Comments (3)
Looking at the documentation it seems like both work to calculate the cross-entropy: http://deeplearning.net/software/theano/library/tensor/nnet/nnet.html#tensor.nnet.categorical_crossentropy
Also, using np.eye
is a very inefficient way to make a one-hot vector since it builds the full identity matrix first. Really shouldn't use that.
from nn-theano.
Actually, I tried if without np.eye, the example won't run for GPU, but it runs for CPU.
from nn-theano.
It could be that the operation is not implemented on the GPU in Theano (CPU and GPU have different implementations and not everything is supported) and that's why you need to use one-hot vectors. You'd be able to see that from the error message though. Sorry, it has been a while since I wrote this code and I don't remember why exactIy I changed it to one-hot vectors.
from nn-theano.
Related Issues (3)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from nn-theano.