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

OpenMMLab Detection Toolbox and Benchmark

OpenMMLab Pre-training Toolbox and Benchmark

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

[MICCAI 2023] MedNeXt is a fully ConvNeXt architecture for 3D medical image segmentation.

PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision Transformer，DEiT，Swin Transformer，CvT，T2T-ViT，MLP-Mixer，XCiT，ConvNeXt，PVTv2 等基础视觉算法

A lightweight end-to-end text-to-speech model

1st place solution of RSNA Screening Mammography Breast Cancer Detection competition on Kaggle: https://www.kaggle.com/competitions/rsna-breast-cancer-detection

A PyTorch-based Python library with UNet architecture and multiple backbones for Image Semantic Segmentation.

👁 2022年数字中国创新大赛 (DCIC 2022) 卫星应用赛题——海上船舶智能检测第三名解决方案

YOLOv5-ODConvNeXt is an improved version of YOLOv5 for ship detection on drone-captured images.

[NeurIPS 2023] Code for the paper "Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models"

provide some new architecture, channel pruning and quantization methods for yolov5

超清遥感图像的语义分割，内附类别不平衡损失为何失效

forex trading with reinforcement learning

😉 Face Recognition using Convnext model Flask

🥈12th place solution on G2Net Detecting Continuous Gravitational Waves🥈

Train torchvision's MaskRCNN model using the ConvNeXt architecture as the backbone network.

PyTorch implementation of "Nextformer: A ConvNeXt Augmented Conformer For End-To-End Speech Recognition"

Export pytorch model to ONNX and convert ONNX from float32 to float 16