TensorDesc#

class tensorrt.plugin.TensorDesc(shape_expr: Optional[tensorrt.plugin._tensor.ShapeExprs] = None, dtype: Optional[tensorrt.tensorrt.DataType] = None, format: Optional[tensorrt.tensorrt.TensorFormat] = None, scale: Optional[float] = None)#

Descriptor for a tensor A TensorDesc never contains nor refers to any tensor data.

Parameters

shape_expr (ShapeExprs) – The data with which to initialize the tensor.
dtype (trt.DataType) – The data type of the tensor.
format (trt.TensorFormat) – Format (layout) of the tensor.
scale (float) – Scale for INT8 data type.

Creates a TensorDesc with constant shape expressions#

tensor = trt.TensorDesc((10, 2, 32, 32), dtype=trt.float32)

Creates a TensorDesc from shape expression of another TensorDesc#

tensor = trt.from_shape_expr(other.shape_expr, dtype=trt.float32)

aliased() → tensorrt.plugin._tensor.TensorDesc#

Returns: Returns a TensorDesc which has identical properties and is aliased to this tensor (would result in a Tensor during enqueue sharing the same data buffer). Returned TensorDesc is immutable.

Communicate that output tensor has identical properties to the input tensor#

@tensorrt.plugin.register("my::plugin")
def _(inp: tensorrt.plugin.TensorDesc) -> tensorrt.plugin.TensorDesc:
    return inp.aliased()

property dtype: tensorrt.tensorrt.DataType#: Data type of the tensor.

property format: tensorrt.tensorrt.TensorFormat#: The format of the tensor.

Warning

Only accessible when TensorDesc.has_shape is true.

get_aliased() → tensorrt.plugin._tensor.TensorDesc#

Returns: Returns a TensorDesc for the tensor which this tensor is aliased to. Returns None is this tensor is not aliased to any other tensor.

property has_shape: bool#: True if this tensor has concrete shape information, False otherwise.

property has_shape_expr: bool#: True if this tensor has symbolic shape expressions, False otherwise.

property is_aliased: bool#: True if this tensor is aliased to another tensor, False otherwise.

property is_dynamic: bool#: True if this tensor has at least one dynamic dimension, False otherwise.

like() → tensorrt.plugin._tensor.TensorDesc#

Returns: Returns a TensorDesc which has identical properties to this tensor, and is mutable.

Communicate that output tensor has identical properties to the input tensor#

@tensorrt.plugin.register("my::plugin")
def _(inp: tensorrt.plugin.TensorDesc) -> tensorrt.plugin.TensorDesc:
    return inp.like()

property ndim: int#: Number of dimensions

numel() → int#

Returns: Returns an int with the number of elements of the tensor.

Warning

Should only be called when TensorDesc.has_shape is true. If a symbolic expression for the number of elements is required, query TensorDesc.shape_expr.numel().

property scale: float#: Scale for INT8 data type.

Warning

Only accessible when TensorDesc.has_shape is true.

property shape: tensorrt.plugin._tensor.Shape#: The (concrete) shape of the tensor.

Warning

Only accessible when TensorDesc.has_shape is true.

property shape_expr: tensorrt.plugin._tensor.ShapeExprs#: Symbolic expressions for the tensor shape.

class tensorrt.plugin.SizeTensorDesc(opt: tensorrt.plugin._tensor.ShapeExpr, upper_bound: tensorrt.plugin._tensor.ShapeExpr)#

Extends TensorDesc

Descriptor for a size tensor: a scalar of either INT32 or INT64 data type used to express the extent of a data-dependent dimension.

Parameters

opt (ShapeExpr) – Symbolic expression for the extent of this size tensor to use in the autotune process of the engine build
upper_bound (ShapeExpr) – Symbolic expression for the upper-bound of this size tensor

Note

It is recommended to construct a size tensor using size_tensor() instead of using this constructor directly

expr() → tensorrt.plugin._tensor.SizeTensorShapeExpr#: Symbolic expression for this size tensor

property index: int#: Output index at which this size tensor resides

property opt: tensorrt.plugin._tensor.ShapeExpr#: Symbolic expression for the extent of this size tensor to use in the autotune process of the engine build

property upper_bound: tensorrt.plugin._tensor.ShapeExpr#: Symbolic expression for the upper-bound of this size tensor