Eltwise
Inputs (Dynamic)
x:
- Required: yes
- Type: float16, float32
- Description: input tensors of the identical data type and shape. Has a maximum size of 32.
- Restriction: The number of inputs x must be less than or equal to 32.
Attribute
- operation:
- Required: no
- Type: int
- Description: Computes element-wise. Addition, multiplication, and maximization are supported. The value can be:
- 0:product
- 1 (default): sum
- 2: max
- Restriction: Must be in the range 0–2.
- coeff:
- Required: no
- Type: ListFloat
- Description: Has the same length as the number of bottom blobs. Default value: [] (Coefficient to be multiplied for the sum operation.)
- Restriction: Keep its length the same as the number of bottom blobs.
Output
y:
- Required: yes
- Type: float16, float32
- Description: output tensor. It has the same data type and shape as the input tensor. It is computed element-wise from the input tensor, supporting operations such as addition, multiplication, and maximization.
- Restriction: Must be float16.
Parent topic: Supported Caffe Operators