Search Packages

torchdistill

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.

image-classification-tools

Demonstration of the CIFAR-10 deeplearning task with PyTorch and TensorFlow

cifar10-tools

Demonstration of the CIFAR-10 deeplearning task with PyTorch and TensorFlow

bsconv

Reference implementation for Blueprint Separable Convolutions (CVPR 2020)

ewe-gate

Epistemic Weight Engine (EWE) — A pre-update gating mechanism for signal-reliability-weighted learning in AI systems. ACM TIST 2026.

nbdt

Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet

naszilla

python framework for NAS algorithms on benchmark search spaces

aognet

Code for CVPR 2019 paper: " Learning Deep Compositional Grammatical Architectures for Visual Recognition"