Schuture

Prompt-Engineering-Guide

🐙 Guides, papers, lecture, notebooks and resources for prompt engineering

Swin-Transformer

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

stable-diffusion-inspector

read pnginfo in stable diffusion generated images / inspect models

GenesisLung

loss-landscape

Code for visualizing the loss landscape of neural nets

pytorch-image-models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

Transfer-Learning-Library

Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization

pytorch-grad-cam

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

covid-chestxray-dataset

We are building an open database of COVID-19 cases with chest X-ray or CT images.

ViT

Implementing Vi(sion)T(transformer)

medical-data

segmentation_models.pytorch

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

AutoLR

AutoLR: Layer-wise Pruning and Auto-tuning of Learning Rates in Fine-tuning of Deep Networks

coursera-ai-for-medicine-specialization

Programming assignments, labs and quizzes from all courses in the Coursera AI for Medicine Specialization offered by deeplearning.ai

Meta-Weight-Net_Code-Optimization

A new code framework that uses pytorch to implement meta-learning, and takes Meta-Weight-Net as an example.

nnUNet

MONAI

AI Toolkit for Healthcare Imaging

USCL

This repository includes the constructed US-4 dataset and the code for USCL (PyTorch version).

Chinese-Word-Vectors

100+ Chinese Word Vectors 上百种预训练中文词向量

pytorch-meta

A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch

higher

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

meta-weight-net

NeurIPS'19: Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting (Pytorch implementation for noisy labels).

learning-to-reweight-examples

PyTorch Implementation of the paper Learning to Reweight Examples for Robust Deep Learning

DataLoaders_DALI

PyTorch DataLoaders implemented with DALI for accelerating image preprocessing

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

kaggle-Ultrasound_Nerve_Segmentation

kaggle网站的一次竞赛，内容是关于超声波图像分割（神经细胞）。代码是我参加竞赛的部分源码，效果是该竞赛排行版的top10%。

Tricks-of-Semi-supervisedDeepLeanring-Pytorch

PseudoLabel 2013, VAT, PI model, Tempens, MeanTeacher, ICT, MixMatch, FixMatch

mean-teacher

A state-of-the-art semi-supervised method for image recognition

temporal-ensembling

PyTorch implementation of Temporal Ensembling for Semi-Supervised Learning

PyContrast

PyTorch implementation of Contrastive Learning methods