Home Explore Help
Register Sign In
AIModelWatermark
/
classification-main
2
0
Fork 0
Files Issues 0 Pull Requests 0 Wiki
Branch: whitebox_wm_integrate
Branches Tags
classificati...
/
bash_train.sh

bash_train.sh 2.8 KB
Permalink History Raw

123456789101112131415161718192021222324 
  1. 

  2. # For 用于训练不同模型，以及保存相应的路径
    3. 

  3. # -------------------------------------------------------------------------------------------------------------------- #
    4. 

  4. python train.py --model 'LeNet' --input_size 32 --save_path './checkpoints/efficientnetv2_s/watermarking/best.pt' --save_path_last './checkpoints/efficientnetv2_s/watermarking/last.pt' --epoch 100
    5. 

  5. python train.py --model 'Alexnet' --input_size 500 --checkpoint_dir './checkpoints/Alexnet/black_wm' --data_path './dataset' --dataset_name 'imagenette2' --output_num 10  --epoch 50 --num_worker 2 --batch 50 --lr_end_epoch 50 --lr_start 0.001
    6. 

  6. python train.py --model 'VGG19' --save_path './checkpoints/VGG19/watermarking/best.pt' --save_path_last './checkpoints/VGG19/watermarking/last.pt' --epoch 100
    7. 

  7. python train.py --model 'GoogleNet' --input_size 32 --save_path './checkpoints/GoogleNet/watermarking/best.pt' --save_path_last './checkpoints/GoogleNet/watermarking/last.pt' --epoch 100
    8. 

  8. python train.py --model 'resnet' --save_path './checkpoints/resnet/watermarking/best.pt' --save_path_last './checkpoints/resnet/watermarking/last.pt' --epoch 100
    9. 

  9. 

  10. 

  11. # For 用于剪枝模型，剪枝后微调训练，保存剪枝后模型路径，以及验证微调模型准确性
    12. 

  12. # -------------------------------------------------------------------------------------------------------------------- #
    13. 

  13. python train.py --model 'resnet'  --prune True --prune_weight './checkpoints/resnet/watermarking/best.pt' --prune_save './checkpoints/resnet/watermarking/prune_best.pt' --epoch 40
    14. 

  14. python train.py --model 'VGG19'  --prune True --prune_weight './checkpoints/VGG19/watermarking/best.pt' --prune_save './checkpoints/VGG19/watermarking/prune_best.pt' --epoch 40
    15. 

  15. python train.py --model 'Alexnet'  --prune True --input_size 112 --prune_weight './checkpoints/Alexnet/watermarking/best.pt' --prune_save './checkpoints/Alexnet/watermarking/prune_best.pt' --epoch 40
    16. 

  16. python train.py --model 'mobilenetv2'  --prune True --prune_weight './checkpoints/mobilenetv2/watermarking/best.pt' --prune_save './checkpoints/mobilenetv2/watermarking/prune_best.pt' --epoch 40
    17. 

  17. python train.py --model 'GoogleNet' --input_size 32 --prune True --prune_weight './checkpoints/GoogleNet/watermarking/best.pt' --prune_save './checkpoints/GoogleNet/watermarking/prune_best.pt' --epoch 40
    18. 

  18. python train.py --model 'badnet' --input_size 32 --prune True --prune_weight './checkpoints/badnet/watermarking/best.pt' --prune_save './checkpoints/badnet/watermarking/prune_best.pt' --epoch 40
    19. 

  19. python train.py --model 'efficientnet' --input_size 32 --prune True --prune_weight './checkpoints/efficientnetv2_s/watermarking/best.pt' --prune_save './checkpoints/efficientnetv2_s/watermarking/prune_best.pt' --epoch 40
    20. 

  20. 

  21. 

  22. 

  23. # For 用于剪枝模型后边缘部署
    24. 

  24. # -------------------------------------------------------------------------------------------------------------------- #
    25.