search

broadinstitute / keras-rcnn

Keras package for region-based convolutional neural networks (RCNNs)
Other
553 stars 224 forks source link

Final detection layer #96

Closed jhung0 closed 6 years ago

jhung0 commented 6 years ago

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.

codecov-io commented 6 years ago

Codecov Report

Merging #96 into master will increase coverage by 4.06%. The diff coverage is 95.77%.

Impacted file tree graph

@@            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
Impacted Files Coverage Δ
...s_rcnn/layers/object_detection/_object_proposal.py 95.83% <100%> (-1.61%) :arrow_down:
keras_rcnn/layers/__init__.py 100% <100%> (ø) :arrow_up:
keras_rcnn/backend/common.py 94.57% <100%> (+1.64%) :arrow_up:
keras_rcnn/layers/detection.py 92.3% <92.3%> (ø)
keras_rcnn/layers/losses/_rcnn.py 95.34% <0%> (+61.13%) :arrow_up:

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 d782b80...c3e7077. Read the comment docs.