mit-zardini-lab/pyncd

A JAX research toolkit for building, editing, and visualizing neural networks.

Capture every activation and gradient of any PyTorch model — forward and backward — with automatic graph visualization, rich metadata, and live interventions. Works on any architecture, including dynamic and recurrent ones.

PyC (Pytorch Concepts) is a PyTorch-based library for designing concept-based interpretable deep learning models.

VisualTorch aims to help visualize Torch-based neural network architectures.

Multi-framework implementation of Deep Kernel Shaping and Tailored Activation Transformations, which are methods that modify neural network models (and their initializations) to make them easier to train.

Interactive Pytorch forward pass visualization in notebooks

Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM, Finer-CAM, LeGrad, RefineCAM)

A coding-free framework built on PyTorch for reproducible deep learning studies. PyTorch Ecosystem. 🏆26 knowledge distillation methods presented at TPAMI, CVPR, ICLR, ECCV, NeurIPS, ICCV, AAAI, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.

Speed of Light Analysis for ML Model Runtime