Yanbin Liu

Motion-aware tuple selection

2

Hi, I am very interested in the data preprocessing part, cause it's very important to avoid trivial problem. And it seems that **Motion-aware tuple selection** part is not released. Could...

Is the test data for EM correct? ta = np.arange(1, (tW-tw+1)+1) ta = ta / ta.sum() These two lines seem to generate 0 values.

Can you release detailed configuration?

10

Hi Jake, Prototypical networks is really a nice work. I have run this code to reproduce the results in NIPS paper. However, it seems the results have some differences with...

loss1 remains large and loss2 decrease to 0

2

When I fine tune VGG16 with the code provided in stage1, loss1 increases until 0.25 and loss2 decreases to a small value < 1e-5. I use output bits: 64, batch...

Hi mengye, Thanks for sharing the code. In the following line: https://github.com/renmengye/few-shot-ssl-public/blob/master/fewshot/data/mini_imagenet.py#L53 I think the val and test dict is wrong for mini-imagenet.

about pnf training

1

Thanks for providing the code implementation. When training pnf model, is "--model.backbone=resnet18_pnf" needed in scripts/train_pnf.sh?

Hi, It's really a clean and simple implementation. Can you give the referenced paper and experimental results by this implementation? Thanks.

How to download ADNI Control Normal (CN) data

1

Hi, I registered an account for the ADNI database. It seems group name CN stands for "Cognitively Normal (NL/CN)" from ADNI system. AND group name Control stands for "Normal Control"....