ml-cvnets

ml-cvnets copied to clipboard

Hi @sacmehta, First I'd like to thank you for your contribution of MobileViTs. But I have the code in this repo very unfriendly for downstream tasks. I cannot find which...

Yiming-M

LayerNorm2d != GroupNorm w/ groups=1

9

Re your MobileVit2, these two norms are not equivalent and it would be misleading to call it LayerNorm2d as the group norm w/ groups=1 is not equivalent. 'LayerNorm2d' is already...

rwightman

Run mobilevit-v2 failed with ANE(iphone 13 pro and ios15.5)

7

Hi, with iphone13pro and ios15.5，i got the error when running mobilevit-v2. Do you have any experience to deal with it? 2022-06-27 15:12:57.196279+0800 CoreMLPerformance[10320:18583922] [espresso] [Espresso::handle_ex_plan] exception=ANECF error: ANECCompile(/var/mobile/Library/Caches/com.apple.aned/tmp/com.example.CoreMLPerformance/824F1B79C0CBD30CBE0EFD39FDD54AB15B3E93F859264B1FE69FDB3F02C8D241/C5992495EF614BA515A970B3EBE95F193A7C62E4F7478D853BED6F250D40E299/) FAILED: err=(...

zshanwei

adam optim ERROR:If capturable=False, state_steps should not be CUDA tensors.

4

Hi, congratulations on your excellent work! I would really appreciate if you could help me through this. So I run ```python PYTHONWARNINGS="ignore" cvnets-train --common.config-file config/classification/imagenet/mobilevit_v2.yaml --common.results-loc mobilevitv2_results/width_1_0_0 --common.override-kwargs scheduler.cosine.max_lr=0.0075 scheduler.cosine.min_lr=0.00075...

yqi19

MobileViT use a larger GPU memory than AlexNet?

1

Is it normal? I noticed that mobilevit have no more than 10 M parameters.

anthonyweidai

Instructions to Run Inference on Mobile Devices

1

Hi, Thank you for the great work. I would request you to share the detailed instructions to run inference and calculate latency on mobile devices (Table. 3 of the paper)....

mmaaz60

How to prepare the custom dataset?

1

 

idazhuang

The accuracy of the two figures does not match

5

Hi，thanks for such a great job，but I have a question, the accuracy of the standard training method of MobileViT-S in (b) and (c) in Figure 9 in the paper seems...

cuicheng01

Recommendations for configuring heads/training on custom datasets?

4

Thanks for developing MobileVit! I'm wondering if there are any specific tips/examples for fine-tuning the pre-trained classification and detection models using mobilevit on custom datasets? I see the n_classes reference...

lessw2020

add the new MobileOne model

1

Thanks apple for open sourcing sota deep learning models to us! I seen that you added recently the brand new mobileViTv2. it could be nice to see also an option...

rotem154154