A collection of learning resources for curious software engineers

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

Code release for ConvNeXt model

🎥 Python and OpenCV-based scene cut/transition detection program & library.

3D ResNets for Action Recognition (CVPR 2018)

Flexible Python configuration system. The last one you will ever need.

The friendly PIL fork

PyTorch implementation of Contrastive Learning methods

Video classification tools using 3D ResNet

Gradually-Warmup Learning Rate Scheduler for PyTorch

Leaf: A Benchmark for Federated Settings

Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch

【ICLR 2024🔥】 Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations by T. Chen et al.

Federated Optimization in Heterogeneous Networks (MLSys '20)

Library for reading and processing ML training data.

Generic template to bootstrap your PyTorch project.

Federated Learning Benchmark - Federated Learning on Non-IID Data Silos: An Experimental Study (ICDE 2022)

Implementation of ViViT: A Video Vision Transformer

Inflated i3d network with inception backbone, weights transfered from tensorflow

A Pytorch-Lightning implementation of self-supervised algorithms

Code for the Convolutional Vision Transformer (ConViT)

Pytorch port of Google Research's VGGish model used for extracting audio features.

IDE for PyTorch and its ecosystem

Deal with bad samples in your dataset dynamically, use Transforms as Filters, and more!

PyTorch implementation of a collections of scalable Video Transformer Benchmarks.