FGVC-PIM

FGVC-PIM copied to clipboard

The url of the pre-trained model is unavailable!

1

hqhQAQ

This is a great job, but I ran on my own dataset and encountered the following errors. Start Training 3 Epoch..0%..10%..20% Start Evaluating 1 Epoch Start Training 2 Epoch Start...

sunlight002

RuntimeError: mat1 and mat2 shapes cannot be multiplied (6144x1456 and 2720x85)

6

When I select efficentnet for training I get the following error, only swin-transformer does not report it Can you help me? Start Training 1 EpochTraceback (most recent call last): File...

smallzhu

Som questions about the paper.

5

 2 of Ls in these equations?  L or lambda?  C or C'? Before or after the fc layer?

KKIverson

hqhQAQ

is heat.py correct?

1

im not sure does heat.py works

lsm0729

About training configuration for NAbirds

1

Excellent work! Can you improve the training configuration for NAbirds? Change ''num_selects'' from [2048, 512, 128, 32] to [256, 128, 64, 32]?

MercuialC

Multiple GPUs Available？

7

It seems the codes only support single GPU trainning. Is it possible to train on multiple GPUs？ thx

KleinXin

How to solve this problem?

4

Hi, bro, your code is very beautiful, but I made the following error when using swin-t to run the code. How can I use the pre training weight downloaded by...

OhJackHu

How to config use_layers for eff or resnet

2

Hi guys, great work! I wanna try eff_b7 or resnet50 as backbone, but seems the code is default to swin.That if simply change backbone to eff_b7 or resnet, the assert...

FRAOTIAC