slimming专题

模型压缩:Networks Slimming-Learning Efficient Convolutional Networks through Network Slimming

Network Slimming-Learning Efficient Convolutional Networks through Network Slimming(Paper) 2017年ICCV的一篇paper,思路清晰,骨骼清奇~~ 创新点: 1. 利用batch normalization中的缩放因子γ 作为重要性因子,即γ越小,所对应的channel不太重要,就可以裁剪(prun

【网络裁剪】——Learning Efficient Convolutional Networks through Network Slimming

转载自:https://blog.csdn.net/h__ang/article/details/89376079 亮点:ICCV 2017 论文链接:https://arxiv.org/abs/1708.06519 官方代码(Torch实现):https://github.com/liuzhuang13/slimming 第三方代码(PyTorch实现):https://github.c