ReLU
Description
Is an activation function. It returns a tensor with the same shape as the input tensor. If the value of a tensor is greater than 0, the value is used. Otherwise, the value is 0.
Input
x: input tensor of type int32, int8, float16, or float.
Output
y: tensor of the identical data type as x.
Constraints
None.
ONNX Opset Support
Opset v8/v9/v10/v11/v12/v13/v14/v15/v16/v17/v18
Parent topic: Supported ONNX Operators