model compression and optimization for deployment for Pytorch, including knowledge distillation, quantization and pruning.(知识蒸馏,量化,剪枝)
MIT License
model compression and optimization for deployment for Pytorch, including knowledge distillation, quantization and pruning.(知识蒸馏,量化,剪枝)
Pruning Method | Code location | Docs | Remark |
---|---|---|---|
01开山之作:Learning Efficient Convolutional Networks Through Network Slimming (ICCV2017) | code: pruning/01NetworkSlimming code reference: link1 link2 | docs | placeholder |
02【ICCV2017】ThiNet | code: 1pruning/02ThiNet code reference: https://github.com/SSriven/ThiNet | docs | 1 |
03【CVPR2020】HRank | code: 1pruning/03HRank code reference: link | docs | placeholder |
Coming... | 1 | 1 | 1 |
docs: https://www.yuque.com/huangzhongqing/pytorch/iar4s1
code: pruning/01NetworkSlimming
code reference:
- https://github.com/foolwood/pytorch-slimming
● support for Vgg- https://github.com/Eric-mingjie/network-slimming
● We also add support for ResNet and DenseNet.
量化 Method | Code location | Docs | Remark |
---|---|---|---|
Coming... | 1 | 1 | 1 |
KD Method | Code location | Docs | Remark |
---|---|---|---|
01开山之作: Distilling the knowledge in a neural network(NIPS2014)ndom | code: 3distillation/01Distilling the knowledge in a neural networkcode reference: https://github.com/Eli-yu-first/Artificial_Intelligence | https://www.yuque.com/huangzhongqing/lightweight/lno6i7 | 1 |
02 Channel-wise Knowledge Distillation for Dense Prediction(ICCV2021) | code: 3distillation/02SemSeg-distill code reference: https://github.com/irfanICMLL/TorchDistiller/tree/main/SemSeg-distill | https://www.yuque.com/huangzhongqing/lightweight/dourdf2ogh9y1cx9#VHZBv | 1 |
Coming... | 1 | 1 | 1 |
docs: https://www.yuque.com/huangzhongqing/lightweight/lno6i7
code: 3distillation/01Distilling the knowledge in a neural network
code reference: https://github.com/Eli-yu-first/Artificial_Intelligence
docs: https://www.yuque.com/huangzhongqing/lightweight/dourdf2ogh9y1cx9#VHZBv
code: 3distillation/02SemSeg-distill
code reference: https://github.com/irfanICMLL/TorchDistiller/tree/main/SemSeg-distill
video:
NAS Method | Code location | Docs | Remark |
---|---|---|---|
01 DARTS(ICLR'2019)【Differentiable Neural Architecture Search 可微分结构】—年轻人的第一个NAS模型 | code: 4NAS/01DARTS(ICLR2019)/pt.darts code reference: https://github.com/khanrc/pt.darts | hthttps://www.yuque.com/huangzhongqing/lightweight/esyutcdebpmowgi3 | video:【论文解读】Darts可微分神经网络架构搜索算法:https://www.bilibili.com/video/BV1Mm4y1R7Cw/?vd_source=617461d43c4542e4c5a3ed54434a0e55 |
Coming... | 1 | 1 | 1 |
doc:https://www.yuque.com/huangzhongqing/lightweight/esyutcdebpmowgi3
code: 4NAS/01DARTS(ICLR2019)/pt.darts code reference::https://github.com/khanrc/pt.darts video:【论文解读】Darts可微分神经网络架构搜索算法:https://www.bilibili.com/video/BV1Mm4y1R7Cw/?vd_source=617461d43c4542e4c5a3ed54434a0e55
Copyright (c) 双愚. All rights reserved.
Licensed under the MIT License.
微信公众号:【双愚】(huang_chongqing) 聊科研技术,谈人生思考,欢迎关注~
往期推荐: