LiteRT overview
Optimized for on-device machine learning : LiteRT addresses five key ODML constraints: latency (there's no round-trip to a server), privacy (no personal data leaves the device), connectivity (internet...
📚 Read more at TensorFlow Guide🔎 Find similar documents
Learn basic and advanced concepts of TensorFlow such as eager execution, Keras high-level APIs and flexible model building.
📚 Read more at TensorFlow Guide🔎 Find similar documents
TF-NumPy Type Promotion
There are 4 options for type promotion in TensorFlow. By default, TensorFlow raises errors instead of promoting types for mixed type operations. Running tf.numpy.experimental_enable_numpy_behavior() s...
📚 Read more at TensorFlow Guide🔎 Find similar documents
Customizing Saving and Serialization
A more advanced guide on customizing saving for your layers and models.
📚 Read more at TensorFlow Guide🔎 Find similar documents
Keras: The high-level API for TensorFlow
Introduction to Keras, the high-level API for TensorFlow.
📚 Read more at TensorFlow Guide🔎 Find similar documents
The Functional API
Complete guide to the functional API.
📚 Read more at TensorFlow Guide🔎 Find similar documents
Training & evaluation with the built-in methods
Complete guide to training & evaluation with `fit()` and `evaluate()`.
📚 Read more at TensorFlow Guide🔎 Find similar documents
Serialization and saving
Complete guide to saving & serializing models.
📚 Read more at TensorFlow Guide🔎 Find similar documents
Making new layers and models via subclassing
Complete guide to writing `Layer` and `Model` objects from scratch.
📚 Read more at TensorFlow Guide🔎 Find similar documents
Understanding masking & padding
Complete guide to using mask-aware sequence layers in Keras.
📚 Read more at TensorFlow Guide🔎 Find similar documents
Working with RNNs
Complete guide to using & customizing RNN layers.
📚 Read more at TensorFlow Guide🔎 Find similar documents
Writing your own callbacks
Complete guide to writing new Keras callbacks.
📚 Read more at TensorFlow Guide🔎 Find similar documents