Now we will install Python libraries used for Deep Learning, specifically: TensorFlow, and Keras.
TensorFlow is a Python library developed and maintained by Google. You can implement many powerful machine learning and Deep Learning architectures in custom models and applications using TensorFlow. To know more visit https://www.tensorflow.org/.
Install the TensorFlow Deep Learning library (all except Windows) by typing:
conda install -c conda-forge tensorflow
Alternatively, you may choose to install using pip and a specific version of TensorFlow for your platform:
pip install tensorflow==1.6
See the installation instructions for TensorFlow (https://www.tensorflow.org/get_started/os_setup#anaconda_installation).
Now we will install keras using the following command:
pip install keras
To validate the environment and the version of the packages, create the following script which will print the version numbers of each library:
# Import the tensorflow library
import tensorflow
# Import the keras library
import keras
print('tensorflow: %s' % tensorflow.__version__)
print('keras: %s' % keras.__version__)
Save the script to a file dl_versions.py. Run the script by typing:
python dl_version.py
You should see output like:
tensorflow: 1.6.0
Using TensorFlow backend.
keras: 2.1.5
Voila!!! Now we are ready with Python development environment to write awesome Deep Learning applications in our local.