Comments (5)
I've solved the problem.THANKS ANYWAY.
from deep_complex_networks.
Hi CedricChing:
How did you fix the problem of "ValueError: Operands could not be broadcast together with shapes (32, 16, 44) (32, 16, 22)" after running command: python scripts/run.py train --model complex?
I am using python2.7, Theano (0.10.0b1), and Keras (2.0.6).
Thanks,
Miranda
from deep_complex_networks.
Hello, @Mi1234 !
The data format of Theano is 'channel_first', but the default setting of keras is 'channel_last', which is the data format of Tensorflow. So the data_format in file '~/.keras/keras.json' should be changed to 'channel_first'. You can follow the instructions here https://keras.io/backend/#switching-from-one-backend-to-another
Hope this suggestion can help you.
Have a good day.
Cedric
from deep_complex_networks.
Thank you very much, CedricChing!
The problem has been solved following you instruction.
Best,
Miranda
from deep_complex_networks.
I am still facing the same issue even after trying this fix. I run the command:
python scripts/run.py train -d cifar10
Any further help will be highly appreciated. :)
from deep_complex_networks.
Related Issues (20)
- Mímir IOError HOT 2
- inverse_st HOT 2
- Windows support HOT 1
- utilsextension DLL load failed HOT 1
- [Feature request] deconvolution layer HOT 2
- modReLU, CreLU, zReLU are absent? HOT 12
- Anybody port this to TensorFlow or Pytorch? HOT 8
- Typo in readme example leads to zero division or input size 0 errors
- questions about transformation of tensor shape in Conv2d HOT 1
- Fourier argument question & comparison of shallow vs. deep complex models
- ValueError: Error when checking target: expected complex_dense_1 to have shape (None, 48) but got array with shape (38400, 24) HOT 1
- GetReal not working HOT 1
- modReLU HOT 2
- AttributeError: 'module' object has no attribute 'Logger' HOT 4
- Question concerning weight initialization.
- Has the plural neural network been doing plural work?
- About the version of library to be imported HOT 3
- Using your own dataset. HOT 1
- Is the learn imaginary data really work?
- different shape tensors
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 deep_complex_networks.