【caffe】Layer解读之：Reshape

叁歲伎倆 2022-05-17 12:39 206阅读 0赞

*  Layer type: Reshape
 *  头文件位置：./include/caffe/layers/reshape\_layer.hpp
 *  CPU 执行源文件位置: ./src/caffe/layers/reshape\_layer.cpp
 *  Reshape层的功能：根据给定参数改变输入blob的维度，仅仅改变数据的维度，但内容不变。

##### 参数解读 #####

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
          }
        }
      }

如上图中的dim，具体还以如下：

#有一个可选的参数组shape, 用于指定blob数据的各维的值（blob是一个四维的数据：n*c*w*h）。 
    
    #dim:0 表示维度不变，即输入和输出是相同的维度。 
    
    #dim:2 或 dim:3 将原来的维度变成2或3 
    
    #dim:-1 表示由系统自动计算维度。数据的总量不变，系统会根据blob数据的其它三维来自动计算当前维的维度值 。 
    
    #假设原数据为：32*3*28*28， 表示32张3通道的28*28的彩色图片 
    # shape { 
    # dim: 0 32-32 
    # dim: 0 3-3 
    # dim: 14 28-14 
    # dim: -1 #让其推断出此数值 
    # } 
    
    #输出数据为：32*3*14*56

##### 参数定义 #####

参数(ReshapeParameter reshape\_param)  
定义位置 ./src/caffe/proto/caffe.proto:  
可选参数组：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只改变输入数据的维度，但内容不变，也没有数据复制的过程，与Flatten layer类似。

输出维度由reshape\_param 指定，正整数直接指定维度大小，下面两个特殊的值：

0 => 表示copy the respective dimension of the bottom layer，复制输入相应维度的值。  
\-1 => 表示infer this from the other dimensions，根据其他维度自动推测维度大小。reshape\_param中至多只能有一个-1。  
再举一个例子：如果指定reshape\_param参数为：\{ shape \{ dim: 0 dim: -1 \} \} ，那么输出和Flattening layer的输出是完全一样的。  
Flatten层的操作详见：[【caffe】Layer解读之：Flatten][caffe_Layer_Flatten]

[caffe_Layer_Flatten]: https://blog.csdn.net/qiu931110/article/details/81589165