Python Deep Learning library
Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano. It was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research.
Use Keras if you need a deep learning library that:
Allows for easy and fast prototyping (through user friendliness, modularity, and extensibility).
Supports both convolutional networks and recurrent networks, as well as combinations of the two.
Runs seamlessly on CPU and GPU.
Read the documentation at Keras.io.
-
4
derived packages
- Download package
-
Checkout Package
osc -A https://api.opensuse.org checkout science:machinelearning/python-Keras && cd $_ - Create Badge
Refresh
Refresh
Source Files
| Filename | Size | Changed |
|---|---|---|
| Keras-2.3.1.tar.gz | 0001341527 1.28 MB | |
| _link | 0000000124 124 Bytes | |
| _multibuild | 0000000053 53 Bytes | |
| python-Keras.changes | 0000002620 2.56 KB | |
| python-Keras.spec | 0000005288 5.16 KB |
Revision 16 (latest revision is 21)
Christian Goll (mslacken)
accepted
request 885443
from
Benjamin Greiner (bnavigator)
(revision 16)
- Downgrade to 2.3.1 * the last version of multi-backend Keras to support tensorflow 1 - Multi-backend Keras is not maintained and not compatible with recent tensorflow2. Switch back to tensorflow 1 and add upstream's announcement about the deprecation of multi-backend keras to the package description. Note that this means that python-Keras is no longer in Tumbleweed. - Fix test suite - Reorganize requirements
Comments 0