This repository provides tools to load and inference Convolutional Neural Network (CNN) models using PyTorch and Python, as well as visualize the intermediate tensors using Svelte and JavaScript.
Clone the repository:
git clone https://github.com/vibalab/CNNExplorer
Install conda environment and python dependencies:
conda create -n cnnexplorer python==3.11.5
conda activate cnnexplorer
pip install -r requirements.txt
Download imagenet sample images
cd server
git clone https://github.com/EliSchwartz/imagenet-sample-images
cd ..
Install nvm and NodeJS following link
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.7/install.sh | bash
source ~/.bashrc
nvm install node
Install Svelte and JavaScript dependencies:
cd client
npm install
cd ..
Example:
cd server
mkdir weights
python get_pretrained.py # get pretrained torchvision models
python app.py
Start the Svelte development server:
cd client
npm run dev
Open your web browser and navigate to http://localhost:8080
.
Contributions are welcome! Please feel free to open issues or pull requests for any improvements or features you'd like to see.
This project is licensed under the MIT License - see the LICENSE file for details.