TensorFlow is an end-to-end open source platform for machine learning. TensorFlow has a meaning, TensorFlow is made up of 2 words Tensor and Flow.
Tensor is the multidimensional array and flow is a graph of operation. Internally, TensorFlow implements machine learning algorithms as a graph of operation on multidimensional array.
A brief history
Why TensorFlow ?Tensor is the multidimensional array and flow is a graph of operation. Internally, TensorFlow implements machine learning algorithms as a graph of operation on multidimensional array.
A brief history
- Developed by Google Brain
- Released under Apache 2.0 license in Nov 2015
- Current stable version : API 1 version 1.14
- Popular GitHub repo with 129k+ stars
- Easy to build and deploy ML models
- Enables researchers to build state of the art ML models with Keras functional API and model subclassing API.
- Supports ML production anywhere - web, servers or edge devices irrespective of platform or language used for training and building.
TensorFlow has flexible architecture
Enables easy deployment across hardware platforms like
Enables easy deployment across hardware platforms like
- CPU
- GPU
- TPUs
- Desktops
- Servers
- Mobile devices
- Edge devices
TensorFlow everywhere
No comments:
Post a Comment