Problem Statement
The applications of Deep Neural Nets is on a roll. Whether it is healthcare, transportation, or retail, companies across all industries are excited about investing in building intelligent solutions. Meanwhile, let’s hope human intelligence remains uncontested.
In this challenge, you will help one of the largest retailers in Germany improve their inventory-management process in its Food and Groceries business. The company is looking for intelligent solutions that can reduce the amount of human effort in its warehouse and retail outlets.
A solution such as a powerful image classifier can help the company track shelf inventory, categorize products, record product volume etc.
You are required to predict the category of each product.
Download Dataset
Data description
The zipped file contains images of training and testing set. The train data has 3215 product images. The test data has 1732 product images.
| Variable | Description |
|---|---|
| image_id | unique id of image |
| label | product category (target) |
Submission
A participant has to submit a .csv file containing the image_id and labels in the .csv format. Check the sample submission file for the format.
image_id,label
test_1000a, candy
test_1000b, water
test_1000c, coffee
test_1000d, water
test_1001a, rice
Evaluation metric
Each submission will be evaluated based on weighted F1 score. Higher the better. To know more, read here.
Scripts
- Keras CNN Starter - Click Here
- Load Data on IBM Data Science Platform - Click Here
- Transfer Learning with InceptionVGG ( ~0.59) - Click Here
Update
- [Sep 04, 17:54] Kindly make sure your pre-trained models are publicly available.
- [Sep 14, 18:00] For all your IBM DSX related queries, please ask on this slack channel: Slack Channel. You can get your slack invite here.
