search

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

关于 移动端部署 量化模型 #39

Open NewCoderQ opened 4 years ago

NewCoderQ commented 4 years ago

作者您好，请问下您那边最近有做 移动端DL框架(MNN, NCNN, TNN)来部署量化后的模型的实验吗？

gogo03 commented 3 years ago

楼上的，加一下V或邮件: 635196543@qq.com 多沟通，我刚好也在搞这一块。

666DZY666 commented 3 years ago

后续会加入。