7.8.33. Coffee Bean Classification
Coffee bean quality classification from images using MobileNetV1 on MSPM0G5187 with NPU.
7.8.33.1. Overview
Task: Image Classification
Application: Coffee bean quality inspection
Dataset: coffee_bean_classification
Model: MobileNetV1_58k_NPU
Device: MSPM0G5187 (NPU-accelerated)
7.8.33.2. Device Support
Device |
Notes |
Configuration File |
|---|---|---|
|
MSPM0 with NPU |
|
7.8.33.3. Running the Example
cd tinyml-modelzoo
./run_tinyml_modelzoo.sh examples/coffee_bean_classification/config_MSPM0.yaml
cd tinyml-modelzoo
run_tinyml_modelzoo.bat examples\coffee_bean_classification\config_MSPM0.yaml
7.8.33.4. Configuration
common:
task_type: 'image_classification'
target_device: 'MSPM0G5187'
dataset:
dataset_name: 'coffee_bean_classification'
input_data_path: 'https://software-dl.ti.com/C2000/esd/mcu_ai/datasets/coffee_bean_classification.zip'
data_processing_feature_extraction:
feature_extraction_name: 'CoffeeBean_Default'
training:
model_name: 'MobileNetV1_58k_NPU'
training_epochs: 30
batch_size: 64
learning_rate: 0.1
quantization: 2
testing: {}
compilation: {}
7.8.33.5. Available Models
Model |
Parameters |
Description |
|---|---|---|
|
~58,000 |
MobileNetV1 optimized for NPU deployment |
7.8.33.6. System Components
Hardware
MSPM0G5187 microcontroller with integrated NPU
Camera interface for image capture
Software
Code Composer Studio (CCS) 12.x or later
MSPM0 SDK 2.10.04 or later
7.8.33.7. Next Steps
Browse similar examples: Machine Readable Code Classification, MNIST Image Classification
Deploy to device: NPU Device Deployment