Giters

666DZY666 / micronet

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

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

请教关于剪枝的问题

Kayterancer opened this issue · comments

commented

模型剪枝这块是必须要走 稀疏训练->剪枝->微调 的整个流程吗？
必须要走这个流程的话，稀疏训练和微调时训练的epoch大概是多少？

commented

1、稀疏训练很关键，微调若剪枝率较小则可以不做，但最好做一下，对恢复精度帮助较大；
2、epoch，稀疏训练可以比微调多一些，比如分别为300和100。