sudarshan babu

In the orignal MAML paper I think they use 64 filters not 32 for classification tasks

Yeah, thanks for the correction, I ran this experiment "mini-imagenet_1_2_0.01_48_5_0" and ia m getting a test accuracy of 50.30, is this correct because in the MAML paper they get only...

Hey thanks for getting back, I went through the code base--its a super useful contribution, thank the whole team for this ! I think a class wrapping the `gradient_update_parameters` which...

Hey, so we have an implementation of metacurvature using pytorch-meta and these are the results on miniImageNet: 52 % for 1-shot and 63.8 % for 5-shot. The meta-curvature paper implements...

Sure I ll clean up the code, give me a couple of weeks

Using the below structure in the config file would resolve this optimizer: name:sgd

In the original MAML paper, they dont track the running mean and variance. They only use the current mean and variance for their normalization. Although in MAML++ they do track...

Hi, Thank you for your contribution. I tried training URT using the pre-trained weights of SUR as instructed in your repo's readme. However I got results that were different from...

I used the resnet features released in the repo and got the same results as in the paper for all the datasets except for traffic sign and MNIST. Thanks for...

Yeah, I am aware of the bug, thanks for letting me know though, but I am still using the old buggy dataloader just to see if I can get the...