Distinguish Leopards vs Jaguars Using ModelArts AutoML
This guide walks you through configuring Huawei Cloud ModelArts, creating an AutoML image‑classification project, labeling cat and leopard photos, training a model, deploying it as an online service, and testing predictions to accurately differentiate between leopards and jaguars.
Service Configuration
Before using ModelArts, add an access key to authorize jobs to access Huawei Cloud OBS storage.
1. Generate an access key in the "User Information > Manage My Credentials" page; the key file will be downloaded.
2. Set the global ModelArts configuration by adding the access key on the ModelArts service page to enable OBS access.
Create AutoML Project
After configuring the service, you can build your own application.
1. Create an OBS bucket named ai-mission1-cat and a folder /automl/cat inside it.
2. Open the ModelArts console, click the left‑navigation "AutoML", and enter the AutoML interface.
3. Click the "Image Classification" button to create a project, name it (e.g., exeML-cat ), and set the training data path to /ai-mission1-cat/automl/cat/ . Then create the project.
Image Annotation
1. Upload images: after the project is created, you can batch‑upload multiple images for training.
2. Annotate images: go to the "Unlabeled" page, select a group of images of the same class, assign a label (e.g., "leopard"); if the label does not exist, type it manually.
3. Verify labels: after labeling all images, go to the "Labeled" page to see all tags and the number of images per tag.
Model Training
In the "Data Annotation" page, set the training duration to 0.1 (shorter training may reduce accuracy) and click "Start Training".
Model Deployment
Wait for training to finish (typically under 6 minutes). The model accuracy is shown; with only lion, tiger, cat, and leopard classes the accuracy reaches 100%, but adding jaguar and leopard reduces it to about 91% due to similarity.
Click the "Deploy" button to publish the model as an online service.
Service Testing
After deployment succeeds, click "Upload Local Image" and select a jaguar picture.
Click the "Predict" button. The result shows a 62.8% probability of being a jaguar. Re‑run with a different pose to see consistent predictions, demonstrating that the AI can successfully distinguish jaguars from leopards.
Huawei Cloud Developer Alliance
The Huawei Cloud Developer Alliance creates a tech sharing platform for developers and partners, gathering Huawei Cloud product knowledge, event updates, expert talks, and more. Together we continuously innovate to build the cloud foundation of an intelligent world.
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.
