segment/train/weights/best.pt, 6.0MB\n","\n","Validating /content/runs/segment/train/weights/best.pt...\n","Ultralytics 8.4.41 🚀 Python-3.12.13 torch-2.10.0+cu128 CUDA:0 (Tesla T4, 14913MiB)\n","YOLO11n-seg summary (fused): 114 layers, 2,839,053 parameters, 0 gradients, 9.6 GFLOPs\n","\u001b[K Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 13/13 1.2it/s 10.4s\n"," all 401 2042 0.602 0.857 0.701 0.582 0.613 0.845 0.707 0.568\n"," back_bumper 94 94 0.882 0.947 0.943 0.8 0.884 0.947 0.943 0.758\n"," back_door 158 159 0.808 0.931 0.932 0.832 0.831 0.925 0.932 0.812\n"," back_glass 114 115 0.875 0.983 0.975 0.844 0.879 0.974 0.969 0.826\n"," back_left_door 15 15 0.503 1 0.517 0.446 0.509 1 0.517 0.428\n"," back_left_light 19 19 0.527 0.879 0.636 0.457 0.533 0.84 0.684 0.496\n"," back_light 161 226 0.823 0.876 0.882 0.661 0.845 0.872 0.888 0.638\n"," back_right_door 12 12 0.391 0.917 0.602 0.539 0.409 0.917 0.602 0.503\n"," back_right_light 13 13 0.384 0.846 0.448 0.365 0.397 0.846 0.448 0.36\n"," front_bumper 208 208 0.91 0.99 0.979 0.906 0.912 0.986 0.979 0.896\n"," front_door 167 167 0.812 0.955 0.939 0.847 0.815 0.952 0.939 0.831\n"," front_glass 214 214 0.942 0.991 0.972 0.906 0.943 0.991 0.972 0.91\n"," front_left_door 15 15 0.489 0.933 0.646 0.613 0.494 0.933 0.646 0.544\n"," front_left_light 30 30 0.454 0.831 0.498 0.338 0.447 0.807 0.502 0.331\n"," front_light 248 373 0.854 0.914 0.905 0.69 0.86 0.901 0.901 0.665\n"," front_right_door 12 12 0.384 0.917 0.478 0.442 0.387 0.917 0.478 0.391\n"," front_right_light 26 26 0.416 0.846 0.566 0.475 0.421 0.846 0.566 0.486\n"," hood 214 214 0.908 0.986 0.955 0.864 0.909 0.986 0.955 0.859\n"," left_mirror 31 31 0.454 0.742 0.602 0.426 0.475 0.672 0.602 0.398\n"," object 1 1 0 0 0 0 0 0 0 0\n"," right_mirror 31 31 0.476 0.806 0.538 0.356 0.448 0.677 0.541 0.374\n"," tailgate 5 5 0.533 0.92 0.817 0.641 0.621 0.987 0.853 0.673\n"," trunk 9 9 0.589 0.889 0.848 0.638 0.534 0.778 0.684 0.559\n"," wheel 34 53 0.44 0.607 0.433 0.299 0.544 0.679 0.666 0.316\n","Speed: 0.3ms preprocess, 3.9ms inference, 0.0ms loss, 5.1ms postprocess per image\n","Results saved to \u001b[1m/content/runs/segment/train\u001b[0m\n","💡 Learn more at https://docs.ultralytics.com/modes/train\n"]}],"execution_count":null},{"cell_type":"code","source":"from google.colab import drive\ndrive.mount('/content/drive')","metadata":{"id":"Y_8yIgxp_tFS"},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!ls\n!zip -r runs.zip runs/","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"gskhZre3Aki6","outputId":"eeaad7d0-bf07-4844-8a3c-3d2b8bc47965"},"outputs":[{"output_type":"stream","name":"stdout","text":["datasets runs\tsample_data yolo11n-seg.pt yolo26n.pt\n"," adding: runs/ (stored 0%)\n"," adding: runs/segment/ (stored 0%)\n"," adding: runs/segment/train/ (stored 0%)\n"," adding: runs/segment/train/labels.jpg (deflated 16%)\n"," adding: runs/segment/train/BoxPR_curve.png (deflated 11%)\n"," adding: runs/segment/train/confusion_matrix.png (deflated 16%)\n"," adding: runs/segment/train/val_batch2_pred.jpg (deflated 7%)\n"," adding: runs/segment/train/BoxF1_curve.png (deflated 9%)\n"," adding: runs/segment/train/MaskR_curve.png (deflated 10%)\n"," adding: runs/segment/train/confusion_matrix_normalized.png (deflated 12%)\n"," adding: runs/segment/train/val_batch0_labels.jpg (deflated 8%)\n"," adding: runs/segment/train/results.png (deflated 8%)\n"," adding: runs/segment/train/train_batch0.jpg (deflated 2%)\n"," adding: runs/segment/train/val_batch0_pred.jpg (deflated 7%)\n"," adding: runs/segment/train/MaskF1_curve.png (deflated 9%)\n"," adding: runs/segment/train/val_batch2_labels.jpg (deflated 8%)\n"," adding: runs/segment/train/results.csv (deflated 60%)\n"," adding: runs/segment/train/train_batch3960.jpg (deflated 9%)\n"," adding: runs/segment/train/weights/ (stored 0%)\n"," adding: runs/segment/train/weights/last.pt (deflated 10%)\n"," adding: runs/segment/train/weights/best.pt (deflated 10%)\n"," adding: runs/segment/train/MaskP_curve.png (deflated 9%)\n"," adding: runs/segment/train/train_batch3961.jpg (deflated 7%)\n"," adding: runs/segment/train/BoxP_curve.png (deflated 9%)\n"," adding: runs/segment/train/args.yaml (deflated 53%)\n"," adding: runs/segment/train/train_batch3962.jpg (deflated 10%)\n"," adding: runs/segment/train/train_batch2.jpg (deflated 2%)\n"," adding: runs/segment/train/MaskPR_curve.png (deflated 11%)\n"," adding: runs/segment/train/train_batch1.jpg (deflated 3%)\n"," adding: runs/segment/train/BoxR_curve.png (deflated 10%)\n"," adding: runs/segment/train/val_batch1_labels.jpg (deflated 7%)\n"," adding: runs/segment/train/val_batch1_pred.jpg (deflated 7%)\n"]}],"execution_count":null},{"cell_type":"markdown","source":"# YOLO_CAR_DAMAGE_FINE_TUNING","metadata":{"id":"JympTsU415bY"}},{"cell_type":"code","source":"!pip install ultralytics","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"hU5TmPp218rC","outputId":"9bd0ed4a-3c54-4023-bcd2-eea4cbf1c9c1","trusted":true,"execution":{"iopub.status.busy":"2026-05-07T19:57:33.180369Z","iopub.execute_input":"2026-05-07T19:57:33.180590Z","iopub.status.idle":"2026-05-07T19:57:39.732061Z","shell.execute_reply.started":"2026-05-07T19:57:33.180566Z","shell.execute_reply":"2026-05-07T19:57:39.731062Z"}},"outputs":[{"name":"stdout","text":"Collecting ultralytics\n Downloading ultralytics-8.4.47-py3-none-any.whl.metadata (39 kB)\nRequirement already satisfied: numpy>=1.23.0 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (2.0.2)\nRequirement already satisfied: matplotlib>=3.3.0 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (3.10.0)\nRequirement already satisfied: opencv-python>=4.6.0 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (4.13.0.92)\nRequirement already satisfied: pillow>=7.1.2 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (11.3.0)\nRequirement already satisfied: pyyaml>=5.3.1 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (6.0.3)\nRequirement already satisfied: requests>=2.23.0 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (2.32.4)\nRequirement already satisfied: scipy>=1.4.1 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (1.16.3)\nRequirement already satisfied: torch>=1.8.0 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (2.10.0+cu128)\nRequirement already satisfied: torchvision>=0.9.0 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (0.25.0+cu128)\nRequirement already satisfied: psutil>=5.8.0 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (5.9.5)\nRequirement already satisfied: polars>=0.20.0 in /usr/local/lib/python3.12/dist-packages (from ultralytics) (1.35.2)\nCollecting ultralytics-thop>=2.0.18 (from ultralytics)\n Downloading ultralytics_thop-2.0.19-py3-none-any.whl.metadata (14 kB)\nRequirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->ultralytics) (1.3.3)\nRequirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->ultralytics) (0.12.1)\nRequirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->ultralytics) (4.61.1)\nRequirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->ultralytics) (1.4.9)\nRequirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->ultralytics) (26.0)\nRequirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->ultralytics) (3.3.2)\nRequirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->ultralytics) (2.9.0.post0)\nRequirement already satisfied: polars-runtime-32==1.35.2 in /usr/local/lib/python3.12/dist-packages (from polars>=0.20.0->ultralytics) (1.35.2)\nRequirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests>=2.23.0->ultralytics) (3.4.4)\nRequirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests>=2.23.0->ultralytics) (3.11)\nRequirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests>=2.23.0->ultralytics) (2.5.0)\nRequirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests>=2.23.0->ultralytics) (2026.1.4)\nRequirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (3.24.3)\nRequirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (4.15.0)\nRequirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (75.2.0)\nRequirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (1.14.0)\nRequirement already satisfied: networkx>=2.5.1 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (3.6.1)\nRequirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (3.1.6)\nRequirement already satisfied: fsspec>=0.8.5 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (2026.2.0)\nRequirement already satisfied: cuda-bindings==12.9.4 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (12.9.4)\nRequirement already satisfied: nvidia-cuda-nvrtc-cu12==12.8.93 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (12.8.93)\nRequirement already satisfied: nvidia-cuda-runtime-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (12.8.90)\nRequirement already satisfied: nvidia-cuda-cupti-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (12.8.90)\nRequirement already satisfied: nvidia-cudnn-cu12==9.10.2.21 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (9.10.2.21)\nRequirement already satisfied: nvidia-cublas-cu12==12.8.4.1 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (12.8.4.1)\nRequirement already satisfied: nvidia-cufft-cu12==11.3.3.83 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (11.3.3.83)\nRequirement already satisfied: nvidia-curand-cu12==10.3.9.90 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (10.3.9.90)\nRequirement already satisfied: nvidia-cusolver-cu12==11.7.3.90 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (11.7.3.90)\nRequirement already satisfied: nvidia-cusparse-cu12==12.5.8.93 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (12.5.8.93)\nRequirement already satisfied: nvidia-cusparselt-cu12==0.7.1 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (0.7.1)\nRequirement already satisfied: nvidia-nccl-cu12==2.27.5 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (2.27.5)\nRequirement already satisfied: nvidia-nvshmem-cu12==3.4.5 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (3.4.5)\nRequirement already satisfied: nvidia-nvtx-cu12==12.8.90 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (12.8.90)\nRequirement already satisfied: nvidia-nvjitlink-cu12==12.8.93 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (12.8.93)\nRequirement already satisfied: nvidia-cufile-cu12==1.13.1.3 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (1.13.1.3)\nRequirement already satisfied: triton==3.6.0 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->ultralytics) (3.6.0)\nRequirement already satisfied: cuda-pathfinder~=1.1 in /usr/local/lib/python3.12/dist-packages (from cuda-bindings==12.9.4->torch>=1.8.0->ultralytics) (1.3.5)\nRequirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.7->matplotlib>=3.3.0->ultralytics) (1.17.0)\nRequirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy>=1.13.3->torch>=1.8.0->ultralytics) (1.3.0)\nRequirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->torch>=1.8.0->ultralytics) (3.0.3)\nDownloading ultralytics-8.4.47-py3-none-any.whl (1.2 MB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m6.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n\u001b[?25hDownloading ultralytics_thop-2.0.19-py3-none-any.whl (28 kB)\nInstalling collected packages: ultralytics-thop, ultralytics\nSuccessfully installed ultralytics-8.4.47 ultralytics-thop-2.0.19\n","output_type":"stream"}],"execution_count":1},{"cell_type":"code","source":"!yolo detect train data=pathToNDJSON model=yolo26l.pt epochs=150 imgsz=640","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"2eQ4UPPQ2NBp","outputId":"404d2794-b7c4-4a0d-f3f5-8bdaea70e443","trusted":true,"execution":{"iopub.status.busy":"2026-05-07T19:58:07.478269Z","iopub.execute_input":"2026-05-07T19:58:07.478722Z","iopub.status.idle":"2026-05-07T23:33:28.756844Z","shell.execute_reply.started":"2026-05-07T19:58:07.478690Z","shell.execute_reply":"2026-05-07T23:33:28.755800Z"},"collapsed":true,"jupyter":{"outputs_hidden":true}},"outputs":[{"name":"stdout","text":"Creating new Ultralytics Settings v0.0.6 file ✅ \nView Ultralytics Settings with 'yolo settings' or at '/root/.config/Ultralytics/settings.json'\nUpdate Settings with 'yolo settings key=value', i.e. 'yolo settings runs_dir=path/to/dir'. For help see https://docs.ultralytics.com/quickstart/#ultralytics-settings.\nWARNING ⚠️ conflicting 'task=segment' passed with 'task=detect' model. Ignoring 'task=segment' and updating to 'task=detect' to match model.\nUltralytics 8.4.47 🚀 Python-3.12.12 torch-2.10.0+cu128 CUDA:0 (Tesla T4, 14913MiB)\n\u001b[34m\u001b[1mengine/trainer: \u001b[0magnostic_nms=False, amp=True, angle=1.0, augment=False, auto_augment=randaugment, batch=16, bgr=0.0, box=7.5, cache=False, cfg=None, classes=None, close_mosaic=10, cls=0.5, cls_pw=0.0, compile=False, conf=None, copy_paste=0.0, copy_paste_mode=flip, cos_lr=False, cutmix=0.0, data=/kaggle/input/datasets/furyprestige/yolocardamage/car-damage-v5v4iyolo26.ndjson, degrees=0.0, deterministic=True, device=None, dfl=1.5, dnn=False, dropout=0.0, dynamic=False, embed=None, end2end=None, epochs=150, erasing=0.4, exist_ok=False, fliplr=0.5, flipud=0.0, format=torchscript, fraction=1.0, freeze=None, half=False, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, imgsz=640, int8=False, iou=0.7, keras=False, kobj=1.0, line_width=None, lr0=0.01, lrf=0.01, mask_ratio=4, max_det=300, mixup=0.0, mode=train, model=yolo26l.pt, momentum=0.937, mosaic=1.0, multi_scale=0.0, name=train-10, nbs=64, nms=False, opset=None, optimize=False, optimizer=auto, overlap_mask=True, patience=100, perspective=0.0, plots=True, pose=12.0, pretrained=True, profile=False, project=None, rect=False, resume=False, retina_masks=False, rle=1.0, save=True, save_conf=False, save_crop=False, save_dir=/kaggle/working/runs/detect/train-10, save_frames=False, save_json=False, save_period=-1, save_txt=False, scale=0.5, seed=0, shear=0.0, show=False, show_boxes=True, show_conf=True, show_labels=True, simplify=True, single_cls=False, source=None, split=val, stream_buffer=False, task=detect, time=None, tracker=botsort.yaml, translate=0.1, val=True, verbose=True, vid_stride=1, visualize=False, warmup_bias_lr=0.1, warmup_epochs=3.0, warmup_momentum=0.8, weight_decay=0.0005, workers=8, workspace=None\n\u001b[KDownloading https://ultralytics.com/assets/Arial.ttf to '/root/.config/Ultralytics/Arial.ttf': 100% ━━━━━━━━━━━━ 755.1KB 16.3MB/s 0.0s\nOverriding model.yaml nc=80 with nc=4\n\n from n params module arguments \n 0 -1 1 1856 ultralytics.nn.modules.conv.Conv [3, 64, 3, 2] \n 1 -1 1 73984 ultralytics.nn.modules.conv.Conv [64, 128, 3, 2] \n 2 -1 2 173824 ultralytics.nn.modules.block.C3k2 [128, 256, 2, True, 0.25] \n 3 -1 1 590336 ultralytics.nn.modules.conv.Conv [256, 256, 3, 2] \n 4 -1 2 691712 ultralytics.nn.modules.block.C3k2 [256, 512, 2, True, 0.25] \n 5 -1 1 2360320 ultralytics.nn.modules.conv.Conv [512, 512, 3, 2] \n 6 -1 2 2234368 ultralytics.nn.modules.block.C3k2 [512, 512, 2, True] \n 7 -1 1 2360320 ultralytics.nn.modules.conv.Conv [512, 512, 3, 2] \n 8 -1 2 2234368 ultralytics.nn.modules.block.C3k2 [512, 512, 2, True] \n 9 -1 1 656896 ultralytics.nn.modules.block.SPPF [512, 512, 5, 3, True] \n 10 -1 2 1455616 ultralytics.nn.modules.block.C2PSA [512, 512, 2] \n 11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n 12 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1] \n 13 -1 2 2496512 ultralytics.nn.modules.block.C3k2 [1024, 512, 2, True] \n 14 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n 15 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1] \n 16 -1 2 756736 ultralytics.nn.modules.block.C3k2 [1024, 256, 2, True] \n 17 -1 1 590336 ultralytics.nn.modules.conv.Conv [256, 256, 3, 2] \n 18 [-1, 13] 1 0 ultralytics.nn.modules.conv.Concat [1] \n 19 -1 2 2365440 ultralytics.nn.modules.block.C3k2 [768, 512, 2, True] \n 20 -1 1 2360320 ultralytics.nn.modules.conv.Conv [512, 512, 3, 2] \n 21 [-1, 10] 1 0 ultralytics.nn.modules.conv.Concat [1] \n 22 -1 1 1974784 ultralytics.nn.modules.block.C3k2 [1024, 512, 1, True, 0.5, True]\n 23 [16, 19, 22] 1 2804784 ultralytics.nn.modules.head.Detect [4, 1, True, [256, 512, 512]] \nYOLO26l summary: 392 layers, 26,182,512 parameters, 26,182,512 gradients, 93.1 GFLOPs\n\nTransferred 1080/1092 items from pretrained weights\n\u001b[34m\u001b[1mAMP: \u001b[0mrunning Automatic Mixed Precision (AMP) checks...\n\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n\u001b[34m\u001b[1mtrain: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 1535.2±964.1 MB/s, size: 82.7 KB)\n\u001b[K\u001b[34m\u001b[1mtrain: \u001b[0mScanning /kaggle/working/datasets/car-damage-v5v4iyolo26-9b7cb9df/labels/train.cache... 5805 images, 0 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 5805/5805 936.5Mit/s 0.0s\n\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01, method='weighted_average', num_output_channels=3), CLAHE(p=0.01, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8))\n\u001b[34m\u001b[1mval: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 693.3±578.4 MB/s, size: 73.6 KB)\n\u001b[K\u001b[34m\u001b[1mval: \u001b[0mScanning /kaggle/working/datasets/car-damage-v5v4iyolo26-9b7cb9df/labels/val.cache... 574 images, 0 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 574/574 11.9Mit/s 0.0s\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 MuSGD(lr=0.01, momentum=0.9) with parameter groups 178 weight(decay=0.0), 190 weight(decay=0.0005), 190 bias(decay=0.0)\nPlotting labels to /kaggle/working/runs/detect/train-10/labels.jpg... \nImage sizes 640 train, 640 val\nUsing 2 dataloader workers\nLogging results to \u001b[1m/kaggle/working/runs/detect/train-10\u001b[0m\nStarting training for 150 epochs...\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 1/150 10.8G 1.542 4.105 0.01933 53 640: 100% ━━━━━━━━━━━━ 363/363 1.1s/it 6:23<1.3s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.2it/s 15.4s0.6s\n all 574 908 0.302 0.301 0.247 0.135\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 2/150 11G 1.626 2.618 0.02081 60 640: 100% ━━━━━━━━━━━━ 363/363 1.1it/s 5:31<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.4s.6s\n all 574 908 0.356 0.338 0.304 0.143\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 3/150 11G 1.766 2.65 0.02333 40 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:14<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.271 0.271 0.209 0.0874\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 4/150 11G 1.831 2.772 0.02453 49 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.372 0.338 0.275 0.115\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 5/150 11G 1.806 2.692 0.02415 34 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:09<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.457 0.389 0.374 0.162\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 6/150 11G 1.784 2.582 0.02373 49 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.7s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.4s.6s\n all 574 908 0.461 0.371 0.354 0.157\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 7/150 11G 1.748 2.464 0.02289 34 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.4s.6s\n all 574 908 0.458 0.421 0.376 0.186\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 8/150 11G 1.713 2.371 0.02218 37 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.4s.6s\n all 574 908 0.527 0.406 0.418 0.204\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 9/150 11.1G 1.667 2.298 0.02164 51 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.4s.6s\n all 574 908 0.54 0.478 0.465 0.252\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 10/150 10.9G 1.654 2.198 0.02134 43 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:07<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.4s.6s\n all 574 908 0.494 0.509 0.468 0.245\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 11/150 11.1G 1.638 2.132 0.02092 51 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:07<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.555 0.451 0.46 0.234\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 12/150 11G 1.619 2.066 0.02062 76 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.61 0.503 0.537 0.287\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 13/150 11G 1.592 1.983 0.01991 43 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:07<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.63 0.531 0.56 0.309\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 14/150 11G 1.568 1.927 0.01957 45 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:07<0.7s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.627 0.552 0.587 0.323\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 15/150 11G 1.546 1.854 0.01939 52 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:07<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.4s.6s\n all 574 908 0.651 0.553 0.592 0.335\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 16/150 11G 1.513 1.782 0.01863 54 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.664 0.596 0.62 0.354\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 17/150 11G 1.495 1.716 0.01852 40 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.658 0.565 0.61 0.34\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 18/150 11G 1.47 1.635 0.01795 43 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.7s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.671 0.595 0.65 0.387\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 19/150 11G 1.457 1.59 0.01778 50 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:07<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.709 0.642 0.677 0.417\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 20/150 11G 1.445 1.572 0.01758 38 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:07<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.771 0.607 0.68 0.397\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 21/150 11G 1.409 1.518 0.01712 51 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.725 0.677 0.718 0.432\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 22/150 10.9G 1.398 1.472 0.01685 46 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:07<0.7s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.796 0.628 0.712 0.442\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 23/150 11G 1.382 1.421 0.01645 52 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.774 0.68 0.732 0.463\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 24/150 11G 1.361 1.382 0.01595 43 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.794 0.699 0.762 0.484\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 25/150 11.1G 1.347 1.333 0.01593 41 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.784 0.687 0.751 0.484\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 26/150 11G 1.325 1.292 0.01566 31 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:07<0.7s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.763 0.677 0.745 0.48\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 27/150 11.1G 1.294 1.271 0.0153 48 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:07<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.805 0.684 0.767 0.505\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 28/150 11G 1.276 1.223 0.01523 36 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:09<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.812 0.689 0.766 0.51\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 29/150 11G 1.27 1.191 0.01482 43 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:09<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.809 0.729 0.799 0.535\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 30/150 10.9G 1.241 1.153 0.01443 68 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.7s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.81 0.751 0.8 0.533\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 31/150 11.1G 1.253 1.13 0.01434 36 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.8it/s 10.3s.6s\n all 574 908 0.834 0.755 0.818 0.542\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 32/150 11G 1.223 1.105 0.01411 44 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.852 0.729 0.808 0.552\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 33/150 11G 1.194 1.083 0.01375 26 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.827 0.738 0.803 0.546\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 34/150 10.9G 1.197 1.045 0.01364 36 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:07<0.7s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.8it/s 10.3s.6s\n all 574 908 0.806 0.755 0.808 0.557\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 35/150 11G 1.183 1.042 0.01336 53 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:07<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.8it/s 10.2s.6s\n all 574 908 0.833 0.774 0.832 0.573\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 36/150 11G 1.16 1.011 0.01305 34 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:07<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.8it/s 10.3s.6s\n all 574 908 0.82 0.774 0.826 0.587\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 37/150 11G 1.15 0.9896 0.01297 50 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:07<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.7it/s 10.3s.6s\n all 574 908 0.843 0.772 0.823 0.592\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 38/150 10.9G 1.138 0.9853 0.01273 34 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:06<0.7s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.8it/s 10.3s.6s\n all 574 908 0.849 0.784 0.855 0.617\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 39/150 11G 1.115 0.9507 0.01261 45 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:07<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 18/18 1.8it/s 10.2s.6s\n all 574 908 0.861 0.791 0.849 0.606\n\n Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n\u001b[K 40/150 11G 1.114 0.9425 0.0125 52 640: 100% ━━━━━━━━━━━━ 363/363 1.2it/s 5:08<0.8s\n\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 94% ━━━━━━━━━━━─ 17/18 1.7it/s 9.7s<0.6s^C\n","output_type":"stream"}],"execution_count":3},{"cell_type":"code","source":"!zip -r lastTrainDamages pathToLastTrainFolderInsideRuns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-05-08T04:38:14.742765Z","iopub.execute_input":"2026-05-08T04:38:14.743518Z","iopub.status.idle":"2026-05-08T04:38:30.951130Z","shell.execute_reply.started":"2026-05-08T04:38:14.743488Z","shell.execute_reply":"2026-05-08T04:38:30.950469Z"}},"outputs":[{"name":"stdout","text":" adding: kaggle/working/runs/detect/train-10/ (stored 0%)\n adding: kaggle/working/runs/detect/train-10/args.yaml (deflated 53%)\n adding: kaggle/working/runs/detect/train-10/train_batch1.jpg (deflated 3%)\n adding: kaggle/working/runs/detect/train-10/weights/ (stored 0%)\n adding: kaggle/working/runs/detect/train-10/weights/last.pt (deflated 8%)\n adding: kaggle/working/runs/detect/train-10/weights/best.pt (deflated 8%)\n adding: kaggle/working/runs/detect/train-10/labels.jpg (deflated 22%)\n adding: kaggle/working/runs/detect/train-10/train_batch0.jpg (deflated 3%)\n adding: kaggle/working/runs/detect/train-10/train_batch2.jpg (deflated 3%)\n adding: kaggle/working/runs/detect/train-10/results.csv (deflated 68%)\n","output_type":"stream"}],"execution_count":2}]} |