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

The `rec` module #234

Closed jrzaurin closed 2 months ago

jrzaurin commented 2 months ago

These are

  1. Factorisation Machines (FM) and DeepFM
  2. Field Aware Factorisation Machines (FFM) and DeepFFM
  3. Extreme Deep Factorisation Machines (xDeepFM)
  4. Deep Interest Networks (DIN)

We will add more in the near future.

codecov[bot] commented 2 months ago

Codecov Report

Attention: Patch coverage is 97.59615% with 10 lines in your changes missing coverage. Please review.

Project coverage is 94.80%. Comparing base (220eb3f) to head (8dd61ce). Report is 34 commits behind head on master.

Files with missing lines Patch % Lines
pytorch_widedeep/models/rec/din.py 98.41% 2 Missing :warning:
...torch_widedeep/models/tabular/embeddings_layers.py 33.33% 2 Missing :warning:
pytorch_widedeep/training/trainer.py 77.77% 2 Missing :warning:
pytorch_widedeep/models/_get_activation_fn.py 50.00% 1 Missing :warning:
pytorch_widedeep/models/rec/deepfm.py 97.56% 1 Missing :warning:
...rch_widedeep/models/tabular/_base_tabular_model.py 90.90% 1 Missing :warning:
...eep/models/tabular/transformers/tab_transformer.py 90.00% 1 Missing :warning:
Additional details and impacted files ```diff @@ Coverage Diff @@ ## master #234 +/- ## ========================================== + Coverage 94.67% 94.80% +0.12% ========================================== Files 116 121 +5 Lines 7252 7579 +327 ========================================== + Hits 6866 7185 +319 - Misses 386 394 +8 ``` | [Flag](https://app.codecov.io/gh/jrzaurin/pytorch-widedeep/pull/234/flags?src=pr&el=flags&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Javier) | Coverage Δ | | |---|---|---| | [unittests](https://app.codecov.io/gh/jrzaurin/pytorch-widedeep/pull/234/flags?src=pr&el=flag&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Javier) | `94.80% <97.59%> (?)` | | Flags with carried forward coverage won't be shown. [Click here](https://docs.codecov.io/docs/carryforward-flags?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=Javier#carryforward-flags-in-the-pull-request-comment) to find out more.

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