Changes

Jump to navigation Jump to search
512 bytes added ,  13:27, 16 May 2022
no edit summary
Line 1: Line 1:  
=== Summary ===
 
=== Summary ===
[https://dataforgood.fr/ DataForGood] is an association that mobilize tech to help citizen projects.
+
[https://dataforgood.fr/ DataForGood] is a French "association" that mobilizes tech to help citizen projects. We are part of [https://dataforgood.fr/projects/tags/saison-10 season #10], this is our 4th season.
    
Main focus this year is on using machine learning to automatically categorize products so as to enable computing Nutri-Score and Éco-Score.
 
Main focus this year is on using machine learning to automatically categorize products so as to enable computing Nutri-Score and Éco-Score.
Line 9: Line 9:  
'''Expected outcomes''': Have a new machine learning model, ready to deploy in production:
 
'''Expected outcomes''': Have a new machine learning model, ready to deploy in production:
   −
* That use more features to predict category: OCR data, nutritional information, eventually images or any feature
+
* That uses more features to predict category: OCR data, nutritional information, eventually images or any feature.
* Precision should be very high to be able to apply category automatically but the model should use it's confidence to ask for user when needed
+
* Precision should be very high to be able to apply category automatically but the model should use its confidence to ask the user whenever needed.
   −
'''Impact:''' augment massively the number of Eco-Score and Nutri-Score we are able to provide on the platform.
+
'''Impact:''' massively increase the number of Eco-Scores and Nutri-Scores we are able to provide on the Open Food Facts platform.
   −
Categorization is also important in many way, for example to compare nutrition data with other products of same category (rank among category).
+
Categorization is also important in many ways, for example to compare nutrition data with other products of same category (rank within a category).
    
'''Timeline''':
 
'''Timeline''':
   −
* 2022-03-12 launch at Data for good launch event
+
* 2022-03-12: Data 4 Good kickoff event
* 2022-03-16 project kickoff (first working session)
+
* 2022-03-16: Actual project kickoff (first working session)
* 2022-06-12 theoretical end of the project
+
* 2022-06-12: Planned end of the project (Data 4 Good Demo Day)
    
=== Resources / Contributing ===
 
=== Resources / Contributing ===
The weekly meeting for this project is every Wednesday 20.00. We have a meeting room at https://meet.jit.si/DFG-OPENFOODFACTS
+
'''There is a spreadsheet to have our coordinates''' see on slack channel.
   −
You should also join data-for-good slack. To be invited, use https://dataforgood.fr/join/
+
The weekly meeting for this project is Wednesdays at 20.00 (French time). We use Google Meet.
   −
'''Main repos'''
+
'''Main information :''' [https://docs.google.com/document/d/13LnTBoBXFWyGGKlGKgmo-utkmiMkapzkVlg39uLKsH4/edit Minutes of the meetings (google docs)]
   −
* [https://github.com/openfoodfacts/robotoff/ robotoff]: Our program that handles predictions / insights: good to read : https://openfoodfacts.github.io/robotoff/introduction/architecture/
+
You should also join the Open Food Facts and Data 4 Good slacks. To be invited, use https://dataforgood.fr/join/ and https://slack.openfoodfacts.org
* [https://github.com/openfoodfacts/robotoff-ann/ robotoff-ann] is a complement to robotoff that focus on logo detection and embedding (we use nearest neighbors to classify logos)  
+
 
* last training of category model (using only title and ingredients): https://github.com/kulizhsy/off-category-classification
+
'''Main GitHub repositories'''
 +
 
 +
* '''Project where development happens''' : https://github.com/openfoodfacts/off-category-classification
 +
* [https://github.com/openfoodfacts/robotoff/ robotoff]: Robotoff, our program that handles predictions / insights
 +
  * good to read : https://openfoodfacts.github.io/robotoff/introduction/architecture/
 +
* [https://github.com/openfoodfacts/robotoff-ann/ robotoff-ann] is a complement to robotoff that focuses on logo detection and embedding (we use nearest neighbors to classify logos)  
 
* All trained models are published as "releases" on https://github.com/openfoodfacts/openfoodfacts-ai
 
* All trained models are published as "releases" on https://github.com/openfoodfacts/openfoodfacts-ai
* [https://openfoodfacts.github.io/api-documentation/ openfoodfacts API documentation]
+
* [https://openfoodfacts.github.io/api-documentation/ Open Food Facts API documentation]
    
=== Archives ===
 
=== Archives ===
   −
* Data4Good launch presentation: '''FIXME'''
+
* [https://docs.google.com/presentation/d/1fMN4di6AN1vz4sC3HYsA1PTya0mDGJYZ9htQYyqkLZQ/edit Data4Good launch presentation (Google Docs)]
 
[[Category:Project]]
 
[[Category:Project]]
 
[[Category:Robotoff]]
 
[[Category:Robotoff]]
199

edits

Navigation menu