【caffe】Layer解讀之：Reshape

 

2018年08月11日 17:36:14 yuanCruise 閱讀數：793更多

所屬專欄： Caffe源碼學習

 版權聲明：本文爲博主原創文章，未經博主允許不得轉載。 https://blog.csdn.net/qiu931110/article/details/81588956

• Layer type: Reshape
• 頭文件位置：./include/caffe/layers/reshape_layer.hpp
• CPU 執行源文件位置: ./src/caffe/layers/reshape_layer.cpp
• Reshape層的功能：根據給定參數改變輸入blob的維度，僅僅改變數據的維度，但內容不變。

參數解讀

 layer {
    name: "reshape"
    type: "Reshape"
    bottom: "input"
    top: "output"
    reshape_param {
      shape {
        dim: 0  # copy the dimension from below
        dim: 2
        dim: 3
        dim: -1 # infer it from the other dimensions
      }
    }
  }

如上圖中的dim，具體還以如下：

#有一個可選的參數組shape, 用於指定blob數據的各維的值（blob是一個四維的數據：n*c*w*h）。  

#dim:0  表示維度不變，即輸入和輸出是相同的維度。  

#dim:2 或 dim:3 將原來的維度變成2或3  

#dim:-1 表示由系統自動計算維度。數據的總量不變，系統會根據blob數據的其它三維來自動計算當前維的維度值 。  

#假設原數據爲：32*3*28*28， 表示32張3通道的28*28的彩色圖片  
#   shape {  
#   dim: 0  32-32  
#   dim: 0  3-3  
#   dim: 14 28-14  
#   dim: -1 #讓其推斷出此數值  
#   }  

#輸出數據爲：32*3*14*56  

參數定義

參數(ReshapeParameter reshape_param) 
定義位置 ./src/caffe/proto/caffe.proto: 
可選參數組：shape

message ReshapeParameter {
  // Specify the output dimensions. If some of the dimensions are set to 0,
  // the corresponding dimension from the bottom layer is used (unchanged).
  // Exactly one dimension may be set to -1, in which case its value is
  // inferred from the count of the bottom blob and the remaining dimensions.
  // For example, suppose we want to reshape a 2D blob "input" with shape 2 x 8:
  //
  //   layer {
  //     type: "Reshape" bottom: "input" top: "output"
  //     reshape_param { ... }
  //   }
  //
  // If "input" is 2D with shape 2 x 8, then the following reshape_param
  // specifications are all equivalent, producing a 3D blob "output" with shape
  // 2 x 2 x 4:
  //
  //   reshape_param { shape { dim:  2  dim: 2  dim:  4 } }
  //   reshape_param { shape { dim:  0  dim: 2  dim:  4 } }
  //   reshape_param { shape { dim:  0  dim: 2  dim: -1 } }
  //   reshape_param { shape { dim:  0  dim:-1  dim:  4 } }
  //
  optional BlobShape shape = 1;

  // axis and num_axes control the portion of the bottom blob's shape that are
  // replaced by (included in) the reshape. By default (axis == 0 and
  // num_axes == -1), the entire bottom blob shape is included in the reshape,
  // and hence the shape field must specify the entire output shape.
  //
  // axis may be non-zero to retain some portion of the beginning of the input
  // shape (and may be negative to index from the end; e.g., -1 to begin the
  // reshape after the last axis, including nothing in the reshape,
  // -2 to include only the last axis, etc.).
  //
  // For example, suppose "input" is a 2D blob with shape 2 x 8.
  // Then the following ReshapeLayer specifications are all equivalent,
  // producing a blob "output" with shape 2 x 2 x 4:
  //
  //   reshape_param { shape { dim: 2  dim: 2  dim: 4 } }
  //   reshape_param { shape { dim: 2  dim: 4 } axis:  1 }
  //   reshape_param { shape { dim: 2  dim: 4 } axis: -3 }
  //
  // num_axes specifies the extent of the reshape.
  // If num_axes >= 0 (and axis >= 0), the reshape will be performed only on
  // input axes in the range [axis, axis+num_axes].
  // num_axes may also be -1, the default, to include all remaining axes
  // (starting from axis).
  //
  // For example, suppose "input" is a 2D blob with shape 2 x 8.
  // Then the following ReshapeLayer specifications are equivalent,
  // producing a blob "output" with shape 1 x 2 x 8.
  //
  //   reshape_param { shape { dim:  1  dim: 2  dim:  8 } }
  //   reshape_param { shape { dim:  1  dim: 2  }  num_axes: 1 }
  //   reshape_param { shape { dim:  1  }  num_axes: 0 }
  //
  // On the other hand, these would produce output blob shape 2 x 1 x 8:
  //
  //   reshape_param { shape { dim: 2  dim: 1  dim: 8  }  }
  //   reshape_param { shape { dim: 1 }  axis: 1  num_axes: 0 }
  //
  optional int32 axis = 2 [default = 0];
  optional int32 num_axes = 3 [default = -1];
}

番外篇

Reshape layer只改變輸入數據的維度，但內容不變，也沒有數據複製的過程，與Flatten layer類似。

輸出維度由reshape_param 指定，正整數直接指定維度大小，下面兩個特殊的值：

0 => 表示copy the respective dimension of the bottom layer，複製輸入相應維度的值。 
-1 => 表示infer this from the other dimensions，根據其他維度自動推測維度大小。reshape_param中至多只能有一個-1。 
再舉一個例子：如果指定reshape_param參數爲：{ shape { dim: 0 dim: -1 } } ，那麼輸出和Flattening layer的輸出是完全一樣的。 
Flatten層的操作詳見：【caffe】Layer解讀之：Flatten