Awesome

Simple way to leverage the class-specific activation of convolutional layers in PyTorch.

Quick Tour

Setting your CAM

TorchCAM leverages PyTorch hooking mechanisms to seamlessly retrieve all required information to produce the class activation without additional efforts from the user. Each CAM object acts as a wrapper around your model.

You can find the exhaustive list of supported CAM methods in the documentation, then use it as follows:

# Define your model
from torchvision.models import resnet18
model = resnet18(pretrained=True).eval()

# Set your CAM extractor
from torchcam.methods import SmoothGradCAMpp
cam_extractor = SmoothGradCAMpp(model)

Please note that by default, the layer at which the CAM is retrieved is set to the last non-reduced convolutional layer. If you wish to investigate a specific layer, use the target_layer argument in the constructor.

Retrieving the class activation map

Once your CAM extractor is set, you only need to use your model to infer on your data as usual. If any additional information is required, the extractor will get it for you automatically.

from torchvision.io.image import read_image
from torchvision.transforms.functional import normalize, resize, to_pil_image
from torchvision.models import resnet18
from torchcam.methods import SmoothGradCAMpp

model = resnet18(pretrained=True).eval()
# Get your input
img = read_image("path/to/your/image.png")
# Preprocess it for your chosen model
input_tensor = normalize(resize(img, (224, 224)) / 255., [0.485, 0.456, 0.406], [0.229, 0.224, 0.225])

with SmoothGradCAMpp(model) as cam_extractor:
  # Preprocess your data and feed it to the model
  out = model(input_tensor.unsqueeze(0))
  # Retrieve the CAM by passing the class index and the model output
  activation_map = cam_extractor(out.squeeze(0).argmax().item(), out)

If you want to visualize your heatmap, you only need to cast the CAM to a numpy ndarray:

import matplotlib.pyplot as plt
# Visualize the raw CAM
plt.imshow(activation_map[0].squeeze(0).numpy()); plt.axis('off'); plt.tight_layout(); plt.show()

Or if you wish to overlay it on your input image:

import matplotlib.pyplot as plt
from torchcam.utils import overlay_mask

# Resize the CAM and overlay it
result = overlay_mask(to_pil_image(img), to_pil_image(activation_map[0].squeeze(0), mode='F'), alpha=0.5)
# Display it
plt.imshow(result); plt.axis('off'); plt.tight_layout(); plt.show()

Setup

Python 3.8 (or higher) and pip/conda are required to install TorchCAM.

Stable release

You can install the last stable release of the package using pypi as follows:

pip install torchcam

or using conda:

conda install -c frgfm torchcam

Developer installation

Alternatively, if you wish to use the latest features of the project that haven't made their way to a release yet, you can install the package from source:

git clone https://github.com/frgfm/torch-cam.git
pip install -e torch-cam/.

CAM Zoo

This project is developed and maintained by the repo owner, but the implementation was based on the following research papers:

• Learning Deep Features for Discriminative Localization: the original CAM paper
• Grad-CAM: GradCAM paper, generalizing CAM to models without global average pooling.
• Grad-CAM++: improvement of GradCAM++ for more accurate pixel-level contribution to the activation.
• Smooth Grad-CAM++: SmoothGrad mechanism coupled with GradCAM.
• Score-CAM: score-weighting of class activation for better interpretability.
• SS-CAM: SmoothGrad mechanism coupled with Score-CAM.
• IS-CAM: integration-based variant of Score-CAM.
• XGrad-CAM: improved version of Grad-CAM in terms of sensitivity and conservation.
• Layer-CAM: Grad-CAM alternative leveraging pixel-wise contribution of the gradient to the activation.

What else

Documentation

The full package documentation is available here for detailed specifications.

Demo app

A minimal demo app is provided for you to play with the supported CAM methods! Feel free to check out the live demo on

If you prefer running the demo by yourself, you will need an extra dependency (Streamlit) for the app to run:

pip install -e ".[demo]"

You can then easily run your app in your default browser by running:

streamlit run demo/app.py

Example script

An example script is provided for you to benchmark the heatmaps produced by multiple CAM approaches on the same image:

python scripts/cam_example.py --arch resnet18 --class-idx 232 --rows 2

All script arguments can be checked using python scripts/cam_example.py --help

Latency benchmark

You crave for beautiful activation maps, but you don't know whether it fits your needs in terms of latency?

In the table below, you will find a latency benchmark (forward pass not included) for all CAM methods:

*The base CAM method cannot work with architectures that have multiple fully-connected layers

This benchmark was performed over 100 iterations on (224, 224) inputs, on a laptop to better reflect performances that can be expected by common users. The hardware setup includes an Intel(R) Core(TM) i7-10750H for the CPU, and a NVIDIA GeForce RTX 2070 with Max-Q Design for the GPU.

You can run this latency benchmark for any CAM method on your hardware as follows:

python scripts/eval_latency.py SmoothGradCAMpp

All script arguments can be checked using python scripts/eval_latency.py --help

Example notebooks

Looking for more illustrations of TorchCAM features? You might want to check the Jupyter notebooks designed to give you a broader overview.

Citation

If you wish to cite this project, feel free to use this BibTeX reference:

@misc{torcham2020,
    title={TorchCAM: class activation explorer},
    author={François-Guillaume Fernandez},
    year={2020},
    month={March},
    publisher = {GitHub},
    howpublished = {\url{https://github.com/frgfm/torch-cam}}
}

Contributing

Feeling like extending the range of possibilities of CAM? Or perhaps submitting a paper implementation? Any sort of contribution is greatly appreciated!

You can find a short guide in CONTRIBUTING to help grow this project!

License

Distributed under the Apache 2.0 License. See LICENSE for more information.