Difference between revisions of "Keras"
m (→Neural Networks Hyperparameter Search, the Visualized Way) |
m (→Neural Networks Hyperparameter Search, the Visualized Way) |
||
| Line 50: | Line 50: | ||
* [http://towardsdatascience.com/neural-networks-hyperparameter-search-the-visualized-way-9c46781bea28 Neural Networks Hyperparameter Search, the Visualized Way | Vladimir Ilievski - Towards Data Science] | * [http://towardsdatascience.com/neural-networks-hyperparameter-search-the-visualized-way-9c46781bea28 Neural Networks Hyperparameter Search, the Visualized Way | Vladimir Ilievski - Towards Data Science] | ||
| − | Track and visualize Machine Learning experiments using [[Python#HiPlot |HiPlot]] Parallel Coordinates Plot in Python | + | Track and visualize Machine Learning experiments using [[Python#HiPlot |HiPlot]] Parallel Coordinates Plot in [[Python]] |
<img src="http://miro.medium.com/max/1250/1*mxBO17gD6RzDcqhwSb-3_Q.png" width="1000"> | <img src="http://miro.medium.com/max/1250/1*mxBO17gD6RzDcqhwSb-3_Q.png" width="1000"> | ||
Revision as of 12:55, 8 January 2022
Youtube search... ...Google search
- TensorFlow
- Keras: The Python Deep Learning library
- Keras.js
- Auto Keras
- Keras_Cheat_Sheet_Python - Data Camp pdf
- TensorFlow.js for training and deploying ML models in the browser and on Node.js (was called Deeplearnjs)
- How to build your own AlphaZero AI using Python and Keras
- NLP Keras model in browser with TensorFlow.js
- Transfer Learning With Keras
- Git - GitHub and GitLab
Note: Keras capability is now also part of Tensorflow
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. 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.
YouTube Keras Series
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.
Neural Networks Hyperparameter Search, the Visualized Way
- Neural Networks Hyperparameter Search, the Visualized Way | Vladimir Ilievski - Towards Data Science
Track and visualize Machine Learning experiments using HiPlot Parallel Coordinates Plot in Python
