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"

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

请问怎么使用使用 v2 large方式训练

dgliu123 opened this issue 4 years ago · comments

dgliu123 commented 4 years ago

请问怎么使用使用 v2 large方式训练

MaybeShewill-CV commented 4 years ago

@dgliu123 这个目前还是得通过改代码的方式＝＝！

dgliu123 commented 4 years ago

我不理解 v2 large方式是个什么方式

MaybeShewill-CV commented 4 years ago

@dgliu123 网络结构和现在略有不同增加了广度和深度具体你可以看下论文里的描述:)