mmclassification/docs/en/user_guides/visualization.md

Visualization Tools

• Browse Dataset
• Parameter Schedule Visualization
• Class Activation Map Visualization
• FAQs

Browse Dataset

python tools/visualizations/browse_dataset.py \
    ${CONFIG_FILE} \
    [-o, --output-dir ${OUTPUT_DIR}] \
    [-p, --phase ${DATASET_PHASE}] \
    [-n, --show-number ${NUMBER_IMAGES_DISPLAY}] \
    [-i, --show-interval ${SHOW_INTERRVAL}] \
    [-m, --mode ${DISPLAY_MODE}] \
    [-r, --rescale-factor ${RESCALE_FACTOR}] \
    [-c, --channel-order ${CHANNEL_ORDER}] \
    [--cfg-options ${CFG_OPTIONS}]

Description of all arguments：

• config : The path of a model config file.
• -o, --output-dir: The output path for visualized images. If not specified, it will be set to '', which means not to save.
• -p, --phase: Phase of visualizing dataset，must be one of ['train', 'val', 'test']. If not specified, it will be set to 'train'.
• -n, --show-number: The number of samples to visualized. If not specified, display all images in the dataset.
• --show-interval: The interval of show (s).
• -m, --mode: The display mode, can be one of ['original', 'transformed', 'concat', 'pipeline']. If not specified, it will be set to 'transformed'.
• -r, --rescale-factor: The image rescale factor, which is useful if the output is too large or too small.
• -c, --channel-order: The channel of the showing images, could be "BGR" or "RGB", If not specified, it will be set to 'BGR'.
• --cfg-options : Modifications to the configuration file, refer to Learn about Configs.

1. The `-m, --mode` is about display mode, display original pictures or transformed pictures or comparison pictures:
- "original" means show images load from disk;
- "transformed" means to show images after transformed;
- "concat" means show images stitched by "original" and "transformed" images;
- "pipeline" means show all the intermediate images throghout the pipeline.

2.  The `-r, --rescale-factor` option is set when the label information is too large or too small relative to the picture. For example, when visualizing the CIFAR dataset, since the resolution of the image is very small, `--rescale-factor` can be set to 10.

Examples：

1. In 'original' mode:

python ./tools/visualizations/browse_dataset.py ./configs/resnet/resnet101_8xb16_cifar10.py --phase val --output-dir tmp --mode original --show-number 100 --rescale-factor 10 --channel-order RGB

• --phase val: Visual validation set, can be simplified to -p val;
• --output-dir tmp: The visualization results are saved in the "tmp" folder, can be simplified to -o tmp;
• --mode original: Visualize the original image, can be simplified to -m original;
• --show-number 100: visualize 100 images, can be simplified to -n 100;
• --rescale-factor: the image is enlarged by 10 times, can be simplified to -r 10;
• --channel-order RGB: The channel order of the visualized image is "RGB", can be simplified to -c RGB.

2. In 'transformed' mode:

python ./tools/visualizations/browse_dataset.py ./configs/resnet/resnet50_8xb32_in1k.py -n 100 -r 2

3. In 'concat' mode:

python ./tools/visualizations/browse_dataset.py configs/swin_transformer/swin-small_16xb64_in1k.py -n 10 -m concat

4. In 'pipeline' mode：

python ./tools/visualizations/browse_dataset.py configs/swin_transformer/swin-small_16xb64_in1k.py -m pipeline

Parameter Schedule Visualization

python tools/visualizations/vis_scheduler.py \
    ${CONFIG_FILE} \
    [-p, --parameter ${PARAMETER_NAME}] \
    [-d, --dataset-size ${DATASET_SIZE}] \
    [-n, --ngpus ${NUM_GPUs}] \
    [-s, --save-path ${SAVE_PATH}] \
    [--title ${TITLE}] \
    [--style ${STYLE}] \
    [--window-size ${WINDOW_SIZE}] \
    [--cfg-options]

Description of all arguments：

• config: The path of a model config file.
• -p, --parameter: The param to visualize its change curve, choose from "lr" and "momentum". Default to use "lr".
• -d, --dataset-size: The size of the datasets. If set，build_dataset will be skipped and ${DATASET_SIZE} will be used as the size. Default to use the function build_dataset.
• -n, --ngpus: The number of GPUs used in training, default to be 1.
• -s, --save-path: The learning rate curve plot save path, default not to save.
• --title: Title of figure. If not set, default to be config file name.
• --style: Style of plt. If not set, default to be whitegrid.
• --window-size: The shape of the display window. If not specified, it will be set to 12*7. If used, it must be in the format 'W*H'.
• --cfg-options: Modifications to the configuration file, refer to Learn about Configs.

Loading annotations maybe consume much time, you can directly specify the size of the dataset with `-d, dataset-size` to save time.

Examples：

python tools/visualizations/vis_scheduler.py configs/resnet/resnet50_b16x8_cifar100.py

When using ImageNet, directly specify the size of ImageNet, as below:

python tools/visualizations/vis_scheduler.py configs/repvgg/repvgg-B3g4_4xb64-autoaug-lbs-mixup-coslr-200e_in1k.py --dataset-size 1281167 --ngpus 4 --save-path ./repvgg-B3g4_4xb64-lr.jpg

Class Activation Map Visualization

MMClassification provides tools\visualizations\vis_cam.py tool to visualize class activation map. Please use pip install "grad-cam>=1.3.6" command to install pytorch-grad-cam.

The supported methods are as follows:

Method	What it does
GradCAM	Weight the 2D activations by the average gradient
GradCAM++	Like GradCAM but uses second order gradients
XGradCAM	Like GradCAM but scale the gradients by the normalized activations
EigenCAM	Takes the first principle component of the 2D Activations (no class discrimination, but seems to give great results)
EigenGradCAM	Like EigenCAM but with class discrimination: First principle component of Activations*Grad. Looks like GradCAM, but cleaner
LayerCAM	Spatially weight the activations by positive gradients. Works better especially in lower layers

Command：

python tools/visualizations/vis_cam.py \
    ${IMG} \
    ${CONFIG_FILE} \
    ${CHECKPOINT} \
    [--target-layers ${TARGET-LAYERS}] \
    [--preview-model] \
    [--method ${METHOD}] \
    [--target-category ${TARGET-CATEGORY}] \
    [--save-path ${SAVE_PATH}] \
    [--vit-like] \
    [--num-extra-tokens ${NUM-EXTRA-TOKENS}]
    [--aug_smooth] \
    [--eigen_smooth] \
    [--device ${DEVICE}] \
    [--cfg-options ${CFG-OPTIONS}]

Description of all arguments：

• img : The target picture path.
• config : The path of the model config file.
• checkpoint : The path of the checkpoint.
• --target-layers : The target layers to get activation maps, one or more network layers can be specified. If not set, use the norm layer of the last block.
• --preview-model : Whether to print all network layer names in the model.
• --method : Visualization method, supports GradCAM, GradCAM++, XGradCAM, EigenCAM, EigenGradCAM, LayerCAM, which is case insensitive. Defaults to GradCAM.
• --target-category : Target category, if not set, use the category detected by the given model.
• --save-path : The path to save the CAM visualization image. If not set, the CAM image will not be saved.
• --vit-like : Whether the network is ViT-like network.
• --num-extra-tokens : The number of extra tokens in ViT-like backbones. If not set, use num_extra_tokens the backbone.
• --aug_smooth : Whether to use TTA(Test Time Augment) to get CAM.
• --eigen_smooth : Whether to use the principal component to reduce noise.
• --device : The computing device used. Default to 'cpu'.
• --cfg-options : Modifications to the configuration file, refer to Learn about Configs.

The argument `--preview-model` can view all network layers names in the given model. It will be helpful if you know nothing about the model layers when setting `--target-layers`.

Examples(CNN)：

Here are some examples of target-layers in ResNet-50, which can be any module or layer:

• 'backbone.layer4' means the output of the forth ResLayer.
• 'backbone.layer4.2' means the output of the third BottleNeck block in the forth ResLayer.
• 'backbone.layer4.2.conv1' means the output of the conv1 layer in above BottleNeck block.

For `ModuleList` or `Sequential`, you can also use the index to specify which sub-module is the target layer.

For example, the `backbone.layer4[-1]` is the same as `backbone.layer4.2` since `layer4` is a `Sequential` with three sub-modules.

1. Use different methods to visualize CAM for ResNet50, the target-category is the predicted result by the given checkpoint, using the default target-layers.

   python tools/visualizations/vis_cam.py \
       demo/bird.JPEG \
       configs/resnet/resnet50_8xb32_in1k.py \
       https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_batch256_imagenet_20200708-cfb998bf.pth \
       --method GradCAM
       # GradCAM++, XGradCAM, EigenCAM, EigenGradCAM, LayerCAM
   

   Image	GradCAM	GradCAM++	EigenGradCAM	LayerCAM

2. Use different target-category to get CAM from the same picture. In ImageNet dataset, the category 238 is 'Greater Swiss Mountain dog', the category 281 is 'tabby, tabby cat'.

   python tools/visualizations/vis_cam.py \
       demo/cat-dog.png configs/resnet/resnet50_8xb32_in1k.py \
       https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_batch256_imagenet_20200708-cfb998bf.pth \
       --target-layers 'backbone.layer4.2' \
       --method GradCAM \
       --target-category 238
       # --target-category 281
   

   Category	Image	GradCAM	XGradCAM	LayerCAM
   Dog
   Cat

3. Use --eigen-smooth and --aug-smooth to improve visual effects.

   python tools/visualizations/vis_cam.py \
       demo/dog.jpg  \
       configs/mobilenet_v3/mobilenet-v3-large_8xb128_in1k.py \
       https://download.openmmlab.com/mmclassification/v0/mobilenet_v3/convert/mobilenet_v3_large-3ea3c186.pth \
       --target-layers 'backbone.layer16' \
       --method LayerCAM \
       --eigen-smooth --aug-smooth
   

   Image	LayerCAM	eigen-smooth	aug-smooth	eigen&aug

Examples(Transformer)：

Here are some examples:

• 'backbone.norm3' for Swin-Transformer;
• 'backbone.layers[-1].ln1' for ViT;

For ViT-like networks, such as ViT, T2T-ViT and Swin-Transformer, the features are flattened. And for drawing the CAM, we need to specify the --vit-like argument to reshape the features into square feature maps.

Besides the flattened features, some ViT-like networks also add extra tokens like the class token in ViT and T2T-ViT, and the distillation token in DeiT. In these networks, the final classification is done on the tokens computed in the last attention block, and therefore, the classification score will not be affected by other features and the gradient of the classification score with respect to them, will be zero. Therefore, you shouldn't use the output of the last attention block as the target layer in these networks.

To exclude these extra tokens, we need know the number of extra tokens. Almost all transformer-based backbones in MMClassification have the num_extra_tokens attribute. If you want to use this tool in a new or third-party network that don't have the num_extra_tokens attribute, please specify it the --num-extra-tokens argument.

1. Visualize CAM for Swin Transformer, using default target-layers:

   python tools/visualizations/vis_cam.py \
       demo/bird.JPEG  \
       configs/swin_transformer/swin-tiny_16xb64_in1k.py \
       https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_tiny_224_b16x64_300e_imagenet_20210616_090925-66df6be6.pth \
       --vit-like
   

2. Visualize CAM for Vision Transformer(ViT):

   python tools/visualizations/vis_cam.py \
       demo/bird.JPEG  \
       configs/vision_transformer/vit-base-p16_ft-64xb64_in1k-384.py \
       https://download.openmmlab.com/mmclassification/v0/vit/finetune/vit-base-p16_in21k-pre-3rdparty_ft-64xb64_in1k-384_20210928-98e8652b.pth \
       --vit-like \
       --target-layers 'backbone.layers[-1].ln1'
   

3. Visualize CAM for T2T-ViT:

   python tools/visualizations/vis_cam.py \
       demo/bird.JPEG  \
       configs/t2t_vit/t2t-vit-t-14_8xb64_in1k.py \
       https://download.openmmlab.com/mmclassification/v0/t2t-vit/t2t-vit-t-14_3rdparty_8xb64_in1k_20210928-b7c09b62.pth \
       --vit-like \
       --target-layers 'backbone.encoder[-1].ln1'
   

Image	ResNet50	ViT	Swin	T2T-ViT

FAQs

• None