PaddlePaddle / Mobile

Embedded and Mobile Deployment

Mobile

Here mainly describes how to deploy PaddlePaddle to the mobile end, as well as some deployment optimization methods and some benchmark.

Build PaddlePaddle

• Build PaddlePaddle for Android
• Build PaddlePaddle for IOS
• Build PaddlePaddle for Raspberry Pi3
• Build PaddlePaddle for NVIDIA Driver PX2

Demo

• A command-line inference demo.
• iOS demo of PDCamera

Deployment optimization methods

Optimization for the library:

• How to build PaddlePaddle mobile inference library with minimum size.

Optimization for models：

• Merge batch normalization layers
• Compress the model based on rounding
• Merge model's config and parameters
• How to deploy int8 model in mobile inference with PaddlePaddle

Model compression

• How to use pruning to train smaller model

PaddlePaddle mobile benchmark

• Benchmark of Mobilenet
• Benchmark of ENet
• Benchmark of DepthwiseConvolution

This tutorial is contributed by PaddlePaddle and licensed under the Apache-2.0 license.