Revision models.vision.unet, models.vision.segmentation

[lijm1358]

What does this PR do?

Related to #839

• pl_bolts.models.vision.segmentation.cli_main
• pl_bolts.models.vision.segmentation.SemSegment
• pl_bolts.models.vision.unet.DoubleConv
• pl_bolts.models.vision.unet.Down
• pl_bolts.models.vision.unet.UNet
• pl_bolts.models.vision.unet.Up

• update docstring, typing hints
• set bias=False of Conv2d in DoubleConv before batch normalization
• add test for unet components

Before submitting

• Was this discussed/approved via a Github issue? (no need for typos and docs improvements)
• Did you read the contributor guideline, Pull Request section?
• Did you make sure your PR does only one thing, instead of bundling different changes together?
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests? [not needed for typos/docs]
• Did you verify new and existing tests pass locally with your changes?
• If you made a notable change (that affects users), did you update the CHANGELOG?

PR review

• Is this pull request ready for review? (if not, please submit in draft mode)

Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.

Did you have fun?

Make sure you had fun coding 🙂

[otaj]

Hi @lijm1358, it looks very good, thank you! I have left one question in the comment, plus I have another question - where is the number 250 as ignore_index for cross_entropy coming from? I assume it's from KITTI and if that's true, then it would be nice to have it also as an argument for the SemSegment class

[lijm1358]

Hi @lijm1358, it looks very good, thank you! I have left one question in the comment, plus I have another question - where is the number 250 as ignore_index for cross_entropy coming from? I assume it's from KITTI and if that's true, then it would be nice to have it also as an argument for the SemSegment class

Thank you for review, @otaj ! Yes, it's from KITTI datset. The labels useless for training are set to 250 in datasets/kitti_dataset.py. I'll add ignore_index as an argument for the SemSegment.