mobilenetv3 代码实现似乎和论文有出入

d-li14 / mobilenetv3.pytorch

74.3% MobileNetV3-Large and 67.2% MobileNetV3-Small model on ImageNet

https://arxiv.org/abs/1905.02244

MIT License

515 stars 125 forks source link

Open nlp-tokio opened 3 years ago

nlp-tokio commented 3 years ago

Mobilenetv3模块实现部分好像少了一个pointwise convolution, 见 https://github.com/d-li14/mobilenetv3.pytorch/blob/master/mobilenetv3.py#:~:text=and%20inp%20%3D%3D%20oup-,if%20inp%20%3D%3D%20hidden_dim%3A,),-else%3A 在line94-104 这部分只适用于第一个模块，代码可以继续简化

AlphaNext commented 1 year ago