m53297601
/
Paddle
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
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.
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'be2e3e67d9'
${ noResults }
Paddle/paddle/fluid/inference/api
History
silingtong123 45c1e7bb7b
add prediction demo and script on windows (#21248) 		6 years ago
..
demo_ci add prediction demo and script on windows (#21248) 6 years ago
details zerocopytensor support uint8, analysis config support profile, analysis predictor support GetInputTensorShape, test=develop (#19822) 6 years ago
CMakeLists.txt Determine whether to copy and link inference lib by ON_INFER (#20931) 6 years ago
README.md Combine Inference Analysis with IR (#13914) 7 years ago
analysis_config.cc add DisableGlogInfo() to AnalysisConfig, test=develop (#20581) 6 years ago
analysis_predictor.cc Bug Fix: Paddle-TRT cannot handle adaptive pooling in pool2d op converter and "num" attribute in split op converter (#20733) 6 years ago
analysis_predictor.h update operator compatible info, test=develop (#19978) 6 years ago
analysis_predictor_tester.cc fix analysis_predictor ci, test=release/1.6 (#20141) 6 years ago
api.cc fix several security bugs reported by security team (#18831) 6 years ago
api_anakin_engine.cc Ensure backward compatibility with the anakin interface, test=develop (#20691) 6 years ago
api_anakin_engine.h support MLU nums, test=develop (#19372) 6 years ago
api_impl.cc Fix/gcc 4.8 ubt link error (#18558) 6 years ago
api_impl.h make clone thread safe (#15363) 7 years ago
api_impl_tester.cc paddle::framework::vectorize() templatization [PART3] (#19643) 6 years ago
api_tester.cc add version support (#15469) 7 years ago
helper.cc rollback paddle_inference_helper.h to helper.h 7 years ago
helper.h add local user data conversion into full_pascalvoc_test_preprocess.py (#19283) 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 Add generalized Conv+Activation MKLDNN fuse pass creation Part2 (#19237) 6 years ago
mkldnn_quantizer.h Reset DeviceContext after quantization warmup (#18182) 7 years ago
mkldnn_quantizer_config.cc Add transpose2 INT8 for mkl-dnn (#19424) 6 years ago
paddle_anakin_config.h Support Bitmain Anakin (#18542) 6 years ago
paddle_analysis_config.h add DisableGlogInfo() to AnalysisConfig, test=develop (#20581) 6 years ago
paddle_api.h zerocopytensor support uint8, analysis config support profile, analysis predictor support GetInputTensorShape, test=develop (#19822) 6 years ago
paddle_inference_api.h Remove the obsolete cmake options (#18481) 6 years ago
paddle_mkldnn_quantizer_config.h C-API quantization core 2 (#16396) 7 years ago
paddle_pass_builder.cc TRT int8: refine trt int8 for dynamic range set (#21112) 6 years ago
paddle_pass_builder.h A a pass to enable the use of cudnn (#19346) 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.