A trainable parameter. It can be a scalar, vector, matrix, or tensor of floating point numbers that can be modified by a training procedure.
Parameter(value = NULL, shape = NULL, dtype = "float32", device = NULL, name = "")
| shape | - list of ints representing tensor shape |
|---|---|
| dtype | - data type to be used ("float32", "float64", or "auto") |
| device | - instance of DeviceDescriptor |
| name |
****** Properties: ******
value