code format

lite/api/ocr_attention_test_fpga.cc

@@ -27,25 +27,6 @@ DEFINE_string(input_file, "", "input_file");
 namespace paddle {
 namespace lite {
 
-// float* temp_data = new float(33 * 10 * 23);
-
-// std::vector<std::string> GetDirectoryFiles(const std::string& dir) {
-//   std::vector<std::string> files;
-//   std::shared_ptr<DIR> directory_ptr(opendir(dir.c_str()),
-//                                      [](DIR* dir) { dir&& closedir(dir); });
-//   struct dirent* dirent_ptr;
-//   if (!directory_ptr) {
-//     std::cout << "Error opening : " << std::strerror(errno) << dir <<
-//     std::endl;
-//     return files;
-//   }
-
-//   while ((dirent_ptr = readdir(directory_ptr.get())) != nullptr) {
-//     files.push_back(std::string(dirent_ptr->d_name));
-//   }
-//   return files;
-// }
-
 void read_from_file(const std::string& path, float* data, int num) {
   std::ifstream file_stream;
   file_stream.open(path);
@@ -87,7 +68,6 @@ void TestModel(const std::vector<Place>& valid_places,
   predictor.Build("", "attention/model", "attention/params", valid_places);
 
   auto* input_tensor = predictor.GetInput(0);
-  // input_tensor->Resize(DDim(std::vector<DDim::value_type>({1, 1, 48, 512})));
   input_tensor->Resize(DDim(std::vector<DDim::value_type>({1, 1, 100, 200})));
   auto* data = input_tensor->mutable_data<float>();
   auto item_size = input_tensor->dims().production();
@@ -95,22 +75,7 @@ void TestModel(const std::vector<Place>& valid_places,
     data[i] = 1;
   }
 
-  // std::ifstream file_stream(FLAGS_input_file);
-  // // file_stream.open(path);
-  // if (!file_stream.good()) {
-  //   std::cout << "file: " << FLAGS_input_file << " dones not exist!\n";
-  //   exit(-1);
-  //   return;
-  // }
-
-  // read_from_file("n7cu17.data", data, 100 * 200);
   read_from_file(FLAGS_input_file, data, 100 * 200);
-  // read_from_file("t.data", data, 48 * 512);
-
-  // for (int i = 0;i < 48 * 512;i++ ) {
-  //   std::cout << ":" << data[i] << std::endl;
-  // }
-
   //=============================================
   auto* init_ids = predictor.GetInput(1);
   init_ids->Resize(DDim(std::vector<DDim::value_type>({1, 1})));
@@ -143,12 +108,9 @@ void TestModel(const std::vector<Place>& valid_places,
 
   float* temp_data = position_encoding_data;
 
-  std::cout << "====================== 1\n";
-
   for (int i = 0; i < position_encoding->dims().production(); ++i) {
     temp_data[i] = 0;
   }
-  std::cout << "====================== 2\n";
   int index = 0;
   for (int i = 0; i < 10; i++) {
     for (int row = 0; row < 10; row++) {
@@ -162,7 +124,6 @@ void TestModel(const std::vector<Place>& valid_places,
       }
     }
   }
-  std::cout << "====================== 3\n";
   for (int i = 0; i < 23; i++) {
     for (int row = 0; row < 10; row++) {
       for (int col = 0; col < 23; col++) {
@@ -175,20 +136,11 @@ void TestModel(const std::vector<Place>& valid_places,
       }
     }
   }
-  std::cout << "====================== 4\n";
   // chw_to_hwc(temp_data, position_encoding_data, 33, 10, 23);
   // delete[] temp_data;
 
   // read_from_file("position_encoding.data", position_encoding_data, 33 * 10 *
   // 23);
-  // position_encoding->ZynqTensor()->readFromFile("position_encoding.data");
-
-  // exit(-1);
-
-  // for (int i = 0; i < FLAGS_warmup; ++i) {
-  //   predictor.Run();
-  // }
-
   auto start = GetCurrentUS();
   for (int i = 0; i < 2; ++i) {
     predictor.Run();
@@ -200,32 +152,8 @@ void TestModel(const std::vector<Place>& valid_places,
             << ", spend " << (GetCurrentUS() - start) / FLAGS_repeats / 1000.0
             << " ms in average.";
 
-  //  std::vector<std::vector<float>> results;
-  //  // i = 1
-  //  results.emplace_back(std::vector<float>(
-  //      {0.00019130898, 9.467885e-05,  0.00015971427, 0.0003650665,
-  //       0.00026431272, 0.00060884043, 0.0002107942,  0.0015819625,
-  //       0.0010323516,  0.00010079765, 0.00011006987, 0.0017364529,
-  //       0.0048292773,  0.0013995157,  0.0018453331,  0.0002428986,
-  //       0.00020211363, 0.00013668182, 0.0005855956,  0.00025901722}));
   auto* out = predictor.GetOutput(0);
 
-  //  ASSERT_EQ(out->dims().size(), 2);
-  //  ASSERT_EQ(out->dims()[0], 1);
-  //  ASSERT_EQ(out->dims()[1], 1000);
-  //
-  //  int step = 50;
-  for (int i = 0; i < 10; i++) {
-    // std::cout << ":" << out->data<float>()[i] << std::endl;
-  }
-  //  for (int i = 0; i < results.size(); ++i) {
-  //    for (int j = 0; j < results[i].size(); ++j) {
-  //      EXPECT_NEAR(out->data<float>()[j * step + (out->dims()[1] * i)],
-  //                  results[i][j],
-  //                  1e-6);
-  //    }
-  //  }
-
   std::string file = "plate_data/" + FLAGS_input_file.substr(9);
   std::cout << "file:::" << file << std::endl;
 
@@ -244,9 +172,6 @@ TEST(OcrAttention, test_arm) {
       Place{TARGET(kHost), PRECISION(kFloat)},
       Place{TARGET(kARM), PRECISION(kFloat)},
   });
-
-  // Place{TARGET(kFPGA), PRECISION(kFP16), DATALAYOUT(kNHWC)},
-
   TestModel(valid_places, Place{TARGET(kARM), PRECISION(kFloat)});
 }
 

lite/api/resnet50_test_fpga.cc

@@ -31,7 +31,11 @@ TEST(ResNet50, test) {
   std::vector<Place> valid_places(
       {Place{TARGET(kFPGA), PRECISION(kFP16), DATALAYOUT(kNHWC)}});
 
-  predictor.Build(FLAGS_model_dir, "", "", valid_places);
+  predictor.Build(FLAGS_model_dir,
+                  "", 
+                  "", 
+                  Place{TARGET(kFPGA), PRECISION(kFP16), DATALAYOUT(kNHWC)},  
+                  valid_places);
 
   auto* input_tensor = predictor.GetInput(0);
   input_tensor->Resize(DDim(std::vector<DDim::value_type>({1, 3, 224, 224})));

lite/backends/fpga/KD/pes/conv_process.hpp

@@ -48,7 +48,6 @@ inline int get_split_num(Tensor* filter) {
              filter->shape().width();
   auto num = filter->shape().num();
   int div_capacity = filter::calc_division_capacity(chw);
-  // int aligned_num = align_to_x(num ,FILTER_NUM_ALIGNMENT);
   int filter_num_alignment = filter::get_filter_num_alignment();
   int aligned_num = align_to_x(num, filter_num_alignment);
   return filter::calc_split_num(aligned_num, div_capacity);
@@ -213,16 +212,6 @@ inline void format_filter(Tensor* filter,
   for (size_t i = 0; i < max_values.size(); i++) {
     scales.push_back(max_values[i] / max_value);
   }
-
-  // filter->saveToFile("filter.txt");
-  // std::ofstream ofs;
-  // ofs.open("quant.txt");
-  // for (int i = 0; i < mem_size; i++) {
-  //   float value = quantized_data[i];
-  //   ofs << value << std::endl;
-  // }
-  // ofs.close();
-  // exit(-1);
 }
 
 inline void format_dw_filter(Tensor* filter,
@@ -356,12 +345,9 @@ inline void split_filter_num(const ConvParam& c_param) {
                       &conv_param->filter,
                       &conv_param->scaleBias,
                       param.groups);
-    // conv_param->scaleBias.saveToFile("sb.txt");
+
     conv_param->scaleBias.flush();
     float* bs_data = conv_param->scaleBias.data<float>();
-    // conv_param->scaleBias.saveToFile("sb.txt");
-    // param.scale()->saveToFile("scale.txt");
-    // param.bias()->saveToFile("bias.txt");
 
     args.group_num = param.groups;
     args.relu_enabled = param.relu.enabled;
@@ -445,7 +431,6 @@ inline void split_channel(const ConvParam& c_param) {
                       &conv_param->scaleBias,
                       param.groups);
     conv_param->scaleBias.flush();
-    // conv_param->scaleBias.saveToFile("sb.txt");
 
     ConvArgs& args = conv_param->args;
     args.group_num = param.groups;

lite/backends/fpga/KD/pes/fully_connected_pe.hpp

@@ -39,12 +39,6 @@ class FullyConnectedPE : public PE {
     convParam_.input = param_.input;
     num_ = param_.input->shape().num();
 
-    // if (num_ == 1) {
-
-    // } else {
-    //   tempOut_.mutableData<void>(FP16, param_.out->shape());
-    //   convParam_.output = &tempOut_;
-    // }
     convParam_.output = param_.output;
 
     convParam_.groups = 1;
@@ -72,11 +66,8 @@ class FullyConnectedPE : public PE {
         new_filter_data[i * chw + j] = scale;
       }
     }
-    // conv_filter->copyFrom(param_.filter);
-
     conv_filter->flush();
     convParam_.filter = conv_filter;
-    // convParam_.filter = param_.filter;
 
     Shape sb_shape(N, {channel});
     float* scale_data = convParam_.scale()->mutableData<float>(FP32, sb_shape);

lite/backends/fpga/KD/tensor.hpp

@@ -25,13 +25,10 @@ limitations under the License. */
 #include <string>
 #include <vector>
 
-// #include "lite/core/tensor.h"
-
 #include "lite/backends/fpga/KD/dl_engine.hpp"
 #include "lite/backends/fpga/KD/float16.hpp"
 #include "lite/backends/fpga/KD/llapi/zynqmp_api.h"
 #include "lite/backends/fpga/KD/shape.hpp"
-// #include "lite/backends/fpga/KD/types.hpp"
 
 namespace paddle {
 namespace zynqmp {
@@ -398,15 +395,9 @@ class Tensor {
   void save_file_with_name(std::string path) {
     // return;
     invalidate();
-    // usleep(20000);
-    // return;
     std::ofstream ofs;
-
     ofs.open(path);
 
-    ofs << "dataType: " << dataType_ << std::endl;
-    ofs << "scale: " << scale()[0] << " , " << scale()[1] << std::endl;
-
     for (int i = 0; i < shape_->numel(); i++) {
       float value = 0;
       if (dataType_ == FP32) {

lite/core/program.cc

@@ -121,7 +121,9 @@ void RuntimeProgram::Run() {
     inst.Run();
 #ifdef LITE_WITH_PROFILE
 #ifdef LITE_WITH_PRECISION_PROFILE
-// LITE_PRECISION_PROFILE(inst)
+#ifndef LITE_WITH_FPGA
+    LITE_PRECISION_PROFILE(inst)
+#endif
 #endif  // LITE_WITH_PRECISION_PROFILE
 #endif  // LITE_WITH_PROFILE
   }

lite/kernels/fpga/transpose_compute.cc

@@ -47,8 +47,6 @@ void Transpose2Compute::Run() {
     //   int num = input_x_dims[1];
     // int channel = input_x_dims[2];
 
-    // // DLOG << "num::" << num << "  channel::" << channel;
-
     // int index = 0;
     // for (int n = 0; n < num; n++) {
     //   for (int c = 0; c < channel; c++) {