Model

class savant.base.model.Model(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))

Base model configuration template.

Validates entries in a module config file under element.model.

local_path: str | None = 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”).

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

model_file: str | None = 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”.

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

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

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.