uyzhang

yolov5_prune

YOLOv5 pruning on COCO Dataset

JCLIP

JSeg

JSeg is a Semantic segmentation toolbox based on MMSegmentation and Jittor

XduTicketSystem

西电软院程序设计实训_自动售票系统

Awesome-Vision-Attentions

Summary of related papers on visual attention. Related code will be released based on Jittor gradually.

uyzhang

cubvh

CUDA Mesh BVH tools.

jittor

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

JDiffusion

JDiffusion is a diffusion model library for generating images or videos based on Diffusers and Jittor.

jtorch

lossy-image-compression

Image Compression using CNN based Autoencoders

micronet

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-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape

mmsegmentation

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

mvpnet

Implementation of the paper "Multi-view PointNet for 3D Scene Understanding"

ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

terminal-config

⬛ Windows Terminal + 🐧 WSL2 + zsh + Powerlevel10K