CloserLookFewShot

CloserLookFewShot copied to clipboard

Hi. What's the stop_epoch nomber for maml? In `train.py` file, it is initilized 400 for 1-shot and 600 for 5-shot. In that file stop_epoch is initialized as `param.stop_epoch*model.n_task`, for maml....

haditabealhojeh

Could anyone explain why don't use validation for baseline?

1

If we don't use validation and don't calculate accuracy during training, how can we know when to stop and how it performs in the training set, and whether it has...

rainylt

accuracy about miniImagenet protonet ResNet18 train_aug

4

Hello, I have run your code python ./train.py --dataset miniImagenet --method protonet --model ResNet18 --train_aug python ./save_features --dataset miniImagenet --method protonet --model ResNet18 --train_aug python ./test.py --dataset miniImagenet --method protonet...

ChaiXingliang

``` while np.sum(feats[-1]) == 0: feats = np.delete(feats,-1,axis = 0) labels = np.delete(labels,-1,axis = 0) ``` I know these lines are intend to delete the all 0 features. But can...

HatsuneBlake

I checked training accuracy when I used Conv4 backbone. I found that the training accuracies are low and their gaps are big. For example, in 5 way 1 shot task...

hjk92g

datamgr get error

1

When I run the code with the train_aug=True,I got the error: TypeError: __init__() missing 1 required positional argument: 'size' Could you help me solve it?Thanks

yejg2017

GPU memory continue to grow for MAML

1

Hi, Thank you for sharing the code. When running MAML with conv4 backbone, the memory usage accumulates as epoch increases, causing CUDA out of memory. It seems the problem is...

suoql

low GPU utilization rate

3

Hello~ It's a very nice work! I wonder why the GPU utilization is always low when I run the code, therefore the speed is slowed down, is there a way...

zoraup

Random seed not assigned: Trying to replicate the CUB results

1

Thanks for releasing the code. We are trying to replicate your results on CUB dataset for comparison purposes. The write_CUB_filelist.py doesnt seem to have assigned a seed. So the filelist...

samarth-b

Can't reach specified accuracy on CUB dataset ResNet18

1

Following the implementation details in the article, I adopted ProNet to run the Cub dataset on Resnet18, but the accuracy was only 74.72% on 5way5shot. Excuse me, what is the...

DevXiaoYan