请问可以支持rnn网络的压缩吗?比如LSTM或者GRU,谢谢!
NewEricWang opened this issue · comments
NewEricWang commented
请问可以支持rnn网络的压缩吗?比如LSTM或者GRU,谢谢!
dzy commented
量化是op级的,可以试试,有问题可以发出来。
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
NewEricWang opened this issue · comments
量化是op级的,可以试试,有问题可以发出来。