micronet
Publicmicronet, 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
batch-normalization-fusebnnconvolutional-networksdorefagroup-convolutioninteger-arithmetic-onlymodel-compressionnetwork-in-networknetwork-slimmingneuromorphic-computing
Erstellungszeit:2019-12-04T23:56:29
Aktualisierungszeit:2025-03-26T22:06:17
2.3K
Stars
0
Stars Increase