Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

regarding data sets and model #10

Open
nazeer2014 opened this issue Feb 8, 2017 · 8 comments
Open

regarding data sets and model #10

nazeer2014 opened this issue Feb 8, 2017 · 8 comments

Comments

@nazeer2014
Copy link

I am trying to run your code

i try to run for datasets and model as follows

:~/reading-text-in-the-wild/DICT2$ python extract_dictnet_weights.py
File "extract_dictnet_weights.py", line 40
model_file = 'LOCATION OF dictnet.mat from http://www.robots.ox.ac.uk/~vgg/research/text/#sec-models NIPS
^
SyntaxError: EOL while scanning string literal

how to fix this
please

@mathDR
Copy link
Owner

mathDR commented Feb 8, 2017

@nazeer2014 Did you download the dictnet model from the website?

@nazeer2014
Copy link
Author

I see a file charnat.mat in model_release directory in 'reading-text-in-the-wild ' dowloaded directory

But i didnt download dictnet model
(I think you talk about downloading from http://www.robots.ox.ac.uk/~vgg/research/text/model_release.tar.gz)

As i am new to this field could you please expalin the in detail steps to run the madles and dataset in ubuntu platform

I hope it willbe helpful for new comers

Many thanks in advance

@mathDR
Copy link
Owner

mathDR commented Feb 8, 2017

Hi @nazeer2014 I was hoping the README file went through this and served as a primer on how to get started. Can you point to instances where it is confusing?

@nazeer2014
Copy link
Author

yes i went through README file

where i get confused is in dataset and model section:

""The training data for the networks comes from the MJSynth dataset and the models are extracted from the MATLAB models located at models

The weights from the MATLAB models are extracted for conversion to Keras via the files

extract_dictnet_weights.py

for the DICT+2 model ""

so when i run extract_dictnet_weights.py

ubuntu says

File "extract_dictnet_weights.py", line 40
model_file = 'LOCATION OF dictnet.mat from http://www.robots.ox.ac.uk/~vgg/research/text/#sec-models NIPS
^
SyntaxError: EOL while scanning string literal

so which file i should modify?

@mathDR
Copy link
Owner

mathDR commented Feb 8, 2017

The file you need is located at the address (robots.ox.ac.uk site). The file is too big to host on github, so you need to download it yourself. After downloading, you need to go into the extract_dictnet_weights.py file and overwrite the text of model_file to where on your local machine you placed the file.

@nazeer2014
Copy link
Author

ah OK I am downlading it i will try

and it is same procedure for extract_charnet_weights.py also ?

@mathDR
Copy link
Owner

mathDR commented Feb 8, 2017

Yes, the procedure is the same. Furthermore, within the README, it denotes the correct versions of keras and tensorflow. You will have to change some tensorflow files as well

@nazeer2014
Copy link
Author

Many Thanks to you

I will check and come back to you if I need any help

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants