🚀 This Flutter app demonstrates image classification using multiple MobileNet V1 models (0.75_224, 0.5_224, and 0.25_224) directly on your smartphone.
MobileNet is a family of efficient convolutional neural networks designed for mobile and embedded vision applications. This app integrates several MobileNet versions to allow:
- 📷 On-device image classification (no internet needed)
- ⚖️ Comparison of accuracy vs. speed across MobileNet variants
- 📱 Real-time deep learning optimized for mobile hardware
Whether you're a developer, researcher, or AI enthusiast, this app helps explore lightweight deep learning models in real-world scenarios.
You can directly install the app by downloading the APK from this repository:
👉 Download SmartClassifier APK
📌 Note: The app is currently undergoing review for release on the Google Play Store. Once published, the Play Store link will be added here.
AppVideo.mp4
- MobileNetV1 0.75_224
- MobileNetV1 0.5_224
- MobileNetV1 0.25_224
The MobileNet models used in this app output predictions based on the ImageNet dataset, which includes 1,000 object classes.
These models are optimized for inference on mobile devices and run entirely offline.
MIT License.
Feel free to open issues or pull requests if you’d like to improve this project or add features.
📬 For questions or collaboration, contact me at: aminnassiri63@gmail.com