GradCAM PyTorch

⭐ Star us on GitHub — it helps!!

PyTorch implementation for Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization

Install

You will need a machine with a GPU and CUDA installed.
Then, you prepare runtime environment:

pip install -r requirements.txt

Use

CUDA_VISIBLE_DEVICES=0 python main.py --model_path=resnet50 --img_path=examples/catdog.png --select_t_layer=False

Arguments:

• model_path - Choose a pretrained model in torchvision.models or saved model (.pt)
  • Examples of available list: ['alexnet', 'vgg19', 'resnet50', 'densenet169', 'mobilenet_v2' ,'wide_resnet50_2', ...]
• img_path - Image Path
• select_t_layer - Choose a target layer manually?
  • If True, you can select a layer and get GradCAM for the layer.
  • Elif False, you can get GradCAM automatically.

Guide for selecting a target layer manually

If you want to select a target layer manually, you run the following code:

CUDA_VISIBLE_DEVICES=0 python main.py --model_path=resnet50 --img_path=examples/catdog.png --select_t_layer=True

You can get system print such as the following figure (left).
Suppose that you select(type) 'number' or 'name' of a target layer like as the figure (middle). And then, you can get GradCAM result.

How to use your customized model

If you want to use a customized model that has a data type 'OrderedDict', you shoud type a code that loads model object.

Search 'load model' function in utils.py and type a code such as:

from yourNetwork import yourNetwork())
model=yourNetwork()

Understanding GradCAM

✅ Check my blog!! GradCAM in da2so