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

A treasure chest for visual classification and recognition powered by PaddlePaddle

Unofficial PyTorch implementation of "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence"

face recognition training project(pytorch)

Optimize RandAugment with differentiable operations

Applying RandAugment on PointNet++

FastClassification is a tensorflow toolbox for class classification. It provides a training module with various backbones and training tricks towards state-of-the-art class classification.

[Re-implementation] FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

Unofficial PyTorch Reimplementation of UniformAugment.

A simple template for classifying things

Full experimentation notebook for my Keras Example on using RandAugment.

Collection of deep learning modules

RandAugment with Keypoints Annotation Support.

EfficientNet with Robust Training: MICCAI Skin Cancer Analysis Challenge

This project includes multiple models, loss functions, optimizers and image augmentations for image classification task

SSL Methods integrated into the official implementation of the ECCV"22 Paper "CoMER: Modeling Coverage for Transformer-based Handwritten Mathematical Expression Recognition"

MobileNetV3 implementation using PyTorch

Prediction of MNIST data with only 100 labels

Image Classification Using Swin Transformer With RandAugment, CutMix, and MixUp

This repository contains the code and the report for the coursework of INFR11031 Advanced Vision, a postgraduate course offered at The University of Edinburgh. The task was to train on limited and improve the accuracy of the ResNet-50 classifier on a small subset of the ImageNet dataset containing 50K training images and 50K test images. Achieve…