search

kjunelee / MetaOptNet

Meta-Learning with Differentiable Convex Optimization (CVPR 2019 Oral)
Apache License 2.0
529 stars 97 forks source link

The number of val-shot choice. #17

Closed AceChuse closed 5 years ago

AceChuse commented 5 years ago

Some as before. Thanks for your code! I think it is really great work. The test epoch is chosen based on the accuracy on val set, right? I want to ask. If we need to use the 5-shot val to choose the model for the 5-shot test and the 1-shot val to choose the model for the 1-shot test. Or just use the 5-shot val to choose the model for both the 5-shot and 1-shot test.

I want to ask this because when I use 5-shot val to choose model for 1-shot test, I all-way cannot get the accuracy in your paper.

kjunelee commented 5 years ago

Just use the 5-shot val to choose the model for both the 5-shot and 1-shot test. => This is the option I chose.

In practice, meta-training has some degree of variance in the final performance due to factors like different random seeds in different versions of packages. For example, I used Python 2 for the submission, but when I tried Python 3 after the submission the performance slightly went down.

AceChuse commented 5 years ago

I do use python3. Thank for your help!