PyTorch_data_loading module

[Natooz]

WIP

Adding new model for PyTorch Dataset classes to load MIDI / tokens, tokenize_midi_dataset now have a tokenizer_config_file_name argument

Data collators to come

[codecov]

Codecov Report

Patch coverage: 91.18% and project coverage change: +0.11% 🎉

Comparison is base (b3ce508) 89.56% compared to head (a98c38a) 89.67%.

Additional details and impacted files

@@            Coverage Diff             @@
##             main      #61      +/-   ##
==========================================
+ Coverage   89.56%   89.67%   +0.11%     
==========================================
  Files          27       31       +4     
  Lines        3688     3933     +245     
==========================================
+ Hits         3303     3527     +224     
- Misses        385      406      +21     

Files Changed	Coverage Δ
miditok/classes.py	87.39% <ø> (ø)
miditok/midi_tokenizer.py	85.36% <66.66%> (ø)
miditok/__init__.py	81.81% <77.77%> (-18.19%)	⬇️
tests/test_pytorch_data_loading.py	85.13% <85.13%> (ø)
miditok/pytorch_data/collators.py	91.30% <91.30%> (ø)
miditok/pytorch_data/datasets.py	96.80% <96.80%> (ø)
miditok/pytorch_data/__init__.py	100.00% <100.00%> (ø)
miditok/tokenizations/__init__.py	100.00% <100.00%> (ø)
miditok/tokenizations/mmm.py	91.98% <100.00%> (ø)
miditok/tokenizations/mumidi.py	93.75% <100.00%> (ø)
... and 6 more

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.