🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

[ICLR'23 Spotlight] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

🔥🔥🔥🔥 YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

Official repository for "Restormer: Efficient Transformer for High-Resolution Image Restoration". SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.

RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.

🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 1.7M (int8) and 3.3M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size …

yolov5剪枝，支持v2,v3,v4版本的yolov5

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-…

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）

YOLOv5 in DOTA with CSL_label.(Oriented Object Detection)（Rotation Detection）（Rotated BBox）基于YOLOv5的旋转目标检测

This is a tensorflow-based rotation detection benchmark, also called UranusDet.

Compute CNN receptive field size in pytorch in one line

mobilev2-yolov5s剪枝、蒸馏，支持ncnn，tensorRT部署。ultra-light but better performence！

The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.

Implementation of popular deep learning networks with TensorRT network definition APIs

Got 100fps on TX2. Got 500fps on GeForce GTX 1660 Ti. Implement yolov4-tiny-tensorrt layer by layer using TensorRT API. If the project is useful to you, please Star it.

yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝，通道剪枝，知识蒸馏

Official PyTorch implementation of "InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image", ECCV 2020

PyTorch ,ONNX and TensorRT implementation of YOLOv4

PyTorch implementation of YOLOv4

Dataset of the paper "Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS"

Distribution-Aware Coordinate Representation for Human Pose Estimation

Repository for Paper: Cross-Domain Complementary Learning Using Pose for Multi-Person Part Segmentation (TCSVT20)

The Triton Inference Server provides a cloud inferencing solution optimized for NVIDIA GPUs.

This is an official implementation of our CVPR 2020 paper "HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation" (https://arxiv.org/abs/1908.10357)

提供对YOLOv3及Tiny的多种剪枝版本，以适应不同的需求。

A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.

Safety helmet wearing detect dataset, with pretrained model

pytorch to caffe by onnx