init Inference top APIs #10549

Superjomn · 2018-05-10T03:19:39Z

With a README.md with some description/plan of how to use the APIs.

luotao1 · 2018-05-10T06:05:30Z

contrib/inference/README.md

@@ -0,0 +1,27 @@
+# Embed Paddle Inference in Your Application
+
+Paddle inference offers the APIs in `C` and `C++` languages.


这里有必要分C和C++两个么？目前只是C++ api，能否先只写C++ api？

嗯，另外加一个 c api，估计另外一个pr里

c如果暂时不需要就先别写了

luotao1 · 2018-05-10T06:05:52Z

contrib/inference/README.md

+
+Paddle inference offers the APIs in `C` and `C++` languages.
+
+One can easily deploy a model trained by Paddle following the steps as below:


Paddle->PaddlePaddle

luotao1 · 2018-05-10T06:12:07Z

contrib/inference/README.md

+
+## Optimize the native Fluid Model
+
+The native model that get from the training phase needs to be optimized for that.


我们是拿了train阶段的save_inference_model，这样会加入feed和fetch op，并做了一定的剪裁优化。如果直接拿train阶段的模型，没有feed和fetch op，就跑不了了。

这里提到的策略1,2,3,应该在save_inference_model的时候就做了。
这里是否应该只提供一些额外的优化策略，比如third-party engine, fuse operators等

对，这里只是解释这个工具的必要性。

luotao1 · 2018-05-10T06:14:58Z

contrib/inference/paddle_inference_api.h

+           const std::vector<std::vector<int>>& input_shapes,
+           const std::vector<std::vector<int>>& output_shapes,
+           const std::vector<std::vector<float>>& input_data,
+           std::vector<std::vector<float>>* output_data);


这个接口，对NLP的已经不适用了。是否考虑接口中直接使用LoDTensor。
因为用户的数据格式千变万化，让用户自己转成LoDTensor比较合理。我们也可以给出一些转换的工具或函数，但run的接口里保持使用LoDTensor。

bool Run(const std::vector<LoDTensor>& input, std::vector<LoDTensor>* output);

inputs和outputs不需要，feed和fetch op里面都有的。

Paddle/paddle/fluid/inference/tests/test_helper.h

Lines 93 to 96 in 4c8ff72

void TestInference(const std::string& dirname,

const std::vector<paddle::framework::LoDTensor*>& cpu_feeds,

const std::vector<paddle::framework::LoDTensor*>& cpu_fetchs,

const int repeat = 1, const bool is_combined = false) {

单侧里面已经封装的比较干净了。

这里还需要考虑多线程预测的情况，需要加一个const int thread_nums的参数。

内部没有多线程，多线程是外面的线程调预测库。

luotao1 · 2018-05-10T06:31:31Z

contrib/inference/paddle_inference_api.h

+
+class Predictor {
+public:
+  struct Attr;


Attr-》Network？

不是Network，是 attribute

luotao1 · 2018-05-10T06:36:59Z

contrib/inference/paddle_inference_api.h

+      kAnakin,             // Use Anakin for inference.
+      kTensorRT,           // Use TensorRT for inference.
+      kAutoMixedAnakin,    // Automatically mix Fluid with Anakin.
+      kAutoMixedTensorRT,  // Automatically mix Fluid with TensorRT.


kAutoMixedAnakin和kAutoMixedTensorRT可以去掉，kAnakin应该就包括kAutoMixedAnakin

kNone里面应该还要分CPU模式，GPU模式

MKLDNN属于kNone还是单列？

不包括，这里 kTensorRT指的是全图用，子图那个是单独的开关kAutoMixedTensorRT

对用户来说，子图全图概念有点复杂，选了TensorRT，就理解为用TensorRT来做优化了，至于用子图还是全图优化（而且全图是子图的一部分），应该内部实现。

部分支持的feature现在还没有，放在这里只剩为了让业务方知道我们在做这个feature

luotao1 · 2018-05-10T06:39:16Z

contrib/inference/README.md

+- Memory reuse for native Fluid executor;
+- Translate the model storage format to some third-party engine's, so that the inference API can utilize the engine for acceleration;
+
+We have an official tool to do the optimization, call `paddle_inference_optimize --help` for more information.


paddle_inference_optimize是binary还是python脚本？
比如python paddle_inference_optimize src_model_dir dst_model_dir --inference_optimize_method=2 代表使用第二种优化策略。

binary或者脚本

panyx0718

Let's kick off this thing. It's in contrib, just for experiment for now

panyx0718 · 2018-05-10T10:37:37Z

contrib/inference/README.md

@@ -0,0 +1,27 @@
+# Embed Paddle Inference in Your Application
+
+Paddle inference offers the APIs in `C` and `C++` languages.


c如果暂时不需要就先别写了

init

6a86630

Superjomn requested review from luotao1 and Xreki May 10, 2018 03:19

fix grammar

eece930

luotao1 reviewed May 10, 2018

View reviewed changes

panyx0718 approved these changes May 10, 2018

View reviewed changes

Superjomn merged commit 6d371e4 into PaddlePaddle:develop May 10, 2018

Superjomn deleted the feature/inference_api branch May 10, 2018 12:04

Xreki added the 预测原名Inference，包含Capi预测问题等 label May 16, 2018

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

init Inference top APIs #10549

init Inference top APIs #10549

Superjomn commented May 10, 2018

luotao1 May 10, 2018

Superjomn May 10, 2018

panyx0718 May 10, 2018

luotao1 May 10, 2018

luotao1 May 10, 2018

Superjomn May 10, 2018

luotao1 May 10, 2018

luotao1 May 10, 2018

Superjomn May 10, 2018

luotao1 May 10, 2018

Superjomn May 10, 2018

luotao1 May 10, 2018

Superjomn May 10, 2018

luotao1 May 10, 2018

Superjomn May 10, 2018 •

edited

Loading

luotao1 May 10, 2018

Superjomn May 10, 2018

panyx0718 left a comment

panyx0718 May 10, 2018

		@@ -0,0 +1,27 @@
		# Embed Paddle Inference in Your Application

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


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

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


		## Optimize the native Fluid Model

		The native model that get from the training phase needs to be optimized for that.

	void TestInference(const std::string& dirname,
	const std::vector<paddle::framework::LoDTensor*>& cpu_feeds,
	const std::vector<paddle::framework::LoDTensor*>& cpu_fetchs,
	const int repeat = 1, const bool is_combined = false) {

init Inference top APIs #10549

init Inference top APIs #10549

Conversation

Superjomn commented May 10, 2018

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Superjomn May 10, 2018 • edited Loading

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

panyx0718 left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Superjomn May 10, 2018 •

edited

Loading