Hardian Lawi

icon indicating a website link https://www.linkedin.com/in/hardianlawi/ icon indicating an email [email protected]

icon company Stealth Startup icon location ML Scientist/Engineer

Results 6 comments of Hardian Lawi

thread does not terminate when calling parallel_apply()

I encounter this issue as well where the thread just hangs there. Is it possible to have a `timeout` option?

Convert lambda to regular function

Can we get this merged? @nikitakit

Spacy and Berkeley parser Multi-processing

I also tried running the spacy pipeline using GPU by adding the codes below, but it does not seem to give much boost. ```python import spacy import torch spacy.prefer_gpu() device...

Change pre-trained model?

I think the codes do not work for all pre-trained models. I tried changing `bert-base-cased` to `roberta-large` and it did not work for the example in the documentation

Example training file

Hi @ntelo007 when I experimented on this, I was using a tabular CSV file, not images data. You can specify the label [here](https://github.com/hardianlawi/MTL-Homoscedastic-Uncertainty/blob/master/scripts/config.py). Also, these scripts were used to solve...

Shape of weight variables

Hi @MariamMohamedFawzy, can you give more details about your problem?