Giters

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

Poor inference result

umairanis03 opened this issue · comments

commented

Hi @MaybeShewill-CV
Thanks for your amazing work.

I tested your pre-trained model on the images in the repository, it works well. Unfortunately, on other images, it performs poorly.

commented

@umairanis03 What do you mean other images?

commented

@MaybeShewill-CV I mean images, not from CityScapes dataset

commented

@umairanis03 The model was trained with cityscapes dataset so what you mentioned above was quite normal in my opinion:)