A lightweight image classification model with 0.13 MB size, 98x faster than MobileNetV3, fully optimized for ARM architecture.
- ✅ Ultra-small size (0.13 MB)
- ✅ High speed (2-5ms per inference)
- ✅ Trained on CIFAR-100 (100 classes)
- ✅ ARM-ready via TFLite
- ✅ Custom architecture built from scratch
| Metric | Value |
|---|---|
| Parameters | 43,124 |
| Model Size (TFLite) | 0.13 MB |
| Accuracy (CIFAR-100) | ~12% |
| Speed (ARM) | 98x faster than MobileNetV3 |
import tensorflow as tf
interpreter = tf.lite.Interpreter(model_path='model_v4_trained.tflite') interpreter.allocate_tensors()
input_details = interpreter.get_input_details() output_details = interpreter.get_output_details()
model_v4_trained.tflite- The optimized TFLite modelmodel_v4_trained.keras- The full Keras modeltest_model.py- Testing and benchmarking scriptrequirements.txt- Python dependencies
This project is submitted to the ARM AI Optimization Challenge.
MIT License