Reshape
Description
Reshapes the input tensor.
Input
- data: input data tensor of type float16, int8, int16, uint16, uint8, int32, int64, uint32, uint64, bool, or double.
- shape: input shape tensor of type int64, specifying the shape of the output tensor.
Output
reshaped data: output tensor of the identical data type as the input data.
Attribute
allowzero: int. The default value is 0. If any value in the input shape is 0, the corresponding dimension value is dynamically copied from the input data. Setting allowzero to 1 indicates that if any value in the input shape is zero, the zero value is followed. This is similar to NumPy.
Constraints
None.
ONNX Opset Support
Opset v8/v9/v10/v11/v12/v13/v14/v15/v16/v17/v18
Parent topic: Supported ONNX Operators