BBuf / model-compression

model compression based on pytorch (1、quantization: 8/4/2bits(dorefa)、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 binary value of feature(A))
170Updated 4 years ago

Alternatives and similar repositories for model-compression:

Users that are interested in model-compression are comparing it to the libraries listed below