Giuseppe Attardi

Results 23 comments of Giuseppe Attardi

It works for me on TF 1.8.

Check your input. Are you supplying a properly formatted tsv file?

There are changes to make in the loss function (in sentiwords.pyx line 139) and its derivative, which is currently a hinge loss on a single polarity value.

Unfortunately not. I never tried DeepNL on Windows. The error on missing file deepnl/words.pyx is strange. On MacOs there was a problem with upper case in file names, but it...

> On 05 mag 2016, at 15:12, jadejarohan65 [email protected] wrote: > > Good evening sir. I trained a model using convolution network script dl-conv.py > my doubt is how to...

> On 12 mar 2016, at 13:19, GraphGrail [email protected] wrote: > > Hi, deepnl is cool, but i cannot find good tutorial on how to train my custom Semantic Role...

> On 12 mar 2016, at 16:04, GraphGrail [email protected] wrote: > > Thanks for answer, sentence splitting and tokenization is not a problem, i can do this myself in Python....

I think there is a problems on Windows, passing file descriptors across threads. It would require some rewriting in order to open descriptors within threads.

Isn't summary = [i for i in page] the same as: summary = page

Watch out: the second argument to reduce_process() might be sys.stdout and not an OutputSplitter. if out_file == '-': output = sys.stdout Then it won't have method open_file(), that you call...