def train_yolov8(model, data_path, img_size, batch_size, epochs, project_name, project_dir): results = model.train( data=data_path, imgsz=img_size, epochs=epochs, batch=batch_size, name=project_name, project=project_dir, warmup_epochs=1.0, box=0.02, mosaic=0.5, optimizer='AdamW', lr0=0.0001, )

epochs = 10
data_path = r'C:\Users\oosnu\mlproject\data\data.yaml'
img_size = 640
batch_size = 64
project_name = 'yolov8n_custom'
project_dir = 'runs/train'

10 epochs completed in 23.234 hours. Optimizer stripped from runs\train\yolov8n_custom38\weights\last.pt, 6.2MB Optimizer stripped from runs\train\yolov8n_custom38\weights\best.pt, 6.2MB

Validating runs\train\yolov8n_custom38\weights\best.pt... Ultralytics YOLOv8.2.25 🚀 Python-3.10.12 torch-2.3.0+cu118 CUDA:0 (NVIDIA GeForce RTX 3060, 12287MiB) Model summary (fused): 168 layers, 3015593 parameters, 0 gradients, 8.1 GFLOPs Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 574/574 [06: all 73379 93309 0.953 0.916 0.96 0.816 Ball 73379 600 0.975 0.94 0.975 0.701 Baseball Bat 73379 724 0.971 0.971 0.991 0.835 Baseball Glove 73379 672 0.994 0.984 0.995 0.862 Bench 73379 4777 0.951 0.897 0.957 0.825 Bicycle 73379 6859 0.966 0.949 0.982 0.876 Boat 73379 225 0.923 0.893 0.941 0.647 Book 73379 1925 0.967 0.941 0.968 0.875 Bottle 73379 1730 0.956 0.903 0.962 0.768 Bus 73379 376 0.933 0.777 0.868 0.739 Calendar 73379 1290 0.99 0.973 0.994 0.93 Camera 73379 1401 0.955 0.944 0.976 0.775 Can 73379 2195 0.975 0.974 0.992 0.841 Cap 73379 1095 0.989 0.985 0.994 0.883 Car 73379 7376 0.882 0.793 0.905 0.792 Cat 73379 599 0.917 0.843 0.931 0.668 Chair 73379 1113 0.917 0.855 0.911 0.837 Clock 73379 1483 0.933 0.954 0.979 0.846 Cup 73379 2210 0.952 0.95 0.982 0.874 Dish 73379 1525 0.965 0.935 0.973 0.838 Dog 73379 94 0.88 0.704 0.883 0.595 Flowerpot 73379 1940 0.938 0.871 0.932 0.77 Folding_Fan 73379 1074 0.965 0.979 0.989 0.854 Frame 73379 2402 0.965 0.974 0.988 0.908 Glasses 73379 1910 0.966 0.973 0.99 0.836 Handbag 73379 1185 0.974 0.969 0.99 0.878 Human 73379 783 0.84 0.516 0.656 0.466 Kettle 73379 1127 0.98 0.969 0.993 0.884 Keyboard 73379 774 0.971 0.951 0.975 0.848 Labacon 73379 5966 0.963 0.894 0.953 0.809 Ladle 73379 945 0.958 0.964 0.986 0.786 Laptop 73379 758 0.954 0.955 0.982 0.916 Mirror 73379 1204 0.927 0.92 0.962 0.821 Monitor 73379 513 0.99 0.945 0.989 0.905 Motorcycle 73379 6244 0.965 0.944 0.98 0.808 Mouse 73379 1169 0.968 0.96 0.988 0.821 Pot 73379 1244 0.99 0.987 0.995 0.879 Racket 73379 741 0.971 0.98 0.989 0.869 Remote 73379 1288 0.975 0.941 0.986 0.776 Scooter 73379 4423 0.974 0.955 0.977 0.874 Seesaw 73379 887 0.946 0.885 0.948 0.725 Smart Phone 73379 2115 0.973 0.968 0.99 0.846 Stand lamp 73379 376 0.865 0.705 0.846 0.737 Station 73379 575 0.982 0.938 0.979 0.833 Suitcase 73379 73 0.927 0.945 0.947 0.824 Swing 73379 797 0.98 0.957 0.986 0.86 Table 73379 4723 0.927 0.954 0.978 0.94 Trash Can 73379 1257 0.971 0.858 0.936 0.85 Truck 73379 5480 0.935 0.899 0.96 0.847 Umbrella 73379 1817 0.969 0.954 0.987 0.855 Wallet 73379 920 0.946 0.898 0.966 0.793 Weight 73379 330 0.96 0.933 0.985 0.789 Speed: 0.1ms preprocess, 2.1ms inference, 0.0ms loss, 0.7ms postprocess per image Results saved to runs\train\yolov8n_custom38