tf.keras              

tf.keras                                               Deep Learning

namespace

Definition: The integrated Keras interface within TensorFlow, tf.keras, is a high-level API used to build, train, evaluate, and deploy deep learning models in the TensorFlow ecosystem. It supports common modeling workflows through Sequential, Functional, and subclassing-based model definitions, as well as built-in training methods such as Model.fit() [TensorFlow API Docs].

Example in context: “The CNNs were implemented in the tf.keras (Tensorflow version 2.2.0) library and trained using the SGD optimizer with a batch size of 32 during 50 epochs.” [Ozaki et al. 2022]

Related terms: Keras API; TensorFlow Keras; TensorFlow high-level API

Добавить комментарий 0

Ваш электронный адрес не будет опубликован. Обязательные поля помечены *