Skip to content
BENIBIX Learn

TensorFlow

AI📈 Machine LearningML Frameworks

Also known as TensorFlow Library, tf.keras

A free tool to build and train neural networks, then ship them to apps.

Think of it like

It is like a factory line for brains. It builds them and ships them to many places.

Example

Google released TensorFlow as open source in November 2015. Jack uses it to put a small photo model inside a phone app.

Why it matters

It is strong at shipping models to phones, browsers and servers. Lots of working systems depend on it.

Definition

TensorFlow is a free library to build, train and run neural networks. Most people use it from Python through Keras, its simple way to stack layers. It has tools to run the finished model on phones, in web pages and on servers. It runs on CPUs, graphics cards and special AI chips. Many companies still run older models built with it.

Example code

python
import tensorflow as tf
model = tf.keras.Sequential([tf.keras.layers.Dense(64, activation="relu"), tf.keras.layers.Dense(1)])
model.compile(optimizer="adam", loss="mse")
Keras stacks two layers. Then the model is set to train with Adam.
TensorFlow sits on the side for neural networks, next to PyTorch.

Common mistake

Thinking Keras and TensorFlow are rivals. Keras is the simple layer you use on top of it.

Key takeaways

  1. 1
    Build and ship. Train it, then run it anywhere.
  2. 2
    Keras on top. The simple way to stack layers.
  3. 3
    Many chips. CPU, graphics card or AI chip.

Learn it properly