pmf_cvpr22

pmf_cvpr22 copied to clipboard

HI there, Encounted error: https://github.com/pytorch/vision/issues/5927 while testing cross-domain fine-tuning. Fix approach: under CropDisease_few_shot.py (and other datasets) ``` def parse_transform(..): # replace Scale with Resize: elif transform_type=='Resize': return method([int(self.image_size*1.15), int(self.image_size*1.15)]) ......

W-XuWX

Hi there, I encountered an error when running test_bscdfsl.py on `--cdfsl_domains CropDisease ChestX`. While scanning through to find the best learning rate for the fine-tuning dataset, the loop works for...

W-XuWX

The effect of fine-tuning without domain gap

1

Your outstanding performance has surprised us, and I have tried to apply the method in my work. In a few shot classification experiment on a single dataset MiniImageNet (without cross-domain...

rachel-lyq

What hyperparameters should be changed for effective training on Meta-Dataset subset?

2

Hi, I have a pre-trained backbone network (self-supervised) which I would want to deploy for few-shot classification. However, I can’t use your meta training pipeline because the Meta-Dataset consist of...

ajkailash

Several code and traning questions

6

Hi, thanks for awesome and useful paper. I am trying to train other backbone on 10 meta-dataset My questions are: 1. What about batch size? For vit it is ok...

cszer

Setting for MiniImagenet

1

Hi, I would like to express my appreciation for the excellent repository and the well-organized code. However, I have a question regarding the number of episodes specified in the paper...

hamidkazemi22

Open source license

1

I hope this message finds you well! I recently stumbled upon your amazing open source repository, and I must say, I'm truly impressed with your work. I wanted to reach...

Goldit

Purpose of learnable scale and bias in the cosine classifier

1

Hi! Thank you for making the code and models public, the paper is very eye-opening! I was trying to do a reimplementation of your code within our framework and came...

leosampaio

cross-domain sample CDFSL, the following error occurred.

2

Thank you very much for the contributed code repository. When testing on the cross-domain sample CDFSL, the following error occurred. When testing 600 samples, an error will occur, "metric_logger has...

githubdds

the mode in single_step function

2

Thank you for your share! Can I use ProtoNet_Finetune during meta-train step? If so, how to modify the forward function of ProtoNet_Finetune? I try to run the meta-train step with...

cosoldier