CloserLookFewShot
CloserLookFewShot copied to clipboard
wyharveychen
source code to ICLR'19, 'A Closer Look at Few-shot Classification'
when I run `python ./train.py --dataset miniImagenet --model Conv4 --method baseline --train_aug`, it reports error below, how could I fix it? 
In the right most image of Figure 5, the title of the figure is "CUB→mini-ImageNet", while the text (in the last paragraph of Page 9) describes the figure for "ImageNet...
config.py assumes the path ```/work/newriver/wyharveychen/CloserLookFewShot/``` exists, but this is not true in general. Using the current working directory makes more sense as a default.
Very nice job!!! I tried to use resnet (10, 12, 18) as a backbone of my model, but it didn't improve performance as we expected. In contrast, In our experiments,...
in the case of image classification, we have a training set, with x inputs, and the loss is computed by whether our neural network was correctly able to predict the...
Thank's for your work! I have a question that is it classifier at test stage is new? I can't find classifier loading trained weights in code.
Hi everyone, I have tried using a batch size of 64 for experiments of MAML on CUBS dataset. However, I am facing an error in this regard. I have attached...
after a lot of attemptions,i finally found a robust parameters to re-implement the refined cosine distance method: 1.we rewrite the cosine distance code. 2. we set scale factor s =...
Thank you for your impressive work, and codes too! Given using a ResNet18 backbone leads to a ~5% raise to accuracy, as is shown in your paper, I tried to...
Hi Harvey, In your paper it was stated that > "For each class, we pick k labeled instances as our support set and **16** instances for the query set for...
Metadata
Owner
Metadata
source code to ICLR'19, 'A Closer Look at Few-shot Classification'