[Amira 3D, Avizo 3D]
Note: This article applies only to Amira/Avizo version 2024.1 and earlier.
Starting with version 2024.2, the deep learning packages are automatically installed within the default Python environment during installation. As a result, all deep learning features are available without requiring any manual installation within the product.
Context
When using AI features such as Deep Learning Segmentation or Noise2Void, you must first install the appropriate Deep Learning Python environment for your software version.
The steps below describe how to set up this environment.
Prerequisites
- Installing a Python environment for Deep Learning does not require a specific license. However, some AI features may require additional editions, such as 3D Pro.
Refer to your software documentation to verify which extensions are required for the features you intend to use. - If your workstation does not have access to the internet, please refer to the link below or the in-app documentation for alternative offline installation steps.
Process
A video demonstration of this procedure is available on the Xtra Library for Thermo Scientific Amira, Avizo and PerGeos Software | How to Install the Deep Learning Python Environment (thermofisher.com).
1. Start Amira or Avizo. From the tab menu in the upper left, select Project to open the Project workroom.
2. Open the Python menu at the top of the interface, then select Environment > Create New Environment.
3. In the pop-up window, enter a desired name for the new environment (for example, deep_learning_environment).
4. Check the box Install Deep Learning Packages.
5. Click OK to start the installation.
6. A new window will open, and the environment will be downloaded and installed.
This process may take several minutes.
7. Open the Python menu again, click Environment, and select the environment you have created.
8. Restart the software.
9. The new Deep Learning environment is now active and ready to use.
Related Link
For additional guidance on installing the Deep Learning Package (both online and offline), refer to the tutorial available in the Xtra Library: