search

xinzheli1217 / learning-to-self-train

Learning to Self-Train for Semi-Supervised Few-Shot
MIT License
93 stars 11 forks source link

Clarification regarding total number of meta-train,meta-test tasks and shot number. #7

Open JKDomoguen opened 4 years ago

JKDomoguen commented 4 years ago

Hello, first great work!

I am trying to re-implement this paper in Pytorch! And I know this codebase is based on the official meta-transfer learning implementation (https://github.com/yaoyao-liu/meta-transfer-learning) since it's basically the same group of authors.

I hope to ask for some few clarifications.

The total number of tasks during meta-training is equal to the number of meta-train iterations right? Which is 15000? Also the total number of tasks during meta-testing AND meta-validation is still 600? Both the same as in the MTL implementation?

Moreover, the number of shots of the support and query during meta-train in one-shot setting is 1 (or 5 for 5-shot) and 15 respectively right? While during meta-validation and meta-testing.,the number of instances per class (shot) for the support set and query is uniformly 1 (or 5 for 5-shot)?

Thank you for your time.

Hugo101 commented 2 years ago

Although it has been a long time, I also want to backup this comment. That would be geat to compare if there is pytorch version of the implementation