Batchsize setting when evaluating the network

jeya-maria-jose / UNeXt-pytorch

Official Pytorch Code base for "UNeXt: MLP-based Rapid Medical Image Segmentation Network", MICCAI 2022

https://jeya-maria-jose.github.io/UNext-web/

MIT License

459 stars 76 forks source link

Batchsize setting when evaluating the network #33

Open wjzhang-ty opened 1 year ago

wjzhang-ty commented 1 year ago

When I evaluate the network on the test set, modifying the batchsize will affect the evaluation score. Why does batchsize affect the evaluation score? Should batchsize=1 be fixed when evaluating functions?