Wu's repositories
Ternary-spiking-neural-network
Ternary spiking neural network
awesome-quantization-and-fixed-point-training
Neural Network Quantization & Low-Bit Fixed Point Training For Hardware-Friendly Algorithm Design
000
caffe-twns
Implementation of Ternary Weight Networks In Caffe
Language:C++000
model-compression
model compression based on pytorch (1、quantization: 16/8/4/2 bits(dorefa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、ternary/binary value(twn/bnn/xnor-net)；2、 pruning: normal、regular and group convolutional channel pruning；3、 group convolution structure；4、batch-normalization folding for quantization)
Language:Python000