CloserLookFewShot

CloserLookFewShot copied to clipboard

Should not use ImageNet mean and std?

1

https://github.com/wyharveychen/CloserLookFewShot/blob/b3b5b8bf7cff700dae361133e0980df4f4ebf824/data/datamgr.py#L13 I am not sure how much performance change will happen, but when we are not using ImageNet pretrained model, I guess we should not normalize with the mean and...

apple2373

questions about cosine distance in the code

1

hi, thank your for the nice work first. i have some problems in the code that confuses me. To compute the cosine distance, the implementation is the following x_norm =...

icoz69

write_omniglot_filelist

1

for dataset in dataset_list: with open(datasetmap[dataset] + ".txt", "r") as lines: for i, line in enumerate(lines): label = line.replace('\n','') folderlist.append(label) filelists[dataset][label] = [ join(data_path,label, f) for f in listdir( join(data_path,...

madiltalay

Hello, I did not find the address to download the pretrain model. "Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation" and "https://github.com/quantacode/Contrastive-Finetuning" both refer to this article. The pre-trained model can...

booker-max