-
Notifications
You must be signed in to change notification settings - Fork 323
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Faster RCNN Model + Pascal VOC DataModule #157
Conversation
Hello @teddykoker! Thanks for updating this PR. There are currently no PEP 8 issues detected in this Pull Request. Cheers! 🍻 Comment last updated at 2020-08-22 19:41:49 UTC |
Codecov Report
@@ Coverage Diff @@
## master #157 +/- ##
==========================================
+ Coverage 90.72% 91.82% +1.10%
==========================================
Files 86 86
Lines 4052 4049 -3
==========================================
+ Hits 3676 3718 +42
+ Misses 376 331 -45
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
Co-authored-by: Jirka Borovec <[email protected]>
@Borda didn't add test for cli, but added test training with |
|
||
model = FasterRCNN() | ||
|
||
train_dl = DataLoader(DummyDetectionDataset(), collate_fn=_collate_fn) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We have a dummy dataset already. why is this one different?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Instead of a tensor label it returns a dict with values {"boxes": FloatTensor[N, 4], "labels": Int64Tensor[N]}
as per the standard in pytorch for detection models. Should this be a choice in the existing dummy dataset?
Also |
@teddykoker mind fixing the failing tests here? |
@williamFalcon it looks like the minimal version tests are failing because I am using a feature of torchvision introduced in 0.7.0 (our requirements state torchvision>=0.5). Our options are:
Let me know what you think. |
for tests we can make torchvision 0.7 but we need to get rid of the deps in the requirements.txt |
|
Before submitting
What does this PR do?
DataModule
LightningModule
PR review
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 🙃