Closed tensorboy closed 6 years ago
The Flatten function in here https://github.com/TreB1eN/InsightFace_Pytorch/blob/master/model.py:
https://github.com/TreB1eN/InsightFace_Pytorch/blob/master/model.py
class Flatten(Module): def forward(self, input): return input.view(input.size(0), -1)
Will not guarantee the output of this layer has 512 channels which used by:
self.linear = Linear(512, embedding_size, bias=False)
in the definition of MobileFaceNet: https://github.com/TreB1eN/InsightFace_Pytorch/blob/master/model.py#L209
Really appreciate your work!
It's my mistake. :)
The Flatten function in here
https://github.com/TreB1eN/InsightFace_Pytorch/blob/master/model.py
:Will not guarantee the output of this layer has 512 channels which used by:
in the definition of MobileFaceNet: https://github.com/TreB1eN/InsightFace_Pytorch/blob/master/model.py#L209
Really appreciate your work!