- repo for deploy ML model
- Not focusing on enhance accuracy but on
deploying model
Building ML Powered App: Going from Idea to Product | TinyML: ML with TFLite on Android and Ultra-Low-Power Microcontrollers | Practical DL for Cloud, Mobile, and Edge |
Test here
branch website
- convert pytorch params and models to onnx format (with pytorch model)
- onnx file to
checkpoint meta
file of tensorflow - meta to tensorflow
protbuf
You can find whole the code here: Colab
branch onnx
- Medium: Running pytorch models in production
- Medium: Converting a Simple Deep Learning Model from PyTorch to TensorFlow
- Stackoverflow: How do I change the Signatures of my SavedModel without retraining the model?
- Migrate your tensorflow from 1.x to 2.x
- Serving tensorflow model
- ResearchGate: How to connect AWS to an android app?
- AWS: Android Sagemaker developer resources