【第38篇】MixConv:混合深度卷积核

摘要

论文链接:https://arxiv.org/abs/1907.09595

官方代码:https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet/mixnet
pytorch代码:https://github.com/romulus0914/MixNet-Pytorch

深度卷积在现代高效 ConvNets 中变得越来越流行,但它

猜你喜欢

转载自blog.csdn.net/hhhhhhhhhhwwwwwwwwww/article/details/124779609