剪枝部分：请问如果我的模型结构较为复杂，分支较多那么我如何修改剪枝的代码来遍历模型获取每个weight呢？

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

MIT License

2.2k stars 478 forks source link

剪枝部分：请问如果我的模型结构较为复杂，分支较多那么我如何修改剪枝的代码来遍历模型获取每个weight呢？ #52

Open zhishao opened 3 years ago

zhishao commented 3 years ago

毕竟不是所有模型都是像您代码里提供的nin一样这么简单的网络结构

666DZY666 commented 3 years ago

确实，剪枝通用性有待加强。