Personal tools


Technical University of Munich_031422A
[Technical University of Munich]

- Overview

Anaconda is a free, open-source distribution of Python and R programming languages. It's used for scientific computing, such as data science, machine learning, and predictive analytics. Anaconda can help with:

  • Package management: Anaconda can simplify package management and deployment.
  • Creating environments: Anaconda can help create an environment for many different versions of Python and package versions.
  • Installing, removing, and upgrading packages: Anaconda can be used to install, remove, and upgrade packages in project environments.
  • Deploying projects: Anaconda can be used to deploy projects with a few mouse clicks.

Anaconda's distribution includes data-science packages for Windows, Linux, and macOS. It also supports tools like Python in Excel and advanced data platforms.


- Installing Anaconda Python for TensorFlow

If you want to use Anaconda, follow these steps:

Step 1: Download and install Anaconda.

Step 2: Open a terminal application and use the default bash shell.

Step 3: Create a new environment for TensorFlow:

        conda create -n tf python=3.6

Step 4: Activate the environment:

       conda activate tf

Step 5: Install TensorFlow:

       pip install tensorflow

Step 6: Verify the installation:

       python -c "import tensorflow as tf; print(tf.version.VERSION)"

Step 7: This should print the version of TensorFlow that is installed.


- Training A Model in Python Tensorflow

Here are the steps on how to train a model in Python Tensorflow:

Step 1: Load the data
The first step is to load the data that you want to train the model on. You can use the tensorflow.keras.utils.get_file() function to load the data.

Step 2: Split the data into training and test sets
Once the data is loaded, you need to split it into training and test sets. The training set will be used to train the model, and the test set will be used to evaluate the model's performance. You can use the tensorflow.keras.utils.train_test_split() function to split the data.

Step 3: Choose a model
Next, you need to choose a model that you want to train. There are many different models available, so you need to choose one that is appropriate for the task that you are trying to solve.

Step 4: Train the model
Once you have chosen a model, you need to train it on the training data. You can use the method to train the model.

Step 5: Evaluate the model
Once the model is trained, you need to evaluate its performance on the test set. You can use the tensorflow.keras.Model.evaluate() method to evaluate the model.

Step 6: Deploy the model
Once the model is trained and evaluated, you can deploy it to production. This means making the model available to users so that they can use it to make predictions.

[More to come ...]

Document Actions