ComplexModel

class savant.base.model.ComplexModel(local_path=None, remote=None, model_file=None, batch_size=1, precision=ModelPrecision.FP16, input=ModelInput(object='auto.frame', layer_name=None, shape=None, maintain_aspect_ratio=False, scale_factor=1.0, offsets=(0.0, 0.0, 0.0), color_format=<ModelColorFormat.RGB: 0>, preprocess_object_meta=None, preprocess_object_image=None), output=ComplexModelOutput(layer_names=[], converter='???', attributes='???', objects='???'))

Complex model configuration template. Validates entries in a module config file under element.model.

Complex model combines object and attribute models, for example face detector that produces bounding boxes and landmarks.

batch_size: int = 1: Number of frames or objects to be inferred together in a batch.

Note

In case the model is an NvInferModel and it is configured to use the TRT engine file directly, the default value for batch_size will be taken from the engine file name, by parsing it according to the scheme {model_name}_b{batch_size}_gpu{gpu_id}_{precision}.engine

input: ModelInput = ModelInput(object='auto.frame', layer_name=None, shape=None, maintain_aspect_ratio=False, scale_factor=1.0, offsets=(0.0, 0.0, 0.0), color_format=<ModelColorFormat.RGB: 0>, preprocess_object_meta=None, preprocess_object_image=None): Optional configuration of input data and custom preprocessing methods for a model. If not set, then input will default to entire frame.

local_path: Optional[str] = None: Path where all the necessary model files are placed. By default, the value of module parameter “model_path” and element name will be used (“model_path / element_name”).

model_file: Optional[str] = None: The model file, eg yolov4.onnx.

Note

The model file is specified without a location. The absolute path to the model file will be defined as “local_path/model_file”.

precision: ModelPrecision = 2

Data format to be used by inference.

Example

precision: fp16
# precision: int8
# precision: fp32

Note

In case the model is an NvInferModel and it is configured to use the TRT engine file directly, the default value for precision will be taken from the engine file name, by parsing it according to the scheme {model_name}_b{batch_size}_gpu{gpu_id}_{precision}.engine

remote: Optional[RemoteFile] = None: Configuration of model files remote location. Supported schemes: s3, http, https, ftp.

output: ComplexModelOutput = ComplexModelOutput(layer_names=[], converter='???', attributes='???', objects='???'): Configuration for post-processing of a complex model’s results.