Detect Products on Retail Shelves with an Optimized Algorithm

Improve your retail execution scenarios that identify products on shelves. Now you can use an optimized algorithm to create a model with detection accuracy (mAP) that’s better for a retail use case. And it still has the same functionality as a model created using the standard detection algorithm.

Where: This change applies to Lightning Experience, Salesforce Classic, and all versions of the Salesforce app in Group, Professional, Enterprise, Performance, Unlimited, Developer, and Contact Manager editions.

How: To use the retail execution algorithm, first create a dataset that has a type of image-detection. Then when you train the dataset to create a model, you specify an algorithm of retail-execution. The cURL command is as follows.
curl -X POST -H "Authorization: <TOKEN>" -H "Cache-Control: no-cache" -H "Content-Type: multipart/form-data" -F "name=Alpine Retail Model" -F "datasetId=<DATASET_ID>" -F "algorithm=retail-execution" https://api.einstein.ai/v2/vision/train
These calls take the algorithm parameter.
  • Train a model—POST /v2/vision/train
  • Retrain a model—POST /v2/vision/retrain