bourdakos1 / capsnet-visualization Goto Github PK

When I run this code I get the following error message:

OSError: [Errno 2] No such file or directory: 'reconstructions'

Is this folder supposed to be there or am I supposed to generated it somehow?

Tx.

I ran run_visualization.py and accessed http://localhost:5000 after follow instruction written in README.md but I can only see empty.
run_visualization.py print these logs.

CapsNet-Visualization % python run_visualization.py
 * Serving Flask app "run_visualization" (lazy loading)
 * Environment: production
   WARNING: Do not use the development server in a production environment.
   Use a production WSGI server instead.
 * Debug mode: on
 * Running on http://127.0.0.1:5000/ (Press CTRL+C to quit)
 * Restarting with stat
 * Debugger is active!
 * Debugger PIN: 205-424-827
path is 
127.0.0.1 - - [06/May/2020 00:18:28] "GET / HTTP/1.1" 304 -
127.0.0.1 - - [06/May/2020 00:18:28] "GET /static/css/main.f402c303.css HTTP/1.1" 404 -
127.0.0.1 - - [06/May/2020 00:18:28] "GET /static/js/main.9b57b7fd.js HTTP/1.1" 404 -

I think it doesn't load static files because static_folder='' is in there.

Can anyone tell me what are the 16-dimensional parameters refer to? According to paper, it refers to thickness, skew etc. How to know which value refer to which parameter in image reconstruction?

Thank you for providing the code of your work.

I am trying to run your model for some other images by running python render.py [filename].
However, I got the error of

TypeError: 'list' objects cannot be interpreted as an integer'

I will be appreciated for any suggestion to solve this error.

Versions of many libraries have gone ahead and do not support the old format of communication among themselves. It turned out to start only after I picked up the correct libraries

bleach==1.5.0
click>=6.7
cycler>=0.10.0
enum34>=1.1.6
Flask==0.12.2
html5lib==0.9999999
itsdangerous>=0.24
Jinja2>=2.10
Markdown>=2.6.11
MarkupSafe>=1.0
matplotlib>=2.1.2
numpy>=1.14.0
Pillow>=5.0.0
protobuf>=3.5.1
pyparsing>=2.2.0
python-dateutil>=2.6.1
pytz>=2017.3
scipy>=1.0.0
six>=1.11.0
tensorflow>=1.4.1
tensorflow-tensorboard>=0.4.0
Werkzeug>=0.14.1

Hello,

I loved the work that you have done. I have a dataset that have a little more complex images than digits. If the image size is 28 X 28, the pixels can blurred and the network cannot recognize anything. Its not able to reconstruct anything. To get some reconstruction, I guess I would have to give him some images greater than 28 X 28. But, when I do that, it gives an error. An array of this shape cannot be converted to 20 X20. Can you please help me with this?

Regards,
Bhagyashree