Jerod Weinman

Thanks for the question. I want to make sure I understand what you're trying to do. (While also confessing I will need to page many details about the code back...

Well, it should be possible without too much trouble, I hope. I note that both [model_fn.predict_fn](https://github.com/weinman/cnn_lstm_ctc_ocr/blob/c3f03b730e7ee0eea11d3d17d25c7c7d1c12a40a/src/model_fn.py#L486) (used for `validate.py` to predict strings) and [model_fn.evaluate_fn](https://github.com/weinman/cnn_lstm_ctc_ocr/blob/c3f03b730e7ee0eea11d3d17d25c7c7d1c12a40a/src/model_fn.py#L400) use the same underlying processing that...

As a quick follow-up before I completely lose track of this thread. The confusing issue that stymied me was that I thought the underlying tensors should be producing batched outputs,...

@igorvishnevskiy thanks for your comments and all your hard work so far! I'm definitely eager to follow the thread your progress, and contribute wherever I might be able to help....

@igorvishnevskiy I'm thrilled you got it figured out. This seems like a nice enhancement to the tool, I'd be glad to see a PR so it can be shared with...

I've added a straightforward/degenerate fix (287e71a2ac158d8c8d6d720c2904a50d22a7ca1f) that seems to work. (E.g., Run `apps/single_curve_tf.py` and `apps/single_stroke_tf.py`). However, that version does not allow for the more flexible stroke width/thickness options that seem...