CSBDeep

Revision as of 05:55, 11 December 2018 by Frauzufall (talk | contribs) (Created page with "{{Component | project = CSBDresden | name = CSBDeep Fiji Plugin | url = https://imagej.net/CSBDeep | source = {{GitHub | org=CSBDeep | repo=CSBDeep_fiji | tag=csbdeep-0.3.3}}...")

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
CSBDeep Fiji Plugin
Project CSBDresden
URL https://imagej.net/CSBDeep
Source on GitHub
License Simplified BSD License
Release 0.3.3
Date Tue Dec 11 00:00:00 CDT 2018
Development status Unstable
Support status Active
Team
Founders Deborah Schmidt
Leads Deborah Schmidt, Benjamin Wilhelm, Florian Jug
Developers Deborah Schmidt, Benjamin Wilhelm, Florian Jug
Debuggers Deborah Schmidt, Benjamin Wilhelm
Reviewers Deborah Schmidt, Benjamin Wilhelm
Support Deborah Schmidt, Benjamin Wilhelm
Maintainers Tobias Pietzsch, Benjamin Wilhelm


Install

ImageJ update site

The CSBDeep plugin can be installed from the ImageJ update site [1]. See the CSBDeep Wiki Pages for more details.

From source

  1. Clone this repository.
  2. Run the following command from inside the repo:

mvn -Dimagej.app.directory=/path/to/Fiji.app/ -Ddelete.other.versions=true

Run demos

  1. Download the exemplary image data
  2. Open Fiji.
  3. Open an example image, e.g. `tribolium.tif`.
  4. Run the plugin via `Plugins > CSBDeep > Demo`.
  5. Run the plugin by pressing `Ok`.

If all goes well, an image will be displayed representing the result of the model execution.

See the CSBDeep Wiki Pages for more details.

Run your own model

  1. Use the python code to train your network with your data. Export it as ZIP.
  2. Open Fiji.
  3. Open an image.
  4. Run the plugin for any network via `Plugins > CSBDeep > Run your network`.
  5. Load your exported network by pressing `Browse` on the `Import model (.zip)` line.
  6. Run the plugin by pressing `Ok`.

If all goes well, an image will be displayed representing the result of the model execution.

See the CSBDeep Wiki Page for more details.

Develop

Code Style

If you use eclipse you can import our code formatter `doc/eclipse-code-formatter.xml`, code cleanup (`doc/eclipse-code-clean-up.xml`) and import order (`eclipse-import-order.importorder`) settings.

GPU support

For GPU support we load the TensorFlow JNI with GPU support manually when a command is initialized. This means that the GPU version of the TensorFLow JNI must be accessible in the java library path (For example `Fiji.app/lib/linux64` in a Fiji installation).

See the according CSBDeep Wiki page for a detailed installation guide.

Muliple GPUs

See the according CSBDeep Wiki page.

License

This project is licensed under the BSD 2-clause "Simplified" License -- see the LICENSE.txt file for details.