Closed JihongJu closed 7 years ago
Merging #27 into master will increase coverage by
4.81%
. The diff coverage is97.14%
.
@@ Coverage Diff @@
## master #27 +/- ##
==========================================
+ Coverage 48.44% 53.25% +4.81%
==========================================
Files 15 17 +2
Lines 545 569 +24
==========================================
+ Hits 264 303 +39
+ Misses 281 266 -15
Impacted Files | Coverage Δ | |
---|---|---|
keras_rcnn/heads/__init__.py | 100% <100%> (ø) |
|
keras_rcnn/models.py | 81.48% <100%> (+81.48%) |
:arrow_up: |
keras_rcnn/heads/resnet.py | 94.11% <94.11%> (ø) |
Continue to review full report at Codecov.
Legend - Click here to learn more
Δ = absolute <relative> (impact)
,ø = not affected
,? = missing data
Powered by Codecov. Last update f3e6f4c...9aadff0. Read the comment docs.
@JihongJu Whoa! You’ve been busy! I’m excited to comment. Would you mind giving me a day or two? It’ll take some time to consider and respond.
cc: @mcquin
@JihongJu I merged the backend and pooling changes.
Great. I will continue the work on weekends.
@0x00b1 If you are okay with this design, I will continue with the Mask branch as in TODO with a new PR.
@JihongJu Awesome! Merged! (I might do a little cleanup today or tomorrow.)
My current implementation is:
And the R-CNN heads from Mask R-CNN looks like![resnet_heads](https://user-images.githubusercontent.com/8668792/27003225-18154e64-4df3-11e7-889a-779114405793.png)
That becomes:
in
keras_rcnn.heads.ResHead
.What do you think? @0x00b1
P.S. The API design should be discussed in broadinstitute/keras-rcnn#28