You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Paddle/paddle/fluid/inference/api
Michał Gallus 7023a86c3a
Fix Pooling output scale (#18186)
6 years ago
..
demo_ci fix package generation for inference test=develop (#18220) 6 years ago
details
CMakeLists.txt Update the Anakin interfaces for content-dnn and MLU (#17890) 6 years ago
README.md
analysis_config.cc
analysis_predictor.cc
analysis_predictor.h
analysis_predictor_tester.cc
api.cc
api_anakin_engine.cc Update the Anakin interfaces for content-dnn and MLU (#17890) 6 years ago
api_anakin_engine.h modify the access level of anakin engine (#18015) 6 years ago
api_impl.cc
api_impl.h
api_impl_tester.cc
api_tester.cc
helper.cc
helper.h Update the Anakin interfaces for content-dnn and MLU (#17890) 6 years ago
high_level_api.md
high_level_api_cn.md
mkldnn_quantizer.cc Fix Pooling output scale (#18186) 6 years ago
mkldnn_quantizer.h Reset DeviceContext after quantization warmup (#18182) 6 years ago
mkldnn_quantizer_config.cc add int8 mkldnn prior_box (#17242) 6 years ago
paddle_anakin_config.h Update the Anakin interfaces for content-dnn and MLU (#17890) 6 years ago
paddle_analysis_config.h
paddle_api.h
paddle_inference_api.h Update the Anakin interfaces for content-dnn and MLU (#17890) 6 years ago
paddle_mkldnn_quantizer_config.h
paddle_pass_builder.cc
paddle_pass_builder.h

README.md

Embed Paddle Inference in Your Application

Paddle inference offers the APIs in C and C++ languages.

You can easily deploy a model trained by Paddle following the steps as below:

  1. Optimize the native model;
  2. Write some codes for deployment.

The APIs

All the released APIs are located in the paddle_inference_api.h header file. The stable APIs are wrapped by namespace paddle, the unstable APIs are protected by namespace paddle::contrib.

Write some codes

Read paddle_inference_api.h for more information.