DataType¶
-
tensorrt.
DataType
¶ Represents data types.
itemsize: int
The size in bytes of thisDataType
.Members:
FLOAT : Represents a 32-bit floating point number.
HALF : Represents a 16-bit floating point number.
INT8 : Represents an 8-bit integer.
INT32 : Represents a 32-bit integer.
TensorRT also exposes some short-hand, NumPy-style DataType
aliases that can be used across the library:
Type | Alias |
tensorrt.DataType.FLOAT |
tensorrt.float32 |
tensorrt.DataType.HALF |
tensorrt.float16 |
tensorrt.DataType.INT32 |
tensorrt.int32 |
tensorrt.DataType.INT8 |
tensorrt.int8 |