kuan-wang / pytorch-mobilenet-v3 Goto Github PK

I'm trying to train mobilenetV3 on DGX 1 using imagenet 2012 dataset but I found it's quite hard to reach to the reported accuracy.

I just got Acc-1 : 70.xx %

Humm.... can I ask you to send me or upload your mobilenetV3-large model on google drive/dropbox?

Thank you!

transforms.Resize(int(input_size/0.875) used in Test phase.
Why use it instead of transforms.RandomResizedCrop() used in Train phase?
We should be consistent in Train and Test phase.

the output channel is mismatch with the output size ,maybe it should be 112.

RT. cannot open this file as a .tar file

the paper mentioned training with dropout. How would you train with dropout with this model?

请问一下，关于mobilenetV3-large 1.00的预训练模型能提供一下吗？

I implemented v3 and tested with/without the modified last stage settings. Although paper claims that this modification doesn't affect accuracy, I find out accuracy actually drops (i.e. 73.45->71.84). May I know about your opinion on that? Thank you!

Would you please provide the hyperparameters used for training of the models? Thanks

mobilenet_v3 small last channel is 1024 instead of 1280 from the paper，is there any evidence that 1280 brings better results?

Where in your code you have used Depthwise Conv? I did not find any depthwise conv.

Could you please publish the train and inference code on ImageNet?

in the init, already defined AdaptiveAvgPool2d in the feature sequence. but in the forward method, there is another mean function. I'm a little confused... 😂😂

Hi, could you share your training setting for Large or Small models?

Thanks!

In original paper paper ,There is no activation function after avg_Pool　in fig5, but your code is added. Does this have any effect?