MaybeShewill-CV / bisenetv2-tensorflow

Unofficial tensorflow implementation of real-time scene image segmentation model "BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation"

Home Page:https://maybeshewill-cv.github.io/bisenetv2-tensorflow/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

about training new custom data set

zjj321 opened this issue · comments

I have trained new data set it worked and successful and all imag is resize 960*540。

but when i try to train smaller dataset: every img is 896 * 544, it is always print error:slice index 262144 of dimension 0 out of bounds。and i changed even smaller image size: 512*320, it print same error。

somewhere should i need to do?

@zjj321 Change the config here

OHEM:
ENABLE: True
SCORE_THRESH: 0.65
MIN_SAMPLE_NUMS: 262144

You may change it into 0.5 * 896 * 544 or 0.25 * 896 * 544

best wishs,thank you so much