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
nhzlx d065b5bf2b
Anakin ssd support
6 years ago
..
demo_ci fix cdn issue, test=develop (#16423) 6 years ago
details fix comments 6 years ago
CMakeLists.txt C-API quantization core 2 (#16396) 6 years ago
README.md Combine Inference Analysis with IR (#13914) 6 years ago
analysis_config.cc C-API quantization core 2 (#16396) 6 years ago
analysis_predictor.cc Anakin ssd support 6 years ago
analysis_predictor.h C-API quantization core 2 (#16396) 6 years ago
analysis_predictor_tester.cc C-API quantization core 2 (#16396) 6 years ago
api.cc Add INT32 support. INT32 in last switch case 6 years ago
api_anakin_engine.cc Because anakin do NOT use glog, so we revert anakin related change 6 years ago
api_anakin_engine.h refactor inference analysis api (#14634) 6 years ago
api_impl.cc Add INT32 support. INT32 in last switch case 6 years ago
api_impl.h make clone thread safe (#15363) 6 years ago
api_impl_tester.cc Add INT32 support. INT32 in last switch case 6 years ago
api_tester.cc add version support (#15469) 6 years ago
helper.cc rollback paddle_inference_helper.h to helper.h 6 years ago
helper.h Merge branch 'develop' into zero_copy 6 years ago
high_level_api.md fix dead link in high_level_api.md 7 years ago
high_level_api_cn.md fix some teeny mistakes 7 years ago
mkldnn_quantizer.cc C-API quantization core 2 (#16396) 6 years ago
mkldnn_quantizer.h C-API quantization core 2 (#16396) 6 years ago
mkldnn_quantizer_config.cc C-API quantization core 2 (#16396) 6 years ago
paddle_anakin_config.h Combine Inference Analysis with IR (#13914) 6 years ago
paddle_analysis_config.h C-API quantization core 2 (#16396) 6 years ago
paddle_api.h fix comments 6 years ago
paddle_inference_api.h refactor inference analysis api (#14634) 6 years ago
paddle_mkldnn_quantizer_config.h C-API quantization core 2 (#16396) 6 years ago
paddle_pass_builder.cc Anakin ssd support 6 years ago
paddle_pass_builder.h Refine default MKL-DNN Pass order (#16490) 6 years ago

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.