search

jrzaurin / pytorch-widedeep

A flexible package for multimodal-deep-learning to combine tabular data with text and images using Wide and Deep models in Pytorch
Apache License 2.0
1.3k stars 190 forks source link

Multi text img columns #215

Closed jrzaurin closed 5 months ago

jrzaurin commented 5 months ago
  1. Added the possibility of using multiple text or image columns
  2. Added option to fuse the model via a ModelFuser
  3. Added multi-target losses
  4. Fixed some bugs
codecov[bot] commented 5 months ago

Codecov Report

Attention: Patch coverage is 88.82175% with 74 lines in your changes missing coverage. Please review.

Project coverage is 94.38%. Comparing base (90c8193) to head (ae3b84f). Report is 54 commits behind head on master.

Files Patch % Lines
...dedeep/load_from_folder/image/image_from_folder.py 66.66% 13 Missing :warning:
pytorch_widedeep/losses_multitarget.py 92.59% 12 Missing :warning:
pytorch_widedeep/models/model_fusion.py 89.28% 12 Missing :warning:
pytorch_widedeep/models/wide_deep.py 79.66% 12 Missing :warning:
pytorch_widedeep/training/_wd_dataset.py 80.00% 5 Missing :warning:
...ytorch_widedeep/training/_multiple_lr_scheduler.py 33.33% 4 Missing :warning:
pytorch_widedeep/callbacks.py 94.44% 3 Missing :warning:
...widedeep/load_from_folder/text/text_from_folder.py 80.00% 3 Missing :warning:
pytorch_widedeep/models/text/rnns/basic_rnn.py 50.00% 3 Missing :warning:
...ep/load_from_folder/tabular/tabular_from_folder.py 83.33% 2 Missing :warning:
... and 4 more
Additional details and impacted files ```diff @@ Coverage Diff @@ ## master #215 +/- ## ========================================== - Coverage 95.01% 94.38% -0.63% ========================================== Files 109 117 +8 Lines 6615 7445 +830 ========================================== + Hits 6285 7027 +742 - Misses 330 418 +88 ```

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.