Commit 29cc533f authored by Nicolas Elie's avatar Nicolas Elie
Browse files

Mettre à jour README.md

parent 44f03277

README.md

+17 −4
Changes for README.md: 17 added lines, 4 removed lines.
Original line number Diff line number Diff line
@@ -25,13 +25,24 @@ The project is mainly based on the Stardist method: https://github.com/stardist/ 
The proposed installation uses Conda environment: https://docs.conda.io/en/latest/.



1. Install conda

2. Download project : git clone git@git.unicaen.fr:nicolas.elie/redpol-open.git

You can install an environment via the provided environment file(s): \_installationEnv.\_yml.

3. In you work directory : <span dir="">conda env create -f</span> \_installationEnv.\_yml

2. Download project : 

> git clone https://git.unicaen.fr/nicolas.elie/redpol-open.git (~ 2.5 Go)

3. cd redpol-open/

4. You can install an environment via the provided environment file(s): installationEnv.yml.

> <span dir="">conda env create -f</span> installationEnv.yml



#### To test the execution of the AnalyzeSequence.ipynb program



The AnalyzeSequence.ipnyb program allows to use our Stardist model on each image of the vsi file.



The program process a detection and classification of chromatophores and save a file results.



In this project, a example file is given : 'Examples/Process_13.vsi' as well as our model Stardist Model :  'models/stardist_multiclass'



To test program :



Run _AnalyzeSequence.ipnyb_ program on conda environment

> jupyter nbconvert --execute --clear-output _AnalyzeSequence.ipynb



#### To build a new model
@@ -44,9 +55,11 @@ INSERT UN EXEMPLE IMAGE QUAPTH AVEC CONTOURS et CLASSES 


On your images, annotate the objects that interest you. If you have categories, remember to declare the different classes. For details on how to use Qupath, see the documentation on their site.



2. Once your annotations are done, use the script "_Export Annotations gson.groovy_" to export the annotations as a json file.

2. Once your annotations are done, use the script "_Export Annotations gson.groovy_" to export the annotations as a json file in Qupath.

3. Then use the python program "_JSON_Qupath_to_ImageLabel.ipynb_" which will allow to format the images and annotations so that they can be used by the program "_Model_Build.ipynb_." This program is directly from an example provided on the github Stardist repository.



> jupyter nbconvert --execute --clear-output JSON_Qupath_to_ImageLabel.ipynb



> **_Be careful, for the program to work, you need a compatible GPU graphics card._**



4. The program "_AnalyzeSequence.ipnyb_" can then be used by designating your own model in the program code.