pytorch-mobilenet-v2

pytorch-mobilenet-v2 copied to clipboard

Quick question regarding inverted residual block. if expand_ratio == 1: self.conv = nn.Sequential( # dw nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False), nn.BatchNorm2d(hidden_dim), nn.ReLU6(inplace=True), # pw-linear nn.Conv2d(hidden_dim, oup, 1, 1,...

abeyang00

Hi. How did you compute the FLOPs for your model? I appreciate it if you share your code.

aryanasadianuoit

Hello! Thanks for the code! I am trying to transfer the Mobile Net to my own dateset which contain the image and saliency data, but when I concat them ,there...

stillbetter

the problem with RMSprop

1

something seems wrong with the loss of RMSprop. Any advice?

FatherOfHam

Hi Thank you for sharing the pre-trained model. I wanted to know which dataset you have used for training the model?

Elahe96

how many warmup epochs did you use? i use the same parameters as described in README.md, but i can only get 71.35%.

wangdongxuking61

libohit

Fix a couple of typos in README example

toby5box

Hi, I wonder how the input_size are used? the only place I can see is check the input size is 32*k.

yitang

zhouxinyu5080