mobilevit-pytorch

mobilevit-pytorch copied to clipboard

einops.EinopsError: Error while processing rearrange-reduction pattern "b d (h ph) (w pw) -> b (ph pw) (h w) d".

4

JiangMei0201

@chinhsuanwu , thank you so much for uploading the code. * There are small issues regarding the structure of model that you've designed, I have updated the code accordingly in...

hungryGeek16

Hi @chinhsuanwu, Could you please update your model by adding initialisation code? And apple has released the [weights](https://github.com/apple/ml-cvnets/blob/main/docs/source/en/general/README-model-zoo.md) for MobileViTs, could you also please add option to load pre-trained weights?...

Yiming-M

Can you share the weight file of the model? I want to use it for transfer learning

4

Thank you

tuchuanle159

I test my code using pretrained mobilevit_xs and pretrained HRNet(Deep High-Resolution Representation Learning for Visual Recognition) by my dataset. I checked that mobilevit_xs have less x8 parameters than HRNet and...

HTCho1

If I want to use Mobilevit in Cifar10, how should I set the parameters?

4

If I want to use Mobilevit in Cifar10, how should I set the parameters? Because I changed the input size, but the parameters don't match. For example: --------------------------------------------------------------------------------------------------------------------------------------- EinopsError: Shape...

learningelectric

I don't think mobile just have less parameters.

anthonyweidai

Thanks for sharing your code! The inference speed of mobilevit is 40 ms/img. How to reproduce the speed in Table3?

ZhangLei999

Did you train the model with some datasets like ImageNet-1k?

4

If you have, could you share the result of the experiments? Anyway, thank you for your sharing the clear implementation!

tucan9389

In my test, mobilevit_xs process one image will cost 113ms, which is much larger than the value in the paper.

rnwang04