Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
JSeg is a Semantic segmentation toolbox based on MMSegmentation and Jittor
Image Compression using CNN based Autoencoders
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
ncnn is a high-performance neural network inference framework optimized for the mobile platform
⬛ Windows Terminal + 🐧 WSL2 + zsh + Powerlevel10K