-
Notifications
You must be signed in to change notification settings - Fork 7k
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
Enable ONNX Test for MaskRcnn #1613
Conversation
Codecov Report
@@ Coverage Diff @@
## master #1613 +/- ##
==========================================
+ Coverage 65.97% 66.03% +0.06%
==========================================
Files 91 91
Lines 7229 7229
Branches 1095 1095
==========================================
+ Hits 4769 4774 +5
+ Misses 2153 2150 -3
+ Partials 307 305 -2
Continue to review full report at Codecov.
|
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.
Thanks a lot!
This is good to merge, I'd just want to have your thoughts on the two comments.
def test_mask_rcnn(self): | ||
images, test_images = self.get_test_images() | ||
|
||
model = models.detection.mask_rcnn.maskrcnn_resnet50_fpn(pretrained=True) | ||
model = models.detection.mask_rcnn.maskrcnn_resnet50_fpn(pretrained=True, min_size=200, max_size=300) |
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.
For a follow-up PR, do you think it would be possible to remove the need for downloading the pre-trained weights in the tests?
@@ -54,7 +54,7 @@ before_install: | |||
- pip install typing | |||
- | | |||
if [[ $TRAVIS_PYTHON_VERSION == 3.6 ]]; then | |||
pip install onnxruntime | |||
pip install -q --user -i https://test.pypi.org/simple/ ort-nightly==1.0.0.dev1123 |
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.
Do you have an idea when the new stable version of the onnxruntime
will be available?
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.
not sure, I will ask and let you know
@fmassa can we merge this? |
MaskRcnn should now be exportable to ONNX.
For more information on exporting this model, follow instructions in : #1555 (comment)