Fiji's Update Site for deepImageJ 1

Please, add the update site URL manually:

I. In Fiji/ImageJ, click on "Help" > "Update...".

II. Once the ImageJ Updater pops up, click on "Manage update sites" > "Add update site".

III. There you can write the name ("DeepImageJ") and the URL given (https://sites.imagej.net/DeepImageJ/).

Manual installation of deepImageJ

Download the dependencies and the plugin given in the following links.

• DeepImageJ 3.0.3

• Dependencies 3.0.3

Place DeepImageJ_X.X.X.jar inside the 'plugins' folder of the 'ImageJ2/Fiji' directory.

Unzip the dependencies_xxx.zip file and copy all the .jar files in the 'jars' folder inside the 'ImageJ2/Fiji' directory. If we already have other versions of the dependencies inside the 'jars' folder, the plugin might not function correctly. For a quick test, if possible, we suggest to remove the duplicated dependencies and leave the ones we provide.

PyTorch models for Windows: please make sure that you have Visual Studio installed:

• Install Visual Studio 2019 redistributable.
• Install Visual Studio 2019.

Detailed installation instructions and software compatibility

• DeepImageJ's Wiki

GPU connection (optional and only if a GPU is available)

Requirements:

• TensorFlow: CUDA 9.0 (TensorFlow 1.12) / CUDA 10.0 (TensorFlow 1.15) and corresponding CUDnn and drivers.
• PyTorch: CUDA 10.2 is accepted, BUT having other CUDA versions installed might be source of conflicts.
  • In Windows, if any version other than CUDA 10.2 is installed, the plugin will fail to load the model (link to the bug issue in GitHub).
  • If deepImageJ is not able to load a PyTorch model using the GPU, remove CUDA_PATH (if exists) from your environment variables and make sure that your PATH does not include any directory or file with the words “Nvidia” or “CUDA”. For that go to 'Edit the system environment variables' or 'Edit environment variables for your account', then click on 'Environment variables' and finally check the 'Path' and 'CUDA_PATH' variables (note that Windows is not case sensitive so they might be written and 'PATH' or 'path').

Detailed information for the GPU installation is given here.