Christian Bartz
Christian Bartz
N specifies the maximum amount of text regions you want to localise in your input image. So if you take the FSNS dataset for instance you will have a maximum...
Yes, you are right! The model you can find for the STN-OCR code (MXNet) is able to produce SOTA results, but the model we trained with Chainer is not, yet....
Good question :sweat_smile:. The network architecture is the same. You should be able to get the same results with either codebase. So take what you like more.
there is nothing wrong :smile:. You get the expected output from this script. Have a closer look at it and you will see that the output is a dict of...
Hmm, it will be difficult for this kind of examples. First, you did not use the right model for this. The text_recognition model only works on already cropped text lines....
I don't quite get your question. What do you want to do? Do you already have a trained model?
This is interesting. The code should actually create a file called `svhn.py` in your log folder. This file is just a copy of the file `svhn.py` in the folder `models`....
I think you receive this error, because the dimensions of your input images are not correct, at least they are not resized to the size expected by the model. You...
`--timesteps` tells the localization network how many text regions you expect to be in the image at max. Increasing ths number should give you longer predictions.
Sure no problem, but you already said that you trained a SVHN model. Could you post the command-line you used to train the model and also the `log` file from...