-
Notifications
You must be signed in to change notification settings - Fork 221
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
Final detection layer #96
Conversation
Codecov Report
@@ Coverage Diff @@
## master #96 +/- ##
==========================================
+ Coverage 75.17% 79.24% +4.06%
==========================================
Files 25 26 +1
Lines 721 766 +45
==========================================
+ Hits 542 607 +65
+ Misses 179 159 -20
Continue to review full report at Codecov.
|
keras_rcnn/layers/detection.py
Outdated
return [(1, None, 4), (1, None, 3)] | ||
|
||
def compute_mask(self, inputs, mask=None): | ||
return 2 * [None] |
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.
Missing a newline
keras_rcnn/layers/detection.py
Outdated
|
||
|
||
def compute_output_shape(self, input_shape): | ||
return [(1, None, 4), (1, None, 3)] |
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.
3
?
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.
1
should be None
(or input_shape[0]
)
keras_rcnn/layers/detection.py
Outdated
|
||
return [keras.backend.expand_dims(pred_boxes, 0), keras.backend.expand_dims(pred_scores, 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.
Remove extra newline
Right now the model's output isn't exactly the boxes you'd be interested in, so this layer should output those boxes/labels.
I'm not sure what a good name would be for it though.