-
Notifications
You must be signed in to change notification settings - Fork 211
timm integration #196
timm integration #196
Conversation
Codecov Report
@@ Coverage Diff @@
## master #196 +/- ##
==========================================
- Coverage 85.70% 85.49% -0.22%
==========================================
Files 54 54
Lines 2483 2495 +12
==========================================
+ Hits 2128 2133 +5
- Misses 355 362 +7
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
flash/vision/backbones.py
Outdated
""" | ||
|
||
if model_name in timm.list_models(): | ||
backbone = timm.create_model(model_name, pretrained=pretrained, num_classes=0, |
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.
Why num_classes = 0 ?
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.
this method is suggested to create a model without a classification head in the timm docs. https://rwightman.github.io/pytorch-image-models/feature_extraction/#create-with-no-classifier-and-pooling
…lightning-flash into issue_172-add_timm
Co-authored-by: Kaushik B <[email protected]> Co-authored-by: Kaushik Bokka <[email protected]> (cherry picked from commit 6e548a4)
What does this PR do?
Fixes #172
Before submitting
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 🙃