Deep Learning Book Chinese Translation

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

An open source implementation of CLIP.

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

Automatic colorization using deep neural networks. "Colorful Image Colorization." In ECCV, 2016.

Implementations of NeRF variants based on Taichi + PyTorch

Implementation of Phenaki Video, which uses Mask GIT to produce text guided videos of up to 2 minutes in length, in Pytorch

Code release for SLIP Self-supervision meets Language-Image Pre-training

A Tensorflow implementation of RetinexNet

iBOT 🤖: Image BERT Pre-Training with Online Tokenizer (ICLR 2022)

A PyTorch implementation of MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis

Standardizing weights to accelerate micro-batch training

This is a PyTorch re-implementation of Axial-DeepLab (ECCV 2020 Spotlight)

Network Dissection http://netdissect.csail.mit.edu for quantifying interpretability of deep CNNs.

PyTorch implementation of DeepLabv3

Unofficial implementation with pytorch DistributedDataParallel for "MoCo: Momentum Contrast for Unsupervised Visual Representation Learning"

Official implementation of "PyVision: Agentic Vision with Dynamic Tooling."

Repo for CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning

A PyTorch re-implementation of the paper 'Exploring Simple Siamese Representation Learning'. Reproduced the 67.8% Top1 Acc on ImageNet.

Implementation of the k-means algorithm in PyTorch that works for large datasets

[ECCV 2022] This repository includes the official implementation our paper "In Defense of Image Pre-Training for Spatiotemporal Recognition".

Homework materials for "Probabilistic Models of the Visual Cortex"

compiler assignment testing codes [PKU, Course: Compiler Design, 2019 Spring]

Tool for computing 3D descriptors in videos developed in my paper "A spatio-temporal descriptor based on 3D gradients", A. Kläser, M. Marszalek and C. Schmid, published at BMVC 2008