
If you’re fine with using the CPU to train your neural network, your installation is done. To install TensorFlow for CPU and GPU processors, run the following command: pip install tensorflow

Run the following command to ensure that the latest version of pip is installed: pip install -upgrade pip Output should be similar to: Python 3.8.2 You can determine the version of Python installed on your computer by running the following command: python3 -version TensorFlow and Keras require Python 3.6+ (Python 3.8 requires TensorFlow 2.2+), and the latest version of pip. GPU – most high end computers feature a separate Graphics Processing Unit (GPU) from Nvidia or AMD that offer training speeds much faster than CPUs, but not as fast as TPUs.TPU – only available currently on Google’s Colaboratory ( Colab ) platform, Tensor Processing Units (TPUs) offer the highest training speeds.CPU – any modern computer can run this version, but it offers the slowest training speeds.Each platform has different hardware requirements and offers different performance: TensorFlow can be run on three different processor platforms, with the main difference being the speed at which your neural network will be trained. The simplest way to install TensorFlow is to install the binary version using one of the official releases on the Python Package Index (PyPI). When you install TensorFlow 2.0+, Keras will be automatically installed, as well. Instead of pip installing each package separately, the recommended approach is to install Keras as part of the TensorFlow installation.


Keras and TensorFlow are open source Python libraries for working with neural networks, creating machine learning models and performing deep learning.
