search

SuperSupermoon / MedViLL

MedViLL official code. (Published IEEE JBHI 2021)
MIT License
83 stars 11 forks source link

Fetching relevants position embeddings instead of all. May increase s… #2

Closed hammad26 closed 2 years ago

hammad26 commented 2 years ago

Hi Relevant position embeddings were only the first one and last one, but all were being calculated. I updated the code to focus only on relevant position embeddings (first and last one). I am hoping that it will improve speed and will also save some memory as well.

hammad26 commented 2 years ago

Hi Decoder part has some serious issue with imports. Corrected the imports and also, beam_size argument was commented in decoder but was being used at the time of model creation. Fixed that as well.

SuperSupermoon commented 2 years ago

Thanks for correcting the typo.