In [ ]:
Image(filename=f'/content/runs/detect/train/results.png', width=800)
Out[ ]:
! jupyter nbconvert --to html ///content/yolov8_footbal_player_detection.ipynb
[NbConvertApp] Converting notebook ///content/yolov8_footbal_player_detection.ipynb to html [NbConvertApp] Writing 2954271 bytes to /content/yolov8_footbal_player_detection.html
!nvidia-smi
Sat Jan 6 15:27:47 2024
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.104.05 Driver Version: 535.104.05 CUDA Version: 12.2 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 Tesla T4 Off | 00000000:00:04.0 Off | 0 |
| N/A 35C P8 9W / 70W | 0MiB / 15360MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
| No running processes found |
+---------------------------------------------------------------------------------------+
%pip install ultralytics
import ultralytics
ultralytics.checks()
Ultralytics YOLOv8.0.235 🚀 Python-3.10.12 torch-2.1.0+cu121 CUDA:0 (Tesla T4, 15102MiB) Setup complete ✅ (2 CPUs, 12.7 GB RAM, 26.6/78.2 GB disk)
from ultralytics import YOLO
import os
from IPython.display import display, Image
from IPython import display
display.clear_output()
!yolo mode=checks
Traceback (most recent call last):
File "/usr/local/bin/yolo", line 8, in <module>
sys.exit(entrypoint())
File "/usr/local/lib/python3.10/dist-packages/ultralytics/cfg/__init__.py", line 402, in entrypoint
raise ValueError(f"Invalid 'mode={mode}'. Valid modes are {MODES}.\n{CLI_HELP_MSG}")
ValueError: Invalid 'mode=<module 'ultralytics.utils.checks' from '/usr/local/lib/python3.10/dist-packages/ultralytics/utils/checks.py'>'. Valid modes are ('train', 'val', 'predict', 'export', 'track', 'benchmark').
Arguments received: ['yolo', 'mode=checks']. Ultralytics 'yolo' commands use the following syntax:
yolo TASK MODE ARGS
Where TASK (optional) is one of ('detect', 'segment', 'classify', 'pose', 'obb')
MODE (required) is one of ('train', 'val', 'predict', 'export', 'track', 'benchmark')
ARGS (optional) are any number of custom 'arg=value' pairs like 'imgsz=320' that override defaults.
See all ARGS at https://docs.ultralytics.com/usage/cfg or with 'yolo cfg'
1. Train a detection model for 10 epochs with an initial learning_rate of 0.01
yolo train data=coco128.yaml model=yolov8n.pt epochs=10 lr0=0.01
2. Predict a YouTube video using a pretrained segmentation model at image size 320:
yolo predict model=yolov8n-seg.pt source='https://youtu.be/LNwODJXcvt4' imgsz=320
3. Val a pretrained detection model at batch-size 1 and image size 640:
yolo val model=yolov8n.pt data=coco128.yaml batch=1 imgsz=640
4. Export a YOLOv8n classification model to ONNX format at image size 224 by 128 (no TASK required)
yolo export model=yolov8n-cls.pt format=onnx imgsz=224,128
5. Run special commands:
yolo help
yolo checks
yolo version
yolo settings
yolo copy-cfg
yolo cfg
Docs: https://docs.ultralytics.com
Community: https://community.ultralytics.com
GitHub: https://github.com/ultralytics/ultralytics
!pip install roboflow
from roboflow import Roboflow
rf = Roboflow(api_key="8f60PiLN5qzO0Jq6glkd")
project = rf.workspace("roboflow-jvuqo").project("football-players-detection-3zvbc")
dataset = project.version(2).download("yolov8")
Requirement already satisfied: roboflow in /usr/local/lib/python3.10/dist-packages (1.1.15) Requirement already satisfied: certifi==2023.7.22 in /usr/local/lib/python3.10/dist-packages (from roboflow) (2023.7.22) Requirement already satisfied: chardet==4.0.0 in /usr/local/lib/python3.10/dist-packages (from roboflow) (4.0.0) Requirement already satisfied: cycler==0.10.0 in /usr/local/lib/python3.10/dist-packages (from roboflow) (0.10.0) Requirement already satisfied: idna==2.10 in /usr/local/lib/python3.10/dist-packages (from roboflow) (2.10) Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.10/dist-packages (from roboflow) (1.4.5) Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from roboflow) (3.7.1) Requirement already satisfied: numpy>=1.18.5 in /usr/local/lib/python3.10/dist-packages (from roboflow) (1.23.5) Requirement already satisfied: opencv-python-headless==4.8.0.74 in /usr/local/lib/python3.10/dist-packages (from roboflow) (4.8.0.74) Requirement already satisfied: Pillow>=7.1.2 in /usr/local/lib/python3.10/dist-packages (from roboflow) (9.4.0) Requirement already satisfied: pyparsing==2.4.7 in /usr/local/lib/python3.10/dist-packages (from roboflow) (2.4.7) Requirement already satisfied: python-dateutil in /usr/local/lib/python3.10/dist-packages (from roboflow) (2.8.2) Requirement already satisfied: python-dotenv in /usr/local/lib/python3.10/dist-packages (from roboflow) (1.0.0) Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from roboflow) (2.31.0) Requirement already satisfied: six in /usr/local/lib/python3.10/dist-packages (from roboflow) (1.16.0) Requirement already satisfied: supervision in /usr/local/lib/python3.10/dist-packages (from roboflow) (0.17.1) Requirement already satisfied: urllib3>=1.26.6 in /usr/local/lib/python3.10/dist-packages (from roboflow) (2.0.7) Requirement already satisfied: tqdm>=4.41.0 in /usr/local/lib/python3.10/dist-packages (from roboflow) (4.66.1) Requirement already satisfied: PyYAML>=5.3.1 in /usr/local/lib/python3.10/dist-packages (from roboflow) (6.0.1) Requirement already satisfied: requests-toolbelt in /usr/local/lib/python3.10/dist-packages (from roboflow) (1.0.0) Requirement already satisfied: python-magic in /usr/local/lib/python3.10/dist-packages (from roboflow) (0.4.27) Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->roboflow) (1.2.0) Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->roboflow) (4.47.0) Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->roboflow) (23.2) Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->roboflow) (3.3.2) Requirement already satisfied: scipy>=1.9.0 in /usr/local/lib/python3.10/dist-packages (from supervision->roboflow) (1.11.4) loading Roboflow workspace... loading Roboflow project... Dependency ultralytics==8.0.196 is required but found version=8.0.235, to fix: `pip install ultralytics==8.0.196`
Downloading Dataset Version Zip in football-players-detection-2 to yolov8:: 100%|██████████| 116758/116758 [00:01<00:00, 72250.14it/s]
Extracting Dataset Version Zip to football-players-detection-2 in yolov8:: 100%|██████████| 1338/1338 [00:00<00:00, 2194.19it/s]
!yolo task=detect mode=train model=yolov8m.pt data={dataset.location}/data.yaml epochs=100 imgsz=640
Downloading https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8m.pt to 'yolov8m.pt'... 100% 49.7M/49.7M [00:00<00:00, 211MB/s] Ultralytics YOLOv8.0.235 🚀 Python-3.10.12 torch-2.1.0+cu121 CUDA:0 (Tesla T4, 15102MiB) engine/trainer: task=detect, mode=train, model=yolov8m.pt, data=/content/football-players-detection-2/data.yaml, epochs=100, time=None, patience=50, batch=16, imgsz=640, save=True, save_period=-1, cache=False, device=None, 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=False, 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, mosaic=1.0, mixup=0.0, copy_paste=0.0, auto_augment=randaugment, erasing=0.4, crop_fraction=1.0, cfg=None, tracker=botsort.yaml, save_dir=runs/detect/train Downloading https://ultralytics.com/assets/Arial.ttf to '/root/.config/Ultralytics/Arial.ttf'... 100% 755k/755k [00:00<00:00, 16.1MB/s] 2024-01-06 15:30:44.708639: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2024-01-06 15:30:44.708712: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2024-01-06 15:30:44.710023: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered Overriding model.yaml nc=80 with nc=4 from n params module arguments 0 -1 1 1392 ultralytics.nn.modules.conv.Conv [3, 48, 3, 2] 1 -1 1 41664 ultralytics.nn.modules.conv.Conv [48, 96, 3, 2] 2 -1 2 111360 ultralytics.nn.modules.block.C2f [96, 96, 2, True] 3 -1 1 166272 ultralytics.nn.modules.conv.Conv [96, 192, 3, 2] 4 -1 4 813312 ultralytics.nn.modules.block.C2f [192, 192, 4, True] 5 -1 1 664320 ultralytics.nn.modules.conv.Conv [192, 384, 3, 2] 6 -1 4 3248640 ultralytics.nn.modules.block.C2f [384, 384, 4, True] 7 -1 1 1991808 ultralytics.nn.modules.conv.Conv [384, 576, 3, 2] 8 -1 2 3985920 ultralytics.nn.modules.block.C2f [576, 576, 2, True] 9 -1 1 831168 ultralytics.nn.modules.block.SPPF [576, 576, 5] 10 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 11 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1] 12 -1 2 1993728 ultralytics.nn.modules.block.C2f [960, 384, 2] 13 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 14 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1] 15 -1 2 517632 ultralytics.nn.modules.block.C2f [576, 192, 2] 16 -1 1 332160 ultralytics.nn.modules.conv.Conv [192, 192, 3, 2] 17 [-1, 12] 1 0 ultralytics.nn.modules.conv.Concat [1] 18 -1 2 1846272 ultralytics.nn.modules.block.C2f [576, 384, 2] 19 -1 1 1327872 ultralytics.nn.modules.conv.Conv [384, 384, 3, 2] 20 [-1, 9] 1 0 ultralytics.nn.modules.conv.Concat [1] 21 -1 2 4207104 ultralytics.nn.modules.block.C2f [960, 576, 2] 22 [15, 18, 21] 1 3778012 ultralytics.nn.modules.head.Detect [4, [192, 384, 576]] Model summary: 295 layers, 25858636 parameters, 25858620 gradients, 79.1 GFLOPs Transferred 469/475 items from pretrained weights TensorBoard: Start with 'tensorboard --logdir runs/detect/train', view at http://localhost:6006/ Freezing layer 'model.22.dfl.conv.weight' AMP: running Automatic Mixed Precision (AMP) checks with YOLOv8n... Downloading https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt to 'yolov8n.pt'... 100% 6.23M/6.23M [00:00<00:00, 76.5MB/s] WARNING ⚠️ NMS time limit 0.550s exceeded AMP: checks passed ✅ train: Scanning /content/football-players-detection-2/train/labels... 612 images, 0 backgrounds, 0 corrupt: 100% 612/612 [00:00<00:00, 1907.33it/s] train: New cache created: /content/football-players-detection-2/train/labels.cache albumentations: Blur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01), CLAHE(p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8)) val: Scanning /content/football-players-detection-2/valid/labels... 38 images, 0 backgrounds, 0 corrupt: 100% 38/38 [00:00<00:00, 1222.88it/s] val: New cache created: /content/football-players-detection-2/valid/labels.cache Plotting labels to runs/detect/train/labels.jpg... optimizer: 'optimizer=auto' found, ignoring 'lr0=0.01' and 'momentum=0.937' and determining best 'optimizer', 'lr0' and 'momentum' automatically... optimizer: AdamW(lr=0.00125, momentum=0.9) with parameter groups 77 weight(decay=0.0), 84 weight(decay=0.0005), 83 bias(decay=0.0) 100 epochs... Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 1/100 6.9G 1.23 1.455 0.8625 94 640: 100% 39/39 [00:36<00:00, 1.07it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.61s/it] all 38 905 0.549 0.382 0.372 0.219 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 2/100 7.43G 1.111 0.773 0.8261 119 640: 100% 39/39 [00:26<00:00, 1.45it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.49it/s] all 38 905 0.72 0.58 0.627 0.355 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 3/100 7.34G 1.256 0.7741 0.8446 80 640: 100% 39/39 [00:26<00:00, 1.47it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.41it/s] all 38 905 0.68 0.583 0.64 0.356 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 4/100 7.33G 1.224 0.7232 0.8445 100 640: 100% 39/39 [00:26<00:00, 1.48it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.48it/s] all 38 905 0.746 0.578 0.65 0.43 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 5/100 7.39G 1.123 0.6519 0.8324 165 640: 100% 39/39 [00:25<00:00, 1.53it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:01<00:00, 1.64it/s] all 38 905 0.849 0.65 0.725 0.457 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 6/100 7.34G 1.063 0.5928 0.8248 145 640: 100% 39/39 [00:26<00:00, 1.50it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.22it/s] all 38 905 0.826 0.68 0.757 0.509 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 7/100 7.39G 1.056 0.5647 0.8198 89 640: 100% 39/39 [00:26<00:00, 1.48it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.37it/s] all 38 905 0.846 0.693 0.745 0.466 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 8/100 7.35G 1.068 0.5658 0.8223 88 640: 100% 39/39 [00:27<00:00, 1.44it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.40it/s] all 38 905 0.863 0.702 0.764 0.492 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 9/100 7.38G 1.084 0.5725 0.8242 208 640: 100% 39/39 [00:26<00:00, 1.45it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.32it/s] all 38 905 0.836 0.726 0.732 0.477 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 10/100 7.14G 1.08 0.5593 0.8206 174 640: 100% 39/39 [00:26<00:00, 1.48it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.24it/s] all 38 905 0.785 0.711 0.748 0.492 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 11/100 7.19G 1.005 0.5477 0.8178 102 640: 100% 39/39 [00:26<00:00, 1.47it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.34it/s] all 38 905 0.825 0.69 0.758 0.504 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 12/100 7.39G 0.9889 0.5369 0.8141 141 640: 100% 39/39 [00:26<00:00, 1.47it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.39it/s] all 38 905 0.825 0.699 0.751 0.495 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 13/100 7.26G 0.9772 0.5308 0.8144 84 640: 100% 39/39 [00:25<00:00, 1.51it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.42it/s] all 38 905 0.885 0.758 0.807 0.541 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 14/100 7.35G 0.9762 0.5217 0.8116 235 640: 100% 39/39 [00:25<00:00, 1.52it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:01<00:00, 1.73it/s] all 38 905 0.924 0.759 0.815 0.56 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 15/100 7.14G 0.9099 0.4842 0.8099 71 640: 100% 39/39 [00:26<00:00, 1.49it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.25it/s] all 38 905 0.938 0.728 0.796 0.545 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 16/100 7.33G 0.9169 0.4849 0.8059 51 640: 100% 39/39 [00:26<00:00, 1.47it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.45it/s] all 38 905 0.914 0.737 0.782 0.531 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 17/100 7.4G 0.997 0.5289 0.8096 139 640: 100% 39/39 [00:26<00:00, 1.48it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.42it/s] all 38 905 0.874 0.678 0.752 0.482 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 18/100 7.18G 0.9931 0.5279 0.8106 105 640: 100% 39/39 [00:26<00:00, 1.47it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.26it/s] all 38 905 0.91 0.758 0.806 0.55 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 19/100 7.25G 0.943 0.4994 0.8092 99 640: 100% 39/39 [00:26<00:00, 1.45it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.37it/s] all 38 905 0.923 0.764 0.814 0.541 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 20/100 7.11G 0.9351 0.4833 0.8048 187 640: 100% 39/39 [00:26<00:00, 1.46it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.41it/s] all 38 905 0.908 0.71 0.809 0.53 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 21/100 7.25G 0.9375 0.4851 0.8055 98 640: 100% 39/39 [00:26<00:00, 1.47it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.33it/s] all 38 905 0.9 0.735 0.792 0.542 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 22/100 7.37G 0.9329 0.486 0.8082 98 640: 100% 39/39 [00:26<00:00, 1.48it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.19it/s] all 38 905 0.884 0.745 0.778 0.546 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 23/100 7.15G 0.9071 0.4727 0.7999 126 640: 100% 39/39 [00:26<00:00, 1.46it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.30it/s] all 38 905 0.864 0.767 0.799 0.528 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 24/100 7.33G 0.9513 0.4887 0.8052 130 640: 100% 39/39 [00:26<00:00, 1.49it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.29it/s] all 38 905 0.91 0.772 0.799 0.53 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 25/100 7.37G 0.8996 0.4602 0.8065 164 640: 100% 39/39 [00:25<00:00, 1.53it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.33it/s] all 38 905 0.914 0.772 0.817 0.564 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 26/100 7.41G 0.8928 0.4598 0.8048 147 640: 100% 39/39 [00:26<00:00, 1.48it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:01<00:00, 1.96it/s] all 38 905 0.809 0.773 0.797 0.533 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 27/100 7.37G 0.89 0.4595 0.8083 87 640: 100% 39/39 [00:26<00:00, 1.47it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.32it/s] all 38 905 0.903 0.756 0.795 0.543 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 28/100 7.38G 0.9169 0.4645 0.802 233 640: 100% 39/39 [00:26<00:00, 1.48it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.31it/s] all 38 905 0.932 0.788 0.81 0.524 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 29/100 7.36G 0.9154 0.4581 0.8005 90 640: 100% 39/39 [00:26<00:00, 1.47it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.65it/s] all 38 905 0.898 0.762 0.804 0.541 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 30/100 7.4G 0.8688 0.4396 0.8003 76 640: 100% 39/39 [00:26<00:00, 1.49it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.37it/s] all 38 905 0.939 0.737 0.812 0.56 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 31/100 7.15G 0.8399 0.4297 0.7962 87 640: 100% 39/39 [00:26<00:00, 1.46it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.87it/s] all 38 905 0.943 0.739 0.814 0.573 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 32/100 7.37G 0.8508 0.4417 0.7999 84 640: 100% 39/39 [00:26<00:00, 1.49it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.40it/s] all 38 905 0.953 0.762 0.817 0.565 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 33/100 7.39G 0.879 0.4522 0.8015 227 640: 100% 39/39 [00:26<00:00, 1.45it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.28it/s] all 38 905 0.944 0.752 0.808 0.564 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 34/100 7.36G 0.8557 0.4342 0.7995 136 640: 100% 39/39 [00:26<00:00, 1.44it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.32it/s] all 38 905 0.925 0.754 0.831 0.567 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 35/100 7.37G 0.8549 0.4325 0.8002 114 640: 100% 39/39 [00:26<00:00, 1.45it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.26it/s] all 38 905 0.931 0.763 0.819 0.56 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 36/100 7.31G 0.8604 0.4341 0.7959 101 640: 100% 39/39 [00:26<00:00, 1.49it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.18it/s] all 38 905 0.942 0.758 0.822 0.573 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 37/100 7.39G 0.8608 0.4352 0.7988 108 640: 100% 39/39 [00:25<00:00, 1.53it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:01<00:00, 1.62it/s] all 38 905 0.955 0.746 0.828 0.572 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 38/100 7.35G 0.837 0.4253 0.7965 102 640: 100% 39/39 [00:25<00:00, 1.51it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:01<00:00, 1.65it/s] all 38 905 0.887 0.789 0.835 0.568 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 39/100 7.27G 0.8354 0.4262 0.7958 149 640: 100% 39/39 [00:25<00:00, 1.53it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:01<00:00, 1.64it/s] all 38 905 0.931 0.786 0.837 0.593 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 40/100 7.24G 0.8191 0.4201 0.797 108 640: 100% 39/39 [00:26<00:00, 1.46it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.65it/s] all 38 905 0.921 0.792 0.85 0.574 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 41/100 7.4G 0.8229 0.4192 0.7989 130 640: 100% 39/39 [00:26<00:00, 1.46it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.44it/s] all 38 905 0.898 0.753 0.834 0.576 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 42/100 7.4G 0.8347 0.419 0.7964 270 640: 100% 39/39 [00:26<00:00, 1.47it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.40it/s] all 38 905 0.939 0.758 0.822 0.569 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 43/100 7.3G 0.8402 0.4263 0.7978 143 640: 100% 39/39 [00:26<00:00, 1.46it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.45it/s] all 38 905 0.859 0.78 0.812 0.581 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 44/100 7.37G 0.8171 0.413 0.792 150 640: 100% 39/39 [00:26<00:00, 1.47it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.36it/s] all 38 905 0.897 0.765 0.825 0.577 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 45/100 7.36G 0.8421 0.417 0.7953 145 640: 100% 39/39 [00:26<00:00, 1.48it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.11it/s] all 38 905 0.874 0.795 0.826 0.582 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 46/100 7.16G 0.8297 0.4137 0.7947 94 640: 100% 39/39 [00:26<00:00, 1.48it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.40it/s] all 38 905 0.889 0.795 0.841 0.591 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 47/100 7.38G 0.7869 0.3984 0.7966 105 640: 100% 39/39 [00:26<00:00, 1.48it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.23it/s] all 38 905 0.907 0.783 0.834 0.584 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 48/100 7.3G 0.7811 0.3945 0.7936 208 640: 100% 39/39 [00:25<00:00, 1.52it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.26it/s] all 38 905 0.929 0.728 0.791 0.565 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 49/100 7.41G 0.7811 0.3922 0.793 109 640: 100% 39/39 [00:26<00:00, 1.49it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.50it/s] all 38 905 0.903 0.753 0.816 0.578 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 50/100 7.38G 0.7684 0.3877 0.7912 169 640: 100% 39/39 [00:25<00:00, 1.50it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.25it/s] all 38 905 0.942 0.772 0.819 0.586 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 51/100 7.35G 0.7793 0.394 0.7926 148 640: 100% 39/39 [00:25<00:00, 1.53it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.30it/s] all 38 905 0.9 0.746 0.812 0.572 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 52/100 7.37G 0.8141 0.4051 0.7958 201 640: 100% 39/39 [00:26<00:00, 1.50it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.41it/s] all 38 905 0.898 0.752 0.82 0.566 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 53/100 7.34G 0.8033 0.3997 0.7909 131 640: 100% 39/39 [00:25<00:00, 1.53it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.10it/s] all 38 905 0.885 0.79 0.827 0.575 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 54/100 7.31G 0.7789 0.3928 0.7905 87 640: 100% 39/39 [00:24<00:00, 1.58it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:01<00:00, 1.59it/s] all 38 905 0.897 0.727 0.799 0.562 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 55/100 7.41G 0.7588 0.3847 0.7904 139 640: 100% 39/39 [00:25<00:00, 1.56it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.39it/s] all 38 905 0.887 0.753 0.813 0.574 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 56/100 7.37G 0.7723 0.3859 0.7881 211 640: 100% 39/39 [00:25<00:00, 1.53it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.41it/s] all 38 905 0.887 0.735 0.801 0.585 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 57/100 7.26G 0.7826 0.3923 0.7942 163 640: 100% 39/39 [00:25<00:00, 1.53it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.39it/s] all 38 905 0.96 0.715 0.821 0.57 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 58/100 7.37G 0.8 0.398 0.789 126 640: 100% 39/39 [00:25<00:00, 1.54it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.29it/s] all 38 905 0.883 0.773 0.823 0.578 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 59/100 7.34G 0.786 0.3911 0.7935 147 640: 100% 39/39 [00:25<00:00, 1.55it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.38it/s] all 38 905 0.917 0.757 0.821 0.584 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 60/100 7.34G 0.7757 0.3853 0.7925 64 640: 100% 39/39 [00:25<00:00, 1.55it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:01<00:00, 1.65it/s] all 38 905 0.957 0.748 0.829 0.584 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 61/100 7.35G 0.7982 0.391 0.7933 83 640: 100% 39/39 [00:25<00:00, 1.53it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.34it/s] all 38 905 0.946 0.723 0.818 0.585 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 62/100 7.31G 0.7657 0.3743 0.7904 106 640: 100% 39/39 [00:25<00:00, 1.51it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.42it/s] all 38 905 0.878 0.784 0.827 0.591 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 63/100 7.32G 0.7324 0.3677 0.7863 112 640: 100% 39/39 [00:25<00:00, 1.55it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.23it/s] all 38 905 0.912 0.773 0.845 0.6 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 64/100 7.23G 0.7696 0.3838 0.7903 71 640: 100% 39/39 [00:25<00:00, 1.51it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.22it/s] all 38 905 0.903 0.734 0.809 0.575 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 65/100 7.26G 0.7492 0.3798 0.792 135 640: 100% 39/39 [00:25<00:00, 1.55it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:01<00:00, 1.78it/s] all 38 905 0.909 0.764 0.818 0.578 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 66/100 7.38G 0.7508 0.3724 0.7899 133 640: 100% 39/39 [00:25<00:00, 1.50it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.21it/s] all 38 905 0.934 0.761 0.825 0.595 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 67/100 7.36G 0.7405 0.371 0.7876 204 640: 100% 39/39 [00:25<00:00, 1.51it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.16it/s] all 38 905 0.928 0.761 0.813 0.56 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 68/100 7.33G 0.7601 0.3785 0.7881 87 640: 100% 39/39 [00:26<00:00, 1.49it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.24it/s] all 38 905 0.906 0.762 0.803 0.575 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 69/100 7.39G 0.7416 0.3743 0.7856 74 640: 100% 39/39 [00:25<00:00, 1.53it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:01<00:00, 1.57it/s] all 38 905 0.962 0.732 0.822 0.583 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 70/100 7.36G 0.7404 0.3705 0.7865 125 640: 100% 39/39 [00:25<00:00, 1.55it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.18it/s] all 38 905 0.95 0.782 0.841 0.601 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 71/100 7.37G 0.7395 0.3635 0.7871 142 640: 100% 39/39 [00:25<00:00, 1.53it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.54it/s] all 38 905 0.925 0.758 0.826 0.583 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 72/100 7.33G 0.7518 0.3723 0.7874 164 640: 100% 39/39 [00:25<00:00, 1.51it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.43it/s] all 38 905 0.933 0.761 0.824 0.593 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 73/100 7.44G 0.7316 0.3596 0.7862 50 640: 100% 39/39 [00:25<00:00, 1.52it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.50it/s] all 38 905 0.943 0.776 0.839 0.6 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 74/100 7.41G 0.73 0.3623 0.7861 174 640: 100% 39/39 [00:25<00:00, 1.55it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:01<00:00, 1.63it/s] all 38 905 0.905 0.8 0.845 0.597 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 75/100 7.37G 0.7262 0.3575 0.7873 113 640: 100% 39/39 [00:25<00:00, 1.54it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.17it/s] all 38 905 0.947 0.764 0.842 0.597 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 76/100 7.31G 0.7103 0.3485 0.7865 165 640: 100% 39/39 [00:25<00:00, 1.55it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.66it/s] all 38 905 0.946 0.777 0.848 0.605 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 77/100 7.36G 0.7216 0.3586 0.7849 159 640: 100% 39/39 [00:25<00:00, 1.52it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.40it/s] all 38 905 0.956 0.787 0.85 0.61 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 78/100 7.35G 0.7264 0.3578 0.7853 121 640: 100% 39/39 [00:25<00:00, 1.50it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.29it/s] all 38 905 0.933 0.765 0.842 0.598 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 79/100 7.41G 0.69 0.3499 0.7858 165 640: 100% 39/39 [00:25<00:00, 1.56it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:01<00:00, 1.65it/s] all 38 905 0.972 0.728 0.838 0.596 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 80/100 7.33G 0.7123 0.3543 0.785 91 640: 100% 39/39 [00:25<00:00, 1.51it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.21it/s] all 38 905 0.93 0.77 0.833 0.588 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 81/100 7.24G 0.7013 0.3493 0.7853 177 640: 100% 39/39 [00:25<00:00, 1.53it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.20it/s] all 38 905 0.898 0.75 0.812 0.58 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 82/100 7.35G 0.7038 0.3472 0.7843 153 640: 100% 39/39 [00:25<00:00, 1.51it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.38it/s] all 38 905 0.926 0.759 0.824 0.594 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 83/100 7.39G 0.6954 0.3454 0.7862 114 640: 100% 39/39 [00:26<00:00, 1.49it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.41it/s] all 38 905 0.944 0.789 0.851 0.594 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 84/100 7.18G 0.6918 0.3444 0.7818 143 640: 100% 39/39 [00:24<00:00, 1.56it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:01<00:00, 1.70it/s] all 38 905 0.877 0.795 0.835 0.602 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 85/100 7.34G 0.689 0.3389 0.7804 161 640: 100% 39/39 [00:25<00:00, 1.51it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.37it/s] all 38 905 0.945 0.744 0.833 0.602 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 86/100 7.37G 0.6858 0.3364 0.7831 102 640: 100% 39/39 [00:25<00:00, 1.50it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.44it/s] all 38 905 0.941 0.77 0.842 0.6 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 87/100 7.33G 0.6843 0.3355 0.7824 181 640: 100% 39/39 [00:25<00:00, 1.50it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.73it/s] all 38 905 0.937 0.777 0.844 0.608 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 88/100 7.36G 0.6764 0.3323 0.7819 177 640: 100% 39/39 [00:25<00:00, 1.51it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.72it/s] all 38 905 0.956 0.787 0.848 0.618 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 89/100 7.13G 0.6551 0.3262 0.7837 97 640: 100% 39/39 [00:25<00:00, 1.52it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.19it/s] all 38 905 0.943 0.753 0.841 0.604 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 90/100 7.25G 0.6674 0.3303 0.7849 94 640: 100% 39/39 [00:25<00:00, 1.53it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.26it/s] all 38 905 0.933 0.79 0.853 0.618 Closing dataloader mosaic albumentations: Blur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01), CLAHE(p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8)) Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 91/100 7.14G 0.6173 0.3181 0.7832 85 640: 100% 39/39 [00:30<00:00, 1.26it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.34it/s] all 38 905 0.972 0.75 0.84 0.594 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 92/100 7.1G 0.6076 0.3133 0.7797 90 640: 100% 39/39 [00:24<00:00, 1.61it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.79it/s] all 38 905 0.946 0.781 0.844 0.611 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 93/100 7.14G 0.5945 0.3093 0.7819 93 640: 100% 39/39 [00:24<00:00, 1.61it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.32it/s] all 38 905 0.979 0.775 0.847 0.617 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 94/100 7.15G 0.5952 0.3044 0.7826 95 640: 100% 39/39 [00:24<00:00, 1.60it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.45it/s] all 38 905 0.978 0.737 0.836 0.595 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 95/100 7.13G 0.5899 0.3044 0.7794 90 640: 100% 39/39 [00:24<00:00, 1.62it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.27it/s] all 38 905 0.936 0.768 0.837 0.595 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 96/100 7.11G 0.5828 0.2996 0.7781 94 640: 100% 39/39 [00:24<00:00, 1.60it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.30it/s] all 38 905 0.938 0.777 0.842 0.599 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 97/100 7.15G 0.57 0.2953 0.7758 95 640: 100% 39/39 [00:23<00:00, 1.63it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.30it/s] all 38 905 0.938 0.784 0.848 0.607 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 98/100 7.15G 0.5678 0.2913 0.7801 89 640: 100% 39/39 [00:23<00:00, 1.64it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.46it/s] all 38 905 0.92 0.78 0.846 0.607 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 99/100 7.13G 0.5756 0.2939 0.7762 95 640: 100% 39/39 [00:24<00:00, 1.60it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.51it/s] all 38 905 0.927 0.784 0.849 0.616 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 100/100 7.1G 0.5788 0.2974 0.7815 94 640: 100% 39/39 [00:23<00:00, 1.68it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:01<00:00, 1.98it/s] all 38 905 0.931 0.783 0.85 0.614 100 epochs completed in 0.822 hours. Optimizer stripped from runs/detect/train/weights/last.pt, 52.0MB Optimizer stripped from runs/detect/train/weights/best.pt, 52.0MB Validating runs/detect/train/weights/best.pt... Ultralytics YOLOv8.0.235 🚀 Python-3.10.12 torch-2.1.0+cu121 CUDA:0 (Tesla T4, 15102MiB) Model summary (fused): 218 layers, 25842076 parameters, 0 gradients, 78.7 GFLOPs Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:00<00:00, 2.21it/s] all 38 905 0.933 0.79 0.853 0.619 ball 38 35 0.937 0.314 0.48 0.22 goalkeeper 38 27 0.864 0.963 0.972 0.776 player 38 754 0.972 0.971 0.988 0.802 referee 38 89 0.958 0.91 0.972 0.677 Speed: 0.2ms preprocess, 9.7ms inference, 0.0ms loss, 1.4ms postprocess per image Results saved to runs/detect/train 💡 Learn more at https://docs.ultralytics.com/modes/train
Image(filename=f'/content/runs/detect/train/confusion_matrix.png', width=900)
--------------------------------------------------------------------------- NameError Traceback (most recent call last) <ipython-input-1-ac603104561d> in <cell line: 1>() ----> 1 Image(filename=f'/content/runs/detect/train/confusion_matrix.png', width=900) NameError: name 'Image' is not defined
Image(filename=f'/content/runs/detect/train/results.png', width=800)
!yolo task=detect mode=val model=/content/runs/detect/train/weights/best.pt data={dataset.location}/data.yaml
Ultralytics YOLOv8.0.234 🚀 Python-3.10.12 torch-2.1.0+cu121 CUDA:0 (Tesla T4, 15102MiB) Model summary (fused): 218 layers, 25842076 parameters, 0 gradients, 78.7 GFLOPs val: Scanning /content/football-players-detection-2/valid/labels.cache... 38 images, 0 backgrounds, 0 corrupt: 100% 38/38 [00:00<?, ?it/s] Class Images Instances Box(P R mAP50 mAP50-95): 0% 0/3 [00:00<?, ?it/s]WARNING ⚠️ NMS time limit 1.300s exceeded Class Images Instances Box(P R mAP50 mAP50-95): 100% 3/3 [00:06<00:00, 2.26s/it] all 38 905 0.936 0.508 0.663 0.492 ball 38 35 0.911 0.294 0.442 0.212 goalkeeper 38 27 0.879 0.556 0.676 0.531 player 38 754 0.979 0.585 0.771 0.651 referee 38 89 0.974 0.596 0.765 0.574 Speed: 10.4ms preprocess, 50.6ms inference, 0.0ms loss, 45.3ms postprocess per image Results saved to runs/detect/val 💡 Learn more at https://docs.ultralytics.com/modes/val
!yolo task=detect mode=predict model=/content/runs/detect/train/weights/best.pt conf=0.25 source={dataset.location}/test/images
Ultralytics YOLOv8.0.234 🚀 Python-3.10.12 torch-2.1.0+cu121 CUDA:0 (Tesla T4, 15102MiB)
Model summary (fused): 218 layers, 25842076 parameters, 0 gradients, 78.7 GFLOPs
WARNING ⚠️ NMS time limit 0.550s exceeded
image 1/13 /content/football-players-detection-2/test/images/40cd38_7_6_png.rf.dc7957fcce915bc48188f18a7b19455b.jpg: 640x640 21 players, 2 referees, 37.1ms
image 2/13 /content/football-players-detection-2/test/images/42ba34_1_5_png.rf.927d602c034ce2997f58f62a7c1245ba.jpg: 640x640 1 ball, 1 goalkeeper, 22 players, 2 referees, 37.1ms
image 3/13 /content/football-players-detection-2/test/images/42ba34_5_5_png.rf.f691b18c36a92663c7241c99d4202bcc.jpg: 640x640 1 goalkeeper, 19 players, 1 referee, 37.1ms
image 4/13 /content/football-players-detection-2/test/images/4b770a_1_4_png.rf.8a0f6be9776a652d40938181f60b3a6c.jpg: 640x640 1 goalkeeper, 19 players, 2 referees, 37.0ms
image 5/13 /content/football-players-detection-2/test/images/4b770a_3_6_png.rf.f5d975605c1f73e1a95a1d8edc4ce5b1.jpg: 640x640 1 goalkeeper, 20 players, 1 referee, 37.1ms
image 6/13 /content/football-players-detection-2/test/images/573e61_1_9_png.rf.3e04feabb7fa88ed2691adcb5034e6ae.jpg: 640x640 18 players, 2 referees, 37.1ms
image 7/13 /content/football-players-detection-2/test/images/573e61_9_6_png.rf.f7756714cdfe79da92e3e99837b7b655.jpg: 640x640 1 goalkeeper, 19 players, 3 referees, 37.0ms
image 8/13 /content/football-players-detection-2/test/images/744b27_1_10_png.rf.322f9266079f0424f6aebb23c23cc6de.jpg: 640x640 1 goalkeeper, 20 players, 2 referees, 37.1ms
image 9/13 /content/football-players-detection-2/test/images/744b27_7_4_png.rf.f34ba47e8f30126bc935832bd269ef19.jpg: 640x640 2 balls, 1 goalkeeper, 19 players, 3 referees, 37.2ms
image 10/13 /content/football-players-detection-2/test/images/744b27_9_9_png.rf.1600b8abf2a9ae799312009febc9002e.jpg: 640x640 1 goalkeeper, 19 players, 1 referee, 37.1ms
image 11/13 /content/football-players-detection-2/test/images/798b45_3_3_png.rf.f5479e3b29e91874aaa4ed87e7d08b4a.jpg: 640x640 1 ball, 1 goalkeeper, 20 players, 2 referees, 37.1ms
image 12/13 /content/football-players-detection-2/test/images/a9f16c_2_10_png.rf.f29e544daf06eb8b4e968d158a40af1b.jpg: 640x640 1 ball, 1 goalkeeper, 17 players, 3 referees, 37.0ms
image 13/13 /content/football-players-detection-2/test/images/a9f16c_2_9_png.rf.c048a60764e56735d7465cdec974d102.jpg: 640x640 1 goalkeeper, 20 players, 2 referees, 37.1ms
Speed: 2.5ms preprocess, 37.1ms inference, 50.1ms postprocess per image at shape (1, 3, 640, 640)
Results saved to runs/detect/predict2
💡 Learn more at https://docs.ultralytics.com/modes/predict
import glob
from IPython.display import Image, display
for image_path in glob.glob(f'/content/runs/detect/predict/*.jpg')[:3]:
display(Image(filename=image_path,height=600))
print("\n")
