change format

test/fpga/test_rfcn_api.cpp

@@ -12,8 +12,8 @@ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 See the License for the specific language governing permissions and
 limitations under the License. */
 
-#include <iostream>
 #include <fstream>
+#include <iostream>
 #include "../../src/io/paddle_inference_api.h"
 
 using namespace paddle_mobile;
@@ -39,68 +39,68 @@ void readStream(std::string filename, char *buf) {
 }
 
 PaddleMobileConfig GetConfig() {
-    PaddleMobileConfig config;
-    config.precision = PaddleMobileConfig::FP32;
-    config.device = PaddleMobileConfig::kFPGA;
-    config.prog_file = g_model;
-    config.param_file = g_param;
-    config.thread_num = 1;
-    config.batch_size = 1;
-    config.optimize = true;
-	  config.lod_mode = true;
-    config.quantification = false;
-    return config;
+  PaddleMobileConfig config;
+  config.precision = PaddleMobileConfig::FP32;
+  config.device = PaddleMobileConfig::kFPGA;
+  config.prog_file = g_model;
+  config.param_file = g_param;
+  config.thread_num = 1;
+  config.batch_size = 1;
+  config.optimize = true;
+  config.lod_mode = true;
+  config.quantification = false;
+  return config;
 }
 
 int main() {
-    open_device();
-    PaddleMobileConfig config = GetConfig();
-    auto predictor =
-            CreatePaddlePredictor<PaddleMobileConfig,
-                    PaddleEngineKind::kPaddleMobile>(config);
-	
-    std::cout << "after loading model" << std::endl;
-    
-    float img_info[3] = {768, 1536, 768.0f / 960.0f};
-    int img_length = 768 * 1536 * 3;
-    auto img = reinterpret_cast<float *>(fpga_malloc(img_length * sizeof(float)));
-    readStream(g_image, reinterpret_cast<char *>(img));
-
-    std::cout << "after initializing data" << std::endl;
-/*
-  predictor->FeedData({img_info, img});
-  predictor->Predict_From_To(0, -1);
-  std::cout << " Finishing predicting " << std::endl;
-	std::vector<void *> v(3, nullptr);
-	predictor->GetResults(&v);
-  int post_nms = 300;
-  for (int num = 0; num < post_nms; num ++){
-    for (int i = 0; i < 8; i ++){
-      std:: cout << ((float*)(v[0]))[num * 8 + i] << std::endl;
+  open_device();
+  PaddleMobileConfig config = GetConfig();
+  auto predictor =
+      CreatePaddlePredictor<PaddleMobileConfig,
+                            PaddleEngineKind::kPaddleMobile>(config);
+
+  std::cout << "after loading model" << std::endl;
+
+  float img_info[3] = {768, 1536, 768.0f / 960.0f};
+  int img_length = 768 * 1536 * 3;
+  auto img = reinterpret_cast<float *>(fpga_malloc(img_length * sizeof(float)));
+  readStream(g_image, reinterpret_cast<char *>(img));
+
+  std::cout << "after initializing data" << std::endl;
+  /*
+    predictor->FeedData({img_info, img});
+    predictor->Predict_From_To(0, -1);
+    std::cout << " Finishing predicting " << std::endl;
+      std::vector<void *> v(3, nullptr);
+      predictor->GetResults(&v);
+    int post_nms = 300;
+    for (int num = 0; num < post_nms; num ++){
+      for (int i = 0; i < 8; i ++){
+        std:: cout << ((float*)(v[0]))[num * 8 + i] << std::endl;
+      }
     }
-  }
-  for (int num = 0; num < post_nms; num ++){
-    for (int i = 0; i < 8; i ++){
-      std:: cout << ((float*)(v[1]))[num * 8 + i] << std::endl;
+    for (int num = 0; num < post_nms; num ++){
+      for (int i = 0; i < 8; i ++){
+        std:: cout << ((float*)(v[1]))[num * 8 + i] << std::endl;
+      }
     }
-  }
-  for (int num = 0; num < post_nms; num ++){
-    for (int i = 0; i < 4; i ++){
-      std:: cout << ((float*)(v[2]))[num * 4 + i] << std::endl;
+    for (int num = 0; num < post_nms; num ++){
+      for (int i = 0; i < 4; i ++){
+        std:: cout << ((float*)(v[2]))[num * 4 + i] << std::endl;
+      }
     }
-  }
-*/
+  */
 
   struct PaddleTensor t_img_info, t_img;
   t_img_info.dtype = FLOAT32;
   t_img_info.layout = LAYOUT_HWC;
-  t_img_info.shape = std::vector<int>({1,3});
+  t_img_info.shape = std::vector<int>({1, 3});
   t_img_info.name = "Image information";
   t_img_info.data.Reset(img_info, 3 * sizeof(float));
 
   t_img.dtype = FLOAT32;
   t_img.layout = LAYOUT_HWC;
-  t_img.shape = std::vector<int>({1,768, 1536, 3});
+  t_img.shape = std::vector<int>({1, 768, 1536, 3});
   t_img.name = "Image information";
   t_img.data.Reset(img, img_length * sizeof(float));
   predictor->FeedPaddleTensors({t_img_info, t_img});
@@ -112,24 +112,24 @@ int main() {
 
   std::vector<PaddleTensor> v(3, PaddleTensor());
   predictor->FetchPaddleTensors(&v);
-	auto post_nms = v[0].data.length()/sizeof(float)/8;
-  for (int num = 0; num < post_nms; num ++){
-    for (int i = 0; i < 8; i ++){
-      auto p = reinterpret_cast<float*>(v[0].data.data());
-      std:: cout << p[num * 8 + i] << std::endl;
+  auto post_nms = v[0].data.length() / sizeof(float) / 8;
+  for (int num = 0; num < post_nms; num++) {
+    for (int i = 0; i < 8; i++) {
+      auto p = reinterpret_cast<float *>(v[0].data.data());
+      std::cout << p[num * 8 + i] << std::endl;
     }
   }
-  for (int num = 0; num < post_nms; num ++){
-    for (int i = 0; i < 8; i ++){
-      auto p = reinterpret_cast<float*>(v[1].data.data());
-      std:: cout << p[num * 8 + i] << std::endl;
+  for (int num = 0; num < post_nms; num++) {
+    for (int i = 0; i < 8; i++) {
+      auto p = reinterpret_cast<float *>(v[1].data.data());
+      std::cout << p[num * 8 + i] << std::endl;
     }
   }
-  for (int num = 0; num < post_nms; num ++){
-    for (int i = 0; i < 4; i ++){
-      auto p = reinterpret_cast<float*>(v[2].data.data());
-      std:: cout << p[num * 4 + i] << std::endl;
+  for (int num = 0; num < post_nms; num++) {
+    for (int i = 0; i < 4; i++) {
+      auto p = reinterpret_cast<float *>(v[2].data.data());
+      std::cout << p[num * 4 + i] << std::endl;
     }
   }
-    return 0;
+  return 0;
 }