doc/inference api #11332
Merged
doc/inference api #11332
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
panyx0718
reviewed
Jun 11, 2018
| }; | ||
|
|
||
| struct PaddleBuf { | ||
| void* data; // pointer to the data memory. |
There was a problem hiding this comment.
need to document the data layout. Is it row-major?
| The main interface is `PaddlePredictor`, there are following methods | ||
|
|
||
| - `bool Run(const std::vector<PaddleTensor>& inputs, std::vector<PaddleTensor>* output_data)` | ||
| - take inputs and output `output_data` |
There was a problem hiding this comment.
Document pointer ownership?
There was a problem hiding this comment.
The return is a unique_ptr, the ownership will transparently transfer.
luotao1
reviewed
Jun 11, 2018
| # Inference High-level APIs | ||
| This document describes the high-level inference APIs one can use to easily deploy a Paddle model for an application. | ||
|
|
||
| The APIs are described in `paddle_inference_api.h`, just one header file, and two libaries `libpaddle_fluid.so` and `libpaddle_fluid_api.so` are needed. |
There was a problem hiding this comment.
对api来说，提供一个libpaddle_fluid_api.so是否就可以了？
There was a problem hiding this comment.
可以编译进去吗，我之前发现不行，还需要 paddle_fluid.so
|
|
||
| ## PaddleTensor | ||
| Forget the hard-to-understand `LoDTensor`, | ||
| we provide the `PaddleTensor` data structure is to give a general tensor interface. |
|
|
||
| The data is stored in a continuous memory `PaddleBuf`, and tensor's data type is specified by a `PaddleDType`. | ||
| The `name` field is used to specify the name of input variable, | ||
| that is important when there are multiple inputs and need to distiuish which variable to set the content. |
There was a problem hiding this comment.
which variable to set the content 缺少谓语
| that is important when there are multiple inputs and need to distiuish which variable to set the content. | ||
|
|
||
| ## engine | ||
| The inference APIs has different underlying implementation, currently there are two valid engines: |
There was a problem hiding this comment.
have different underlying implementations
| ## engine | ||
| The inference APIs has different underlying implementation, currently there are two valid engines: | ||
|
|
||
| - the native engine, which is consists of the native operators and framework, |
| The inference APIs has different underlying implementation, currently there are two valid engines: | ||
|
|
||
| - the native engine, which is consists of the native operators and framework, | ||
| - the Anakin engine, which is a Anakin library embeded. |
|
|
||
| The native engine takes a native Paddle model as input, and supports any model that trained by Paddle. | ||
|
|
||
| The Anakin engine can only take the Anakin model as input(user need to manully transform the format first) and currently not all Paddle models are supported. |
There was a problem hiding this comment.
41行需要放到38行后面，43行需要放到39行后面么？
| - take inputs and output `output_data` | ||
| - `Clone` to clone a predictor from an existing one, with model parameter shared. | ||
|
|
||
| There is a factory method to help create a predictor |
| ## Reference | ||
|
|
||
| - [paddle_inference_api.h](./paddle_inference_api.h) | ||
| - [demos](./demo) |
There was a problem hiding this comment.
… feature/anakin-ci
panyx0718
reviewed
Jun 13, 2018
| The APIs are described in `paddle_inference_api.h`, just one header file, and two libaries `libpaddle_fluid.so` and `libpaddle_fluid_api.so` are needed. | ||
|
|
||
| ## PaddleTensor | ||
| Forget the hard-to-understand `LoDTensor`, |
panyx0718
approved these changes
Jun 21, 2018
reyoung
pushed a commit
to reyoung/Paddle
that referenced
this pull request
Jun 30, 2018
Superjomn
pushed a commit
that referenced
this pull request
Jun 30, 2018
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.