Good :
https://blog.csdn.net/qq_46378251/article/details/128773539
https://blog.csdn.net/m0_59286668/article/details/128768117
https://www.jianshu.com/p/87661307c5b2
https://zhuanlan.zhihu.com/p/371296750
https://blog.csdn.net/m0_59286668/article/details/128768117
CAM
https://github.com/jacobgil/pytorch-grad-cam
Chosing the Target Layer
You need to choose the target layer to compute CAM for. Some common choices are:
- FasterRCNN: model.backbone
- Resnet18 and 50: model.layer4[-1]
- VGG and densenet161: model.features[-1]
- mnasnet1_0: model.layers[-1]
- ViT: model.blocks[-1].norm1
- SwinT: model.layers[-1].blocks[-1].norm1
If you pass a list with several layers, the CAM will be averaged accross them. This can be useful if you're not sure what layer will perform best.
!git clone https://github.com/frgfm/torch-cam.git
!pip install -e torch-cam/.
pip install torchcam
os.chdir("/data/pincer/other/Train_Custom_Dataset-main/")
!python torch-cam/scripts/cam_example.py --help
usage: cam_example.py [-h] [--arch ARCH] [--img IMG] [--class-idx CLASS_IDX] [--device DEVICE] [--savefig SAVEFIG] [--method METHOD] [--target TARGET] [--alpha ALPHA] [--rows ROWS] [--noblock] Saliency Map comparison optional arguments: -h, --help show this help message and exit --arch ARCH Name of the architecture (default: resnet18) --img IMG The image to extract CAM from (default: https://www.woopets.fr/assets/races/000/066/big- portrait/border-collie.jpg) --class-idx CLASS_IDX Index of the class to inspect (default: 232) --device DEVICE Default device to perform computation on (default: None) --savefig SAVEFIG Path to save figure (default: None) --method METHOD CAM method to use (default: None) --target TARGET the target layer (default: None) --alpha ALPHA Transparency of the heatmap (default: 0.5) --rows ROWS Number of rows for the layout (default: 1) --noblock Disables blocking visualization (default: False)
# 类别-边牧犬
!python torch-cam/scripts/cam_example.py \
--img test_img/border-collie.jpg \
--savefig output/B1_border_collie.jpg \
--arch resnet18 \
--class-idx 232 \
--rows 2
/home/software/anaconda3/envs/tf115/lib/python3.7/site-packages/torchvision/models/_utils.py:209: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. f"The parameter '{pretrained_param}' is deprecated since 0.13 and may be removed in the future, " /home/software/anaconda3/envs/tf115/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) Downloading: "https://download.pytorch.org/models/resnet18-f37072fd.pth" to /root/.cache/torch/hub/checkpoints/resnet18-f37072fd.pth 100%|██████████████████████████████████████| 44.7M/44.7M [00:02<00:00, 15.6MB/s] WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `fc_layer`, thus set to 'fc'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. Figure(600x400)
# 类别-虎斑猫
!python torch-cam/scripts/cam_example.py \
--img test_img/cat_dog.jpg \
--savefig output/B2_cat_dog.jpg \
--arch resnet18 \
--class-idx 282 \
--rows 2
/home/software/anaconda3/envs/tf115/lib/python3.7/site-packages/torchvision/models/_utils.py:209: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. f"The parameter '{pretrained_param}' is deprecated since 0.13 and may be removed in the future, " /home/software/anaconda3/envs/tf115/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `fc_layer`, thus set to 'fc'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'.
# 类别-边牧犬
!python torch-cam/scripts/cam_example.py \
--img test_img/cat_dog.jpg \
--savefig output/B3_cat_dog.jpg \
--arch resnet18 \
--class-idx 232 \
--rows 2
/home/software/anaconda3/envs/tf115/lib/python3.7/site-packages/torchvision/models/_utils.py:209: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. f"The parameter '{pretrained_param}' is deprecated since 0.13 and may be removed in the future, " /home/software/anaconda3/envs/tf115/lib/python3.7/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights. warnings.warn(msg) WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `fc_layer`, thus set to 'fc'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'. WARNING:root:no value was provided for `target_layer`, thus set to 'layer4'.
标签:layer,set,cam,--,py,WARNING,CAM,root,target From: https://www.cnblogs.com/emanlee/p/17112542.html