NNKit: A Python framework for creating dynamic neural networks.
NNKit: A Python framework for creating dynamic neural networks
NNKit is a framework for creating and training neural network models, based on dynamic computation graphs. See this post for more info on how the framework works.
You can pip install nnkit, in which case Numpy will also be installed. Otherwise you can download the source and manually install numpy if necessary.
The following is a list of modules, nodes and optimizers, along with the framework version in which they were added.
- ReLU (1.0)
- LReLU (1.0)
- Sigmoid (1.0)
- Tanh (1.0)
- Softmax (1.0)
- Multiply (1.0)
- Add (1.0)
- L1 (1.0)
- L2 (1.0)
- Cross Entropy (1.0)
- Huber (1.4.0)
- Batch Normalization (1.0)
- L2 (1.0)
- Dropout (1.0)
- Gradient descent / momentum (1.0)
- Adam / RMSProp (1.0)
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size nnkit-1.4.2.tar.gz (9.3 kB)||File type Source||Python version None||Upload date||Hashes View|