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
2.22k stars 478 forks source link

关于resnet的add和inception的concatenation如何量化 #53

Open zhangfeixiang222 opened 4 years ago

zhangfeixiang222 commented 4 years ago

你好,在google 的一篇论文Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference提到:关于add量化时不进行特别的操作,只是在部署时需要将其放缩到同一尺度下进行运算;关于concatenation拼接操作,需要限制拼接模块的输入输出都在同一尺度下。请问关于这两个操作,有什么特别的想法吗?(在代码中好像没有体现)

666DZY666 commented 3 years ago

后续会加入