Zhou Junyang's Projects
https://github.com/MVIG-SJTU/AlphaPose
A curated list of resources dedicated to optical flow algorithms. Feel free to make PRs to contribute.
An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites
Extract training data set suitable for YOLO darknet from COCO database
Convolutional Neural Networks
https://github.com/AlexeyAB/darknet
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression (AAAI 2020)
建模nCov传播情况
https://github.com/HuAndrew/Human-Pose-Estimation-Papers
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
YOLO V2 & V3 , YOLO Combined with RCNN and MaskRCNN
ncnn is a high-performance neural network inference framework optimized for the mobile platform
OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.
PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)
Code for the paper "Pose2Seg: Detection Free Human Instance Segmentation" @ CVPR2019.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Implementation of "SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks"
:zap: Yolo universal target detection model combined with EfficientNet-lite, the calculation amount is only 230Mflops(0.23Bflops), and the model size is 1.3MB