chaoso

avatarify

Avatars for Zoom, Skype and other video-conferencing apps.

cl-ica

Code for the paper "Contrastive Learning Inverts the Data Generating Process".

CLIP_Video_Representation

Use CLIP to represent video for Retrieval Task

ClipBERT

Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning for image-text and video-text tasks.

conformal_classification

Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true class with high probability.

CP-Flow

Convex potential flows

DEFT

Joint detection and tracking model named DEFT, or ``Detection Embeddings for Tracking." Our approach relies on an appearance-based object matching network jointly-learned with an underlying object detection network. An LSTM is also added to capture motion constraints.

elastic

PyTorch elastic training

entropix

Computing the information content of trained neural networks

gcm-cf

[CVPR 2021] Released code for Counterfactual Zero-Shot and Open-Set Visual Recognition

gradinit

Learning to Initialize Neural Networks for Stable and Efficient Training

Hub

Fastest unstructured dataset management for TensorFlow/PyTorch. Stream data real-time & version-control it. http://activeloop.ai

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

LD

Localization Distillation for Object Detection

MAI-2021-Workshop

MAI 2021 Workshop

model_search

MPL-pytorch

Unofficial PyTorch implementation of "Meta Pseudo Labels"

PVT

rexnet

Official Pytorch implementation of ReXNet (Rank eXpansion Network) with pretrained models

Self-Supervised-Learning-Overview

Self-Supervised Learning: Reading List with Topics.

TinyYOLOv2Barracuda

Tiny YOLOv2 on Unity Barracuda

Transformer-in-Vision

Some recent Transformer-based CV works

transformers-interpret

Model explainability designed to work exclusively with 🤗 transformers. Explain your transformers model in just 2 lines of code.

TransGAN

[Preprint] "TransGAN: Two Transformers Can Make One Strong GAN", Yifan Jiang, Shiyu Chang, Zhangyang Wang

Ultra-Data-Efficient-GAN-Training

[Preprint] "Ultra-Data-Efficient GAN Training: Drawing A Lottery Ticket First, Then Training It Toughly", Tianlong Chen, Yu Cheng, Zhe Gan, Jingjing Liu, Zhangyang Wang

Un-Mix

Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning

unbiased-teacher

PyTorch code for ICLR 2021 paper Unbiased Teacher for Semi-Supervised Object Detection

Unsupervised-Semantic-Segmentation

Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals.

vissl

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

vit-pytorch

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