Good deep net architectures

[tadas-subonis]

Hello,

would anyone be willing to share some architectures that worked for you quite well? I figured that this would be a great place to ask that even though it is (kinda) not directly related to the project :-).

For example, I had some decent success with https://github.com/Holmeyoung/crnn-pytorch/blob/master/models/crnn.py (CRNN)

What other models are worth giving a shot?

[Belval]

Hi,

I've only read of two methods, but there is probably a lot more literature covering the subject than what I read.

• CRNN, that has been proven to work
• NRTR, that uses attention instead of the Bidirectional RNN used by Shi and al.

Unfortunately, I did not find any implementation of the latter on GitHub, and my version is unfinished.

[YacobBY]

@tadas-subonis https://github.com/clovaai/deep-text-recognition-benchmark This one combined with their CRAFT detector is very good.

[tadas-subonis]

@YacobBY Thanks for the link! It has some really useful stuff.