omrishsu
omrishsu
I'm [trying to add a new operation](https://github.com/google-research/tapas/issues/128) without training the models again on the wikisql data. However, it seems that the model's graph have some TPU constrains that prevent it...
I want to add another aggregation operating. I've updated the code (protos enums, calc metrics, the model code, etc). By adding a new aggregation operation, some variables need to change...
I've tested the model with the following text: `"The movie: 'Spider-Man 3' (2007) was directed by Sam Raimi.\nDuration: 156\nGenres: J.K. Simmons\nActor1: James Franco\nActor2: Kirsten Dunst\nActor3: Action, Adventure, Romance\nTopics: sandman, spider...
From the [demo of HinSAGE link prediction](https://stellargraph.readthedocs.io/en/stable/demos/link-prediction/hinsage-link-prediction.html) I’ve understood that the model can predict the label of a link between two nodes. I’m looking to know if a link should...
Hi, I'm trying to test ochre on the ICDAR 2017 dataset (English only). I'm not using the workflow but operating ochre myself: 1) I took all the English monographs and...
In utils.py there is a try – except that try to align two strings. In case of an exception the code continues using the argument that was define in the...
Hi, The train_lstm step writes an “all chars” text file that assumes that it encounters all the chars in the corpus. But this is not necessarily true. The training is...
Hi, I’m working on a method to synthetically generating an ocr post processing dataset. I think that ochre could be a great project for benchmark different datasets and evaluate which...
Hi I’m conducting research regarding OCR corpuses, and I would like to use this project for evaluation of how differences on the training corpus effects the quality of the post-processing....
When running with a different dataset I get Invalid argument: Cannot parse tensor from proto: dtype: DT_FLOAT tensor_shape { dim { size: 148860 } dim { size: 297720 } }...