Uri Alon

Oh yes, that can definitely be the issue. You can try to train on the python150k first, and after convergence -- train on the additional 1600 examples. Best, Uri On...

Hi @smyoder , Thank you for your interest in our work! This indeed sounds like a Windows compatibility issue with file paths. Is this the full error that you're seeing?...

Hi, It looks like the data path was not found, or at least, not parsed well on windows. I suggest running on Linux. Best, Uri

Hi @estiver-alvarez , Thank you for your interest in our work! Are you using the `keras` backend? Can you use the `TensorFlow` backend instead? Best, Uri P.S - [https://code2seq.org/](https://code2seq.org/) is...

Hi @Sohaib90 , It seems that you are describing a problem that is unrelated to the original problem described in this issue. Can you please create a separate issue and...

Hi @IHaveNoEnglishName , Sorry for the delay. Early stopping is not implemented, so you can simply set `NUM_TRAIN_EPOCHS` to `999999` and kill the process manually when you want to stop....

Hi @allomy , Thank you for your interest in code2vec! I think that you can loss here: https://github.com/tech-srl/code2vec/blob/master/tensorflow_model.py#L228 from the standard cross entropy to sigmoid cross entropy: https://www.tensorflow.org/api_docs/python/tf/compat/v1/nn/sigmoid_cross_entropy_with_logits But you...

Hi @allomy , Actually it might be easiest for you to use [https://code2seq.org/](https://code2seq.org/) . It predicts a sequence of labels and not multi-label, but it may either be a good...

Hi @sakshi15108 , Thank you for your kind words! If I remember correctly, `_create_inner_model` does nothing for the tensorflow-model. The model is created here: [https://github.com/tech-srl/code2vec/blob/master/tensorflow_model.py#L197](https://github.com/tech-srl/code2vec/blob/master/tensorflow_model.py#L197) Best, Uri

Hi @ShaliniR11 , Sorry for the delayed response. Did you notice that you have a "space" token in line 21, right before the path? can you delete this space and...