## DeploymentSettings_ONNXRuntime_ONNX

CLASS - DeploymentSettings_ONNXRuntime_ONNX(

graph_author:= None`Optional[str]`

graph_description:= None`Optional[str]`

input_shapes_for_deployment:= None`Union[list, tuple, List[list], List[tuple], Tuple[tuple], Tuple[list], None]`

utilize_full_int_range:= False`bool`

)

**Ancestors** - (* BaseDeploymentSettings*)

Use this if you wish to deploy to ONNXRuntime in `Settings.deployment_settings`

.

### Class Variables

**graph_author**() - Name of the Author of the Graph to attach to the final Model File.`Optional[str]`

**graph_description**() - Any description that should be attached to the final Model file`Optional[str]`

**input_shapes_for_deployment**() - Shapes to use for the deployment of the final Model file. Spatial Dimensions can be None if your model does not depend on it. For example, OK: Conv2d(...) AdaptiveAvgPool(output_size=(1,1)) Flatten() Linear() or Fully Convolutional model NOT OK: Conv2d(...) Flatten() Linear()`Union[list, tuple, List[list], List[tuple], Tuple[tuple], Tuple[list], None]`

**utilize_full_int_range**() - Set to True if you're planning to run the model on a CPU that supports AVX512-VNNI.`bool`

See Also

## DeploymentSettings_TFLite

CLASS - DeploymentSettings_TFLite(

graph_author:= None`Optional[str]`

graph_description:= None`Optional[str]`

input_shapes_for_deployment:= None`Union[list, tuple, List[list], List[tuple], Tuple[tuple], Tuple[list], None]`

)

**Ancestors** - (* BaseDeploymentSettings*)

Use this if you wish to deploy to TFLite in `Settings.deployment_settings`

.

### Class Variables

**graph_author**() - Name of the Author of the Graph to attach to the final Model File.`Optional[str]`

**graph_description**() - Any description that should be attached to the final Model file`Optional[str]`

**input_shapes_for_deployment**() - Shapes to use for the deployment of the final Model file. Spatial Dimensions can be None if your model does not depend on it. For example, OK: Conv2d(...) AdaptiveAvgPool(output_size=(1,1)) Flatten() Linear() or Fully Convolutional model NOT OK: Conv2d(...) Flatten() Linear()`Union[list, tuple, List[list], List[tuple], Tuple[tuple], Tuple[list], None]`

## DeploymentSettings_TensorRT_ONNX

CLASS - DeploymentSettings_TensorRT_ONNX(

graph_author:= None`Optional[str]`

graph_description:= None`Optional[str]`

input_shapes_for_deployment:= None`Union[list, tuple, List[list], List[tuple], Tuple[tuple], Tuple[list], None]`

)

**Ancestors** - (* BaseDeploymentSettings*)

Use this if you wish to deploy to TensorRT in `Settings.deployment_settings`

.

### Class Variables

**graph_author**() - Name of the Author of the Graph to attach to the final Model File.`Optional[str]`

**graph_description**() - Any description that should be attached to the final Model file`Optional[str]`

**input_shapes_for_deployment**() - Shapes to use for the deployment of the final Model file. Spatial Dimensions can be None if your model does not depend on it. For example, OK: Conv2d(...) AdaptiveAvgPool(output_size=(1,1)) Flatten() Linear() or Fully Convolutional model NOT OK: Conv2d(...) Flatten() Linear()`Union[list, tuple, List[list], List[tuple], Tuple[tuple], Tuple[list], None]`