Christos Baziotis

Is there a solution with OPENCV=1? I can't get it to work.

First of all, what version of pytorch do you have? The project was developed with pytorch version `0.4.0`. Judging by the error message, the problem seems to be that the...

Pretraining should take seconds to minutes, depending on your hardware. Please upgrade ekphrasis and try again: ``` pip install ekphrasis -U ```

This is related to https://github.com/cbaziotis/ekphrasis/issues/11#issuecomment-506710607. Use the proposed workaround until I resolve the issue.

Have you set `unpack_contractions=True`?

The library uses memoization. You can either shrink the [maxsize](https://github.com/cbaziotis/ekphrasis/blob/66e69afb9e92b4cc0f4d2ac3e1fe0342f8063c50/ekphrasis/classes/segmenter.py#L116), or call python's garbage collector manually. ```python import gc # ekphrasis preproccessing... gc.collect() ```

Hi Matt, Could you please pull from the master and try again? Also, in case you are not aware of this, when loading a model with custom layers, you have...

Please tell me what version of keras are you using and with what backend, in order to be able to reproduce the problem. I don't use Keras for my projects...

Unfortunately, i have updated the repo in order to work with keras 2.x. There are some breaking changes from keras 1.X to 2.x. Also, this may be a TF issue....

Hi guys, sorry for taking so long to update the repository. I just updated the codebase. It now works with the latest versions of Keras (2.2.0) and Tensorflow (1.8.0). Please...