ink1

crucially `dev = torch.device('cuda:0')` is not enough for GPU support. `z_logits = enc(x.cuda())` does the trick though.

Try dall-e mini instead. It may be not as good, but it's been released and ready to start https://github.com/borisdayma/dalle-mini

Yes, I'm running fsns_demo.py the way it is suggested in the readme ``` python fsns_demo.py model_35000.npz \ ../datasets/fsns/fsns_char_map.json ```

I assume FSNS. I downloaded fsns_model.zip which contained model_35000.npz which I'm trying to use.

I unpacked fsns_model.zip into model directory and then ``` cd chainer python fsns_demo.py ../model model_35000.npz \ ../file.jpg ../datasets/fsns/fsns_char_map.json --gpu 0 ```

No, the code is the same. I did a bit of debugging and found that the network being initialised is InverseCompositionalLocalizationNet. I actually unpacked both fsns_model.zip and text_recognition_model.zip this must...

My major deviation from your requirements is TF 1.5.0. Is that potentially a problem? Edit: reverted to 1.4.1 to no avail

You are right, it's the file size. As long as the image is 150x600, RGB FSNS Demo works fine. I've got some FSNS images and the output looks correct. However...

Besides MATLAB OCR (and related) and textspotting by Jaderberg et al (2014), I've only tried CRNN (https://github.com/meijieru/crnn.pytorch). I've seen a few other papers but they had no open source code...

I'm also interested in that, see #16 The best starting I could find is the yaml file shared with sflckr checkpoint. Replace validation by train at the end of the...