- Keras 2.x Projects
- Giuseppe Ciaburro
- 88字
- 2021-07-02 14:36:11
Keras backend options
Keras is a model-level library that provides high-level blocks for the development of deep learning models. Keras developers have focused their efforts on creating high-level models by neglecting low-level operations such as tensor products, convolutions, and so on. These operations have been entrusted to specialized and well-optimized tensor manipulation libraries that already exist, thus acting as a backend engine for Keras. Several backend engines can be connected perfectly to Keras. Actually, Keras has three backend implementations available—TensorFlow, Theano, and Microsoft Cognitive Toolkit (CNTK).
推薦閱讀
- Dreamweaver CS3+Flash CS3+Fireworks CS3創(chuàng)意網(wǎng)站構(gòu)建實(shí)例詳解
- 最簡(jiǎn)數(shù)據(jù)挖掘
- Photoshop CS3特效處理融會(huì)貫通
- 人工智能與人工生命
- WordPress Theme Development Beginner's Guide(Third Edition)
- 永磁同步電動(dòng)機(jī)變頻調(diào)速系統(tǒng)及其控制(第2版)
- C語(yǔ)言開發(fā)技術(shù)詳解
- 工業(yè)機(jī)器人操作與編程
- Machine Learning with the Elastic Stack
- Pentaho Analytics for MongoDB
- 統(tǒng)計(jì)挖掘與機(jī)器學(xué)習(xí):大數(shù)據(jù)預(yù)測(cè)建模和分析技術(shù)(原書第3版)
- Hands-On Dashboard Development with QlikView
- Learning Linux Shell Scripting
- INSTANT Adobe Story Starter
- 深度學(xué)習(xí)原理與 TensorFlow實(shí)踐