benglard / convnetpy Goto Github PK
View Code? Open in Web Editor NEWPython port of ConvNetJS
License: MIT License
Python port of ConvNetJS
License: MIT License
It seems like random_action_distribution
isn't being used properly?
Traceback (most recent call last):
File "main_learning2.py", line 373, in <module>
main()
File "main_learning2.py", line 353, in main
action = brain.forward(simulator.map)
File "/Users/eric/src/plithos/src/convnetpy/deepqlearn.py", line 232, in forward
action = self.random_action()
File "/Users/eric/src/plithos/src/convnetpy/deepqlearn.py", line 155, in random_action
cumprob += self.random_action_distribution[k]
AttributeError: 'Brain' object has no attribute 'random_action_distribution'
Hey there, first of all... THANKS! I really appreciate you putting in all the work to make this so much easier for people like me to jump into.
I'm getting this error importing deepqlearn:
Traceback (most recent call last):
File "main_learning2.py", line 5, in <module>
from convnetpy.deepqlearn import Brain
File "/Users/eric/src/plithos/src/convnetpy/deepqlearn.py", line 2, in <module>
from net import Net
File "/Users/eric/src/plithos/src/convnetpy/net.py", line 1, in <module>
from layers.input import InputLayer
File "/Users/eric/src/plithos/src/convnetpy/layers/input.py", line 1, in <module>
from util import getopt
ImportError: No module named util
Easy enough fix, just change import util
to import ..util
, but I may be using this wrong?
@benglard Hi, thanks for sharing the ConvNetPy project. I have found that there is a dark_knowledge.py file in the examples path. I suppose that this dark knowledge is the same thing that Hinton named last year which can be considered as one way of model compression. In dark_knowledge.py, there seems not main function and would you like explain it more in details or add more comments? Thank you .
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.