2.2 Image Classification
0. Introduction to [Image Classification]
The [Image Classification] model allows users to collect image data for multiple categories and create a custom AI model for image classification.
For example, if you want to create an [Image Classification] AI model that distinguishes between cats and dogs, you need to collect multiple images of both cats and dogs.
Once the model is trained, it will classify new images by determining which category they belong to.
Now, let's explore how to create an [Image Classification] model using HUENIT OS.
1. How to Train the [Image Classification] Model
When launching [Image Classification] for the first time, a white square with a crosshair will appear on the screen.
Place the object inside the white square and tap the touchscreen to start training.
The [Image Classification] model can support up to 4 categories (IDs), with a maximum of 5 images per category.
Training Multiple Categories
Once image collection for the first category is complete, press and hold the AI Camera button to open a pop-up.
Click [Train Next Model] to proceed.
The number of trained IDs will be displayed, and a new white square will appear on the screen.
Place a new object inside the square and tap the screen to continue training the next category.
2. Completing Model Training
Once all necessary data has been collected for [Image Classification], press and hold the AI Camera button for 2 seconds to complete training.
⚠ Important: If the button is not held down long enough, the system will return to the AI Model Selection screen, requiring the model to be retrained from the beginning.
When the [End Training] pop-up appears, press the button to confirm and finalize training.
✅ After completing training:
You can now test your custom [Image Classification] model.
Check whether images are correctly classified into their trained categories and if the probability scores meet your expectations.
3. How to Save a Trained Model
Once the model has been successfully trained and verified, it can be saved in HUENIT OS. This allows the model to be used later in HUENIT LAB (Software).
Press and hold the button on the AI Camera after training is complete.
Click [Save Model] to store the trained model in HUENIT OS.
If the training results are unsatisfactory, click [Delete & Retrain] to restart the training process
In [Save Model], choose a storage slot except for the 6th option (Not Saveable).
"Empty Space" indicates an available slot with no saved model.
Slots with existing names already contain trained AI models.
⚠ Warning: Saving a new model in an occupied slot will overwrite and delete the existing model.
Last updated