[x86 doc] add demo for x86 API (#3090)

docs/advanced_user_guides/x86.md

@@ -9,8 +9,8 @@ Paddle-Lite 支持在Docker或Linux环境编译x86预测库。环境搭建参考
 1、 下载代码
 ```bash
 git clone https://github.com/PaddlePaddle/Paddle-Lite.git
-#需要切换到 release/v2.0.0之后版本
-git checkout <release_tag>
+# 切换到release分支
+git checkout release/v2.3
 ```
 
 2、 源码编译
@@ -42,43 +42,56 @@ x86编译结果位于 `build.lite.x86/inference_lite_lib`
 
 ## x86预测API使用示例
 
+1、我们提供Linux环境下x86 API运行mobilenet_v1的示例：[mobilenet_full_x86demo](https://paddlelite-data.bj.bcebos.com/x86/mobilenet_full_x86demo.zip)。下载解压后内容如下：
+
+![](https://paddlelite-data.bj.bcebos.com/x86/x86-doc/demo.png)
+
+`mobilenet_v1`为模型文件、`lib`和`include`分别是Paddle-Lite的预测库和头文件、`third_party`下是编译时依赖的第三方库`mklml`、`mobilenet_full_api.cc`是x86示例的源代码、`build.sh`为编译的脚本。
+
+2、demo内容与使用方法
+
+``` bash
+# 1、编译
+sh build.sh
+```
+编译结果为当前目录下的 `mobilenet_full_api `
+``` bash
+# 2、执行预测
+mobilenet_full_api mobilenet_v1
+```
+`mobilenet_v1`为当前目录下的模型路径，`mobilenet_full_api`为第一步编译出的可执行文件。
+
+3、示例源码`mobilenet_full_api.cc`
+
 ```c++
-#include <gflags/gflags.h>
 #include <iostream>
 #include <vector>
-#include "paddle_api.h"          // NOLINT
-#include "paddle_use_kernels.h"  // NOLINT
-#include "paddle_use_ops.h"      // NOLINT
-#include "paddle_use_passes.h"   // NOLINT
+#include "paddle_api.h"
 
-using namespace paddle::lite_api;  // NOLINT
 
-DEFINE_string(model_dir, "", "Model dir path.");
-DEFINE_string(optimized_model_dir, "", "Optimized model dir.");
-DEFINE_bool(prefer_int8_kernel, false, "Prefer to run model with int8 kernels");
+using namespace paddle::lite_api;  // NOLINT
 
 int64_t ShapeProduction(const shape_t& shape) {
   int64_t res = 1;
   for (auto i : shape) res *= i;
   return res;
 }
-void RunModel() {
-  // 1. Set CxxConfig
-  CxxConfig config;
-  config.set_model_file(FLAGS_model_dir + "model");
-  config.set_param_file(FLAGS_model_dir + "params");
-
-  config.set_valid_places({
-    lite_api::Place{TARGET(kX86), PRECISION(kFloat)}
-  });
 
+void RunModel(std::string model_dir) {
+   // 1. Create CxxConfig
+   CxxConfig config;
+   config.set_model_dir(model_dir);
+   config.set_valid_places({
+     Place{TARGET(kX86), PRECISION(kFloat)},
+     Place{TARGET(kHost), PRECISION(kFloat)}
+   });
   // 2. Create PaddlePredictor by CxxConfig
   std::shared_ptr<PaddlePredictor> predictor =
       CreatePaddlePredictor<CxxConfig>(config);
 
   // 3. Prepare input data
   std::unique_ptr<Tensor> input_tensor(std::move(predictor->GetInput(0)));
-  input_tensor->Resize(shape_t({1, 3, 224, 224}));
+  input_tensor->Resize({1, 3, 224, 224});
   auto* data = input_tensor->mutable_data<float>();
   for (int i = 0; i < ShapeProduction(input_tensor->shape()); ++i) {
     data[i] = 1;
@@ -90,15 +103,21 @@ void RunModel() {
   // 5. Get output
   std::unique_ptr<const Tensor> output_tensor(
       std::move(predictor->GetOutput(0)));
-  std::cout << "Output dim: " << output_tensor->shape()[1] << std::endl;
+  std::cout << "Output shape " << output_tensor->shape()[1] << std::endl;
   for (int i = 0; i < ShapeProduction(output_tensor->shape()); i += 100) {
-    std::cout << "Output[" << i << "]:" << output_tensor->data<float>()[i] << std::endl;
+    std::cout << "Output[" << i << "]: " << output_tensor->data<float>()[i]
+              << std::endl;
   }
 }
 
 int main(int argc, char** argv) {
-  google::ParseCommandLineFlags(&argc, &argv, true);
-  RunModel();
+  if (argc < 2) {
+    std::cerr << "[ERROR] usage: ./" << argv[0] << " naive_buffer_model_dir\n";
+    exit(1);
+  }
+  std::string model_dir = argv[1];
+  RunModel(model_dir);
   return 0;
 }
+
 ```

docs/api_reference/cxx_api_doc.md

@@ -277,13 +277,13 @@ config.set_power_mode(LITE_POWER_HIGH);
 std::shared_ptr<PaddlePredictor> predictor = CreatePaddlePredictor<MobileConfig>(config);
 ```
 
-### `set_model_from_file(model_dir)`
+### `set_model_from_file(model_file)`
 
 设置模型文件，当需要从磁盘加载模型时使用。
 
 参数：
 
-- `model_dir(std::string)` - 模型文件路径
+- `model_file(std::string)` - 模型文件路径
 
 返回：`None`