Initial version of segmentation reference scripts #820
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
hendrycks
reviewed
Mar 30, 2019
references/segmentation/datasets.py
Outdated
|
|
||
| class SBDD(object): | ||
| def __init__(self, root, image_set='train', transforms=None): | ||
| self.root = root |
There was a problem hiding this comment.
os.path.expanduser(root)
There was a problem hiding this comment.
I'll definitely improve those datasets.
BTW, there has been a SBD dataset that has been recently merged into master, so I'll be inheriting from it instead most probably
Codecov Report
@@ Coverage Diff @@
## master #820 +/- ##
==========================================
+ Coverage 56.61% 57.87% +1.25%
==========================================
Files 38 46 +8
Lines 3432 3696 +264
Branches 540 561 +21
==========================================
+ Hits 1943 2139 +196
- Misses 1372 1431 +59
- Partials 117 126 +9
Continue to review full report at Codecov.
|
Leverage more and more torchvision datasets
Also remove outplanes from ResNet, and add a function for querying intermediate outputs. I won't keep it in the end, because it's very hacky and don't work with tracing
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Outdated suggestions cannot be applied.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.
This is the segmentation counter part of #819
I've trained both FCN and DeepLabV3, and they give results within 3% of the reported numbers.
This will be heavily refactored once detection models are implemented.
In particular, many of the functionalities here will be cleaned up / generalized and moved into torchvision.