Semantic segmentation model #259
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
This pull request is now in conflict... :( |
|
This pull request is now in conflict... :( |
|
This pull request is now in conflict... :( |
|
This pull request is now in conflict... :( |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Model for semantic segmentation task that uses Unet architecture and Kitti datamodule by default.
I've added simple tests for Unet, Kitti DM and SemSegment model + updated docs.
Three things I was unsure of:
To use Kitti dataset you have to manually download it and provide the local directory to the data module - how can I add checks or tests to ensure that someone has downloaded the kitti dataset?
Ideally the SemSegment model should be generalizable - this specific example uses the UNet architecture but you should be able to override this with your own architecture. Any suggestions or examples for how to add this flexibility to the model?
Where should these models be housed? I've put both UNet and SemSegment under Vision since this seemed the most general. I've implemented UNet as just an architecture to plug into other models like SemSegment. Let me know if you think they should be moved!
Also, I wasn't able to train the model on Kitti because of issues with uploading the data to a cluster. I'm thinking I'll train on PascalVOCSegmentation from torchvision instead :)