Keras
Keras is a deep learning API written in Python, running on top of the machine learning platform TensorFlow.
63471
19621
The goal of Keras is to be able to go from idea to result as fast as possible is key to doing good research. It is
-
Simple -- but not simplistic. Keras reduces developer cognitive load to free you to focus on the parts of the problem that really matter.
-
Flexible -- Keras adopts the principle of progressive disclosure of complexity: simple workflows should be quick and easy, while arbitrarily advanced workflows should be possible via a clear path that builds upon what you've already learned.
-
Powerful -- Keras provides industry-strength performance and scalability: it is used by organizations and companies including NASA, YouTube, or Waymo.
Official Website Link: https://keras.io/
Links
Documentation
Documentation & Developer Guides
Using Keras with Weights & Biases
Train a quick model in Keras and track results with W&B
Object Localization with Keras and W&B
Exploring object localization using the bounding box regression technique in Keras.
LSTM RNN in Keras
Understand what LSTM & RNNs are and how to build them with Keras.
Keras Layer Input Explanation With Code Samples
Simple answers to common questions related to the Keras layer arguments.
Integrating Keras with Weights & Biases using the bloodMNIST dataset,
Train a simple image classifier in Keras.
Optimizing Models with Post-Training Quantization in Keras
Performing Facial Keypoints Detection with Post-Training Quantization in Keras
Integrating Keras-Tuner with W&B
Learn how to use Keras Tuner - a tool that helps in the automation of hyper-parameter tuning in Keras.
Iterate on AI agents and models faster. Try Weights & Biases today.