search

weinman / cnn_lstm_ctc_ocr

Tensorflow-based CNN+LSTM trained with CTC-loss for OCR
GNU General Public License v3.0
498 stars 170 forks source link

Could you give a link to a trained model to test the neural network? #40

Closed teemiik closed 5 years ago

weinman commented 5 years ago

PR welcome for a script that will save the model (not as a training checkpoint).

teemiik commented 5 years ago

@weinman I can make you this scenario, because I still need it, if the neural network shows a good result, I'll put it here, but I need the training checkpoint files for test.

teemiik commented 5 years ago

@weinman I just don't have a chance to train her for the test yet.

weinman commented 5 years ago

Using the tfrecord files included in the repo, you should be able to run one (or even zero) rounds of training, even on a CPU to get model.ckpt-00000 to work from.

teemiik commented 5 years ago

@weinman but in this case, I do not know in practice how well the network works, you have even examples of work I do not see here

weinman commented 5 years ago

I'm simply pointing out everything is already provided to produce a simple training checkpoint, enough to write a script that produces a stored model (even if the model is terrible). I will gladly use such a script to produce and link to a well-trained mjsynth-based model.

teemiik commented 5 years ago

@weinman Well good, is your model trained for English only? is it possible to support multiple languages?

weinman commented 5 years ago

@teemilk Can you read about mjsynth before you ask any more questions.

weinman commented 3 years ago

The model checkpoint (trained using MapTextSynth) from the ICDAR 2019 paper is posted here: https://weinman.cs.grinnell.edu/data/cnn_lstm_ctc_ocr_checkpoint_icdar19.tar.bz2