Version 0.17.0

[phborba]

• New evaluation metrics;
• New evaluation on test set;
• New inference service with image upload;
• Bug fixes;

[codecov]

Codecov Report

Merging #149 (96d39b4) into main (2c40286) will decrease coverage by 3.55%.
The diff coverage is 37.52%.

@@            Coverage Diff             @@
##             main     #149      +/-   ##
==========================================
- Coverage   79.88%   76.32%   -3.56%     
==========================================
  Files          65       67       +2     
  Lines        6856     7313     +457     
==========================================
+ Hits         5477     5582     +105     
- Misses       1379     1731     +352     

Flag	Coverage Δ
cpu	76.32% <37.52%> (-3.56%)	⬇️
python	76.32% <37.52%> (-3.56%)	⬇️
unittest	76.32% <37.52%> (-3.56%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
...odels_trainer/config_definitions/dataset_config.py	0.00% <0.00%> (ø)
...ainer/config_definitions/loss_config_definition.py	0.00% <0.00%> (ø)
..._models_trainer/config_definitions/train_config.py	0.00% <0.00%> (ø)
...entation_models_trainer/custom_losses/base_loss.py	88.23% <0.00%> (ø)
..._models_trainer/custom_losses/crossfield_losses.py	83.07% <ø> (ø)
pytorch_segmentation_models_trainer/main.py	0.00% <0.00%> (ø)
..._segmentation_models_trainer/predict_from_batch.py	0.00% <0.00%> (ø)
...odels_trainer/predict_mod_polymapper_from_batch.py	0.00% <0.00%> (ø)
...els_trainer/tools/visualization/crossfield_plot.py	60.37% <0.00%> (ø)
pytorch_segmentation_models_trainer/train.py	85.29% <0.00%> (-2.59%)	⬇️
... and 31 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 650b304...96d39b4. Read the comment docs.