search

ChenDelong1999 / RemoteCLIP

🛰️ Official repository of paper "RemoteCLIP: A Vision Language Foundation Model for Remote Sensing" (IEEE TGRS)
https://arxiv.org/abs/2306.11029
Apache License 2.0
228 stars 13 forks source link

How to split train/test in linear-prob, knn? #2

Closed chagmgang closed 10 months ago

ChenDelong1999 commented 10 months ago

Hi, sorry for missing this detail in our paper.

In classification experiments of both linear-prob and k-NN, we use a spliting ratio of train:test=8:2.

chagmgang commented 10 months ago

Thank you for reply. Is it splited randomly?

ChenDelong1999 commented 10 months ago

Hi, sorry for missing previous comment.

Many of the classification dataset do not provide official train/val/test split, therefore we have to do this by our own. In our implementation, for each class, we use the first 80% samples (starting from something like 001.jpg, 002.jpg ...) for training, and use the remaining for testing.

chagmgang commented 10 months ago

Thank you reply.