DingKe/nn_playground
A collection of experimental Keras implementations of various neural network architectures and training techniques.
Not currently ranked — collecting fresh signals.
star history
This repository serves as a playground for experimental deep learning implementations in Keras, providing reference implementations of neural network architectures including Variational Autoencoders, various GAN variants (Wasserstein, Least Squares, Generalized Loss Sensitive), normalization techniques (weight, layer), compression methods (binary/ternary/XNOR networks), and modern architectures like QRNN, gated CNNs, and Squeeze-and-Excitation networks. All scripts default to TensorFlow backend with channels-first data format.
Frequently asked
- What is DingKe/nn_playground?
- A collection of experimental Keras implementations of various neural network architectures and training techniques.
- Is nn_playground open source?
- Yes — DingKe/nn_playground is open source, released under the MIT license.
- What language is nn_playground written in?
- DingKe/nn_playground is primarily written in Python.
- How popular is nn_playground?
- DingKe/nn_playground has 432 stars on GitHub.
- Where can I find nn_playground?
- DingKe/nn_playground is on GitHub at https://github.com/DingKe/nn_playground.