tensorflow模型裁剪资料收集

model-optimization官方:

https://github.com/tensorflow/model-optimization
https://github.com/tensorflow/model-optimization/blob/master/tensorflow_model_optimization/g3doc/guide/pruning/pruning_with_keras.ipynb
解读和使用:https://zhuanlan.zhihu.com/p/162776131

tensorflow.contrib.model_pruning.python剪枝模块简单使用:

from tensorflow.contrib.model_pruning.python import pruning
from tensorflow.contrib.model_pruning.python.layers import layers

https://blog.youkuaiyun.com/xue_csdn/article/details/105220985

Channel Pruning for Accelerating Very Deep Neural Networks

论文:https://arxiv.org/pdf/1707.06168.pdf
github:https://github.com/yihui-he/channel-pruning
https://github.com/Tencent/PocketFlow
解读:https://zhuanlan.zhihu.com/p/87791509
PocketFlow使用文档:https://pocketflow.github.io/cp_learner/

Discrimination-aware Channel Pruning for Deep Neural Networks

论文:https://arxiv.org/pdf/1810.11809.pdf
github:https://github.com/Tencent/PocketFlow
解读:https://blog.youkuaiyun.com/nature553863/article/details/83822895
PocketFlow使用文档:https://pocketflow.github.io/dcp_learner/

Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers

论文:https://arxiv.org/abs/1802.00124
github:https://github.com/bobye/batchnorm_prune
解读:https://blog.youkuaiyun.com/hw5226349/article/details/84779325

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值