【caffe】caffe中transform_param中參數的執行順序

執行順序

caffe中transform_param有四個選項：scale，mean，mirror，crop_size

transform_param {
    scale: 0.00390625
    mean_file_size: "examples/cifar10/mean.binaryproto"
    mirror: 1  # 1表示開啓鏡像，0表示關閉，也可用ture和false來表示
    crop_size: 227 # 剪裁一個 227*227的圖塊，在訓練階段隨機剪裁，在測試階段從中間裁剪
  }

需要知道他們的執行順序來設值，比如先mean再scale和先scale再mean結果就不同了。

閱讀源碼“data_transformer.cpp”可知，執行順序是mean(file)、mean(value)、crop、mirror、scale。如有其它特殊的預處理可在此添加代碼。此外由 const bool do_mirror = param_.mirror() && Rand(2); 可知每次batch是隨機的做mirror（水平翻轉）的。

代碼

// data_transformer.cpp

template<typename Dtype>
void DataTransformer<Dtype>::Transform(Blob<Dtype>* input_blob,
                                       Blob<Dtype>* transformed_blob) {
  const int crop_size = param_.crop_size();
  const int input_num = input_blob->num();
  const int input_channels = input_blob->channels();
  const int input_height = input_blob->height();
  const int input_width = input_blob->width();

  if (transformed_blob->count() == 0) {
    // Initialize transformed_blob with the right shape.
    if (crop_size) {
      transformed_blob->Reshape(input_num, input_channels,
                                crop_size, crop_size);
    } else {
      transformed_blob->Reshape(input_num, input_channels,
                                input_height, input_width);
    }
  }

  const int num = transformed_blob->num();
  const int channels = transformed_blob->channels();
  const int height = transformed_blob->height();
  const int width = transformed_blob->width();
  const int size = transformed_blob->count();

  CHECK_LE(input_num, num);
  CHECK_EQ(input_channels, channels);
  CHECK_GE(input_height, height);
  CHECK_GE(input_width, width);


  const Dtype scale = param_.scale();
  const bool do_mirror = param_.mirror() && Rand(2);
  const bool has_mean_file = param_.has_mean_file();
  const bool has_mean_values = mean_values_.size() > 0;

  int h_off = 0;
  int w_off = 0;
  if (crop_size) {
    CHECK_EQ(crop_size, height);
    CHECK_EQ(crop_size, width);
    // We only do random crop when we do training.
    if (phase_ == TRAIN) {
      h_off = Rand(input_height - crop_size + 1);
      w_off = Rand(input_width - crop_size + 1);
    } else {
      h_off = (input_height - crop_size) / 2;
      w_off = (input_width - crop_size) / 2;
    }
  } else {
    CHECK_EQ(input_height, height);
    CHECK_EQ(input_width, width);
  }

  Dtype* input_data = input_blob->mutable_cpu_data();
  if (has_mean_file) {
    CHECK_EQ(input_channels, data_mean_.channels());
    CHECK_EQ(input_height, data_mean_.height());
    CHECK_EQ(input_width, data_mean_.width());
    for (int n = 0; n < input_num; ++n) {
      int offset = input_blob->offset(n);
      caffe_sub(data_mean_.count(), input_data + offset,
            data_mean_.cpu_data(), input_data + offset);
    }
  }

  if (has_mean_values) {
    CHECK(mean_values_.size() == 1 || mean_values_.size() == input_channels) <<
     "Specify either 1 mean_value or as many as channels: " << input_channels;
    if (mean_values_.size() == 1) {
      caffe_add_scalar(input_blob->count(), -(mean_values_[0]), input_data);
    } else {
      for (int n = 0; n < input_num; ++n) {
        for (int c = 0; c < input_channels; ++c) {
          int offset = input_blob->offset(n, c);
          caffe_add_scalar(input_height * input_width, -(mean_values_[c]),
            input_data + offset);
        }
      }
    }
  }

  Dtype* transformed_data = transformed_blob->mutable_cpu_data();

  for (int n = 0; n < input_num; ++n) {
    int top_index_n = n * channels;
    int data_index_n = n * channels;
    for (int c = 0; c < channels; ++c) {
      int top_index_c = (top_index_n + c) * height;
      int data_index_c = (data_index_n + c) * input_height + h_off;
      for (int h = 0; h < height; ++h) {
        int top_index_h = (top_index_c + h) * width;
        int data_index_h = (data_index_c + h) * input_width + w_off;
        if (do_mirror) {
          int top_index_w = top_index_h + width - 1;
          for (int w = 0; w < width; ++w) {
            transformed_data[top_index_w-w] = input_data[data_index_h + w];
          }
        } else {
          for (int w = 0; w < width; ++w) {
            transformed_data[top_index_h + w] = input_data[data_index_h + w];
          }
        }
      }
    }
  }
  if (scale != Dtype(1)) {
    DLOG(INFO) << "Scale: " << scale;
    caffe_scal(size, scale, transformed_data);
  }
}