search

Hlings / AsyFOD

(CVPR2023) The PyTorch implementation of the "AsyFOD: An Asymmetric Adaptation Paradigm for Few-Shot Domain Adaptive Object Detection".
MIT License
33 stars 3 forks source link

val data #10

Closed 906096481 closed 8 months ago

906096481 commented 9 months ago

Hello, when I train my own data set, the target field sample number is only about 10, assuming I use 8 of them for training, how should my validation set fit the data?

Hlings commented 8 months ago

Hi. The target sample should be selected from the defined target train dataset. The target val dataset should remain the same for each variant of the selected few-shot target train dataset.