Eltwise
Input (Dynamic)
x:
- Required: yes
- Type: float16, float32
- Description: input tensor. Has a maximum size of 32.
- Restriction: Must be of type float16. Keep the number of bottom blobs within 32.
Attribute
- operation:
- Required: no
- Type: int
- Description: element-wise operation type, selected from:
- 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. Coefficient to be multiplied for the sum operation (default = {}).
- Restriction: Keep its length the same as the number of bottom blobs.
Output
y:
- Required: yes
- Type: float16, float32
- Description: output tensor of element-wise product, sum, or max on the input tensor. Has the same data type and shape as the input tensor.
- Restriction: Must be of type float16.
Parent topic: Supported Caffe Operators