Python sample codes for robotics algorithms.

Demonstrate all the questions on LeetCode in the form of animation.（用动画的形式呈现解LeetCode题目的思路）

Code and exercises from Problem and Solving with Algorithms and Data Structures

An unofficial styleguide and best practices summary for PyTorch

Applied Multivariate Statistical Analysis | PKU 2019 Fall

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Pytorch implementation of convolutional neural network visualization techniques

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

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

《Pytorch模型训练实用教程》中配套代码

Official DeiT repository

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

[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.

This repository contains some of the latest data augmentation techniques and optimizers for image classification using pytorch and the CIFAR10 dataset

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

An efficient implicit semantic augmentation method, complementary to existing non-semantic techniques.

source code to ICLR'19, 'A Closer Look at Few-shot Classification'

Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning, in ICCV 2021

Teaches a student network from the knowledge obtained via training of a larger teacher network

PyTorch implementation of "Distilling the Knowledge in a Neural Network" for model compression

Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019

Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)

Multi-Scale Dense Networks for Resource Efficient Image Classification （ICLR 2018 Oral）

A scientific and useful toolbox, which contains practical and effective long-tail related tricks with extensive experimental results

This is the PyTorch implementation of our paper "Cross-X learning for Fine-Grained Visual Categorization"

[ECCV'20 Oral] MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution

[ICLR 2021 Spotlight] Code release for "Long-tailed Recognition by Routing Diverse Distribution-Aware Experts."