bourdakos1 / capsnet-visualization Goto Github PK
View Code? Open in Web Editor NEW๐ A visualization of the CapsNet layers to better understand how it works
License: MIT License
๐ A visualization of the CapsNet layers to better understand how it works
License: MIT License
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?
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
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.