poolformer

poolformer copied to clipboard

Can I say PoolFormer is just a non-trainable MLP-like module?

9

Hi! Thanks for sharing the great work! I have some questions about PoolFormer. If I explain PoolFormer like the following attachments, can I say PoolFormer is just a non-trainable MLP-like...

072jiajia

Aboutu the results graph

3

Hello, can you tell me hows to get the results graph？

paidaxing485

Hi, I observed GPU memory leakage after every epoch, I couldn't find the root cause but emptying the cache fixed it, might be helpful.

luis-guerraf

Invitation of making PR for OpenMMLab / MMSegmentation.

5

Hi, first congrats for acceptance of CVPR'2022. This work deserves because it is very great. I am a member of OpenMMLab and mainly work for developing MMSegmentation. I think if...

MengzhangLI

On the use of Apex AMP and hybrid stages

6

Is there a specific reason why you used Apex AMP instead of the native AMP provided by PyTorch? Have you tried native AMP? I tried to train `poolformer_s12` and `poolformer_s24`...

DonkeyShot21

Have you ever tested the network on Cifar-10 dataset? What about the results?

2

LouiValley

Recommendations for training poolFormer on custom dataset?

1

Hello, Thank you for this great contribution. Can you please clarify recommendations for training on a custom dataset?

loucif01

About subtract in pooling

16

Hi, thank you for publishing such a nice paper. I just have one question. I do not understand the subtraction of the input in eqn.4. Is it necessary? What will...

Dong-Huo

Why not using DW conv

5

Hi, thanks for the paper. While your paper does again show that any mixing in spatial domain could work in CV, from practical point of view there is a large...

bonlime

About MLN（Modified Layer Normalization）

2

This paper provides new perspectives about Transformer block, but I have some questions about one of the details. As far as I know, the LayerNorm officially provided by Pytorch implements...

youngtboy