Christian Bartz

> I tried pictures of varying format and sizes The FSNS Model is trained on pictures of size `600x150`. Furthermore, the FSNS dataset consists of images that always show four...

the FSNS model should technically be able to recognize digits and characters appearing on an image. But what exactly do you mean with 'localized' image. Do you mean a line...

You won't find any of this in this repository. But in [this](https://github.com/Bartzi/stn-ocr) repository you can find code for such a case and also a link to a model. You are...

Yes, you can use this network architecture and code to train a model that can do so.

There is no such code in this repository, but the other repository contains such [code](https://github.com/Bartzi/stn-ocr/blob/master/mxnet/eval_text_recognition_model.py). You could also use the code in this repository to train such a model. But...

I don't have anything like that. But you can have a look at the evaluation files and create a python script that does s.th. like this for you. Should not...

Sequence accuracy is around 78% on the FSNS dataset, but this is hardly comparable to what you are trying to achieve.

Hmm, I think I could do this, but you'd have to wait until next week... I know that the evaluation code loooks difficult, but it is actually quite easy. First,...

Alright, I've created a small demo script for you. You can find it [here](https://github.com/Bartzi/see/blob/master/chainer/fsns_demo.py). I've also added usage information to the README [here](https://github.com/Bartzi/see#fsns-demo) Hope it helps.

Alright I see your problem. You get this error, because the input size of your images is not correct, it should be 600x150. But I suggest, that you do not...