search

frankkramer-lab / MIScnn

A framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning
GNU General Public License v3.0
400 stars 116 forks source link

Added Focal Loss #80

Closed Deathlymad closed 3 years ago

Deathlymad commented 3 years ago

added locally stored focal loss function.

codecov-commenter commented 3 years ago

Codecov Report

Merging #80 (56c8774) into development (f364606) will decrease coverage by 0.17%. The diff coverage is 55.55%.

Impacted file tree graph

@@               Coverage Diff               @@
##           development      #80      +/-   ##
===============================================
- Coverage        91.57%   91.40%   -0.18%     
===============================================
  Files               52       52              
  Lines             3705     3746      +41     
===============================================
+ Hits              3393     3424      +31     
- Misses             312      322      +10
Impacted Files Coverage Δ
setup.py 0.00% <ø> (ø)
miscnn/neural_network/metrics.py 22.72% <20.00%> (-0.49%) :arrow_down:
miscnn/neural_network/data_generator.py 94.44% <100.00%> (ø)
miscnn/neural_network/model.py 96.70% <100.00%> (+1.09%) :arrow_up:
miscnn/processing/data_augmentation.py 97.80% <100.00%> (ø)
miscnn/evaluation/split_validation.py 88.46% <0.00%> (-2.02%) :arrow_down:
miscnn/evaluation/cross_validation.py 89.39% <0.00%> (-0.93%) :arrow_down:
miscnn/data_loading/interfaces/nifti_io.py 84.84% <0.00%> (-0.64%) :arrow_down:
miscnn/data_loading/interfaces/image_io.py 85.71% <0.00%> (-0.23%) :arrow_down:
... and 4 more

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 f364606...56c8774. Read the comment docs.