convnext

OpenMMLab Detection Toolbox and Benchmark

OpenMMLab Pre-training Toolbox and Benchmark

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

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

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

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

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

forex trading with reinforcement learning

ConvNeXt conversion code for PT to TF along with evaluation code on ImageNet-1k val.

MedNeXt is a fully ConvNeXt architecture for 3D medical image segmentation.

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

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

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

Tensorflow implementations of ConvNeXt V1 + V2 models w/ weights, including conversion and evaluation scripts.

An (admittedly amature) attempt to combine the strength of CNNs for sequence prediction though PACING - Patched bAsed ConvolutIoNal Generators

Generating Adversarial examples for ConvNeXt

tf-keras re-implementation of ConvNeXt (https://arxiv.org/abs/2201.03545) from Facebook Research.

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

Paddle YOLOX, 51.8mAP on COCO val by YOLOX-x, 44.6mAP on YOLOX-s ConvNeXt