search

songlab-cal / tape-neurips2019

Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology. (DEPRECATED)
https://arxiv.org/abs/1906.08230
MIT License
118 stars 34 forks source link

Global Arguments question #7

Closed spark157 closed 5 years ago

spark157 commented 5 years ago

In @proteins.configin __main__.py there are two default global arguments set as follows:

    freeze_embedding_weights = False  # noqa: F841
    save_outputs = False  # noqa: F841

Can you tell me what freeze_embedding_weights does? If I want the pretrained unsupervised weights for the fluorescence task to remain fixed (ie. the embeddings will be constant) should I switch this to True?

For save_outputs, if this is False will outputs be saved? [See README.md|Saving Results - not sure if there is a discrepency here.] If 'save_outputs' is True what gets saved?

Thanks.

Scott

thomas-a-neil commented 5 years ago

Thanks for your questions!

freeze_embedding_weights does exactly as you describe - if you want to train the downstream task model without propagating gradient updates through the language model, you should set this flag to True

save_outputs will save the outputs of the validation pass into a file called outputs.pkl. When running tape-eval, outputs are automatically saved and this flag is ignored.