XiaLiPKU / EMANet

The code for Expectation-Maximization Attention Networks for Semantic Segmentation (ICCV'2019 Oral)

Home Page:https://xialipku.github.io/publication/expectation-maximization-attention-networks-for-semantic-segmentation/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

How can eval.py generate results of segmentation?

illutheplanet opened this issue · comments

When running eval.py only appears mIoU, what should I do to get the segmentation maps?

When running eval.py only appears mIoU, what should I do to get the segmentation maps?

I would like to add this function further.
For now, you can hack the codes, and save the 'pred' into a png.
Moreover, to visualize the results by eye, you may need colorize the generated pngs.

how to show attention map?

how to show attention map?

Just output the Z is enough.
But for better color and value, you would better normalize the value map.

how to show attention map?

Just output the Z is enough.
But for better color and value, you would better normalize the value map.

how to show attention map?

Just output the Z is enough.
But for better color and value, you would better normalize the value map.

Okay, thank you very much