Model JSON Structure

This page outlines model JSON structure and parameters.

JSON Configuration File Parameters

JSON Overview

All models in model zoos are paired with JSON configuration files that describe the model type, its intended function, the runtime environment it is compiled for, and its preprocessing and postprocessing settings.

We can organize these parameters into five sections:

• General: Basic information to identify the model.
• DEVICE: Environment the model expects.
• MODEL_PARAMETERS: Settings for how the model operates.
• PRE_PROCESS: Preprocessing settings for model inputs.
• POST_PROCESS: Postprocessing settings for model outputs.

Incorrectly setting these parameters may decrease precision or performance.

Example JSON Configuration

Below is an example JSON configuration for reference. Note that you can include or omit parameters as needed:

{
  "ConfigVersion": <config_version_number>,
  "Checksum": "<checksum>",
  "DEVICE": [
    {
      "DeviceType": "<device_type>",
      "RuntimeAgent": "<runtime_agent>",
      "SupportedDeviceTypes": "<supported_device_types>"
    }
  ],
  "PRE_PROCESS": [
    {
      "InputN": <input_N>,
      "InputH": <input_H>,
      "InputW": <input_W>,
      "InputC": <input_C>,
      "InputQuantEn": <boolean_for_quant_enabled>
    }
  ],
  "MODEL_PARAMETERS": [
    {
      "ModelPath": "<path_to_model>"
    }
  ],
  "POST_PROCESS": [
    {
      "OutputPostprocessType": "<postprocess_type>",
      "OutputNumClasses": <number_of_output_classes>,
      "LabelsPath": "<path_to_labels_json>"
    }
  ]
}

---

General Parameters

General parameters are located at the top of the JSON file. They indicate the configuration file version and the checksum of the model binary for all models.

Parameter	Type	Mandatory
ConfigVersion	int	yes
Checksum	string	yes

• ConfigVersion The version of the JSON configuration file. The current JSON config version is 10. It is verified against the minimum compatible and current framework software versions. If the version is not within the acceptable range, a version-check runtime exception is generated during model loading.

• Checksum The checksum of the model binary file.

---

Device Parameters

Section name in JSON: DEVICE

This section includes three parameters: DeviceType, RuntimeAgent, and SupportedDeviceTypes. Refer to the Supported Hardware section for details on device compatibility.

Parameter	Type	Mandatory
DeviceType	string	yes
RuntimeAgent	string	yes
SupportedDeviceTypes	string	yes

• DeviceType The type of device on which the model will run.

• RuntimeAgent The runtime agent responsible for executing the model.

• SupportedDeviceTypes Lists the device types that are supported by the model. Refer to the Supported Hardware documentation for details on device compatibility.

---

Model Parameters

Section name in JSON: MODEL_PARAMETERS

These parameters control how the model operates.

Parameter	Type	Mandatory	Models
ModelPath	string	yes	All

• ModelPath The path to a model file.

---

Preprocessing Parameters

Section name in JSON: PRE_PROCESS

These parameters control settings used to prepare and transform input data before it is fed into the model, ensuring proper formatting and normalization. This section may contain multiple elements (one per input tensor in multi-input networks).

Input Configuration

Fundamental properties of the input data, including its type, dimensions, and layout.

Parameter	Type	Mandatory	Default	Input Type
InputN	int	yes	(none)	All
InputH	int	yes	(none)	All
InputW	int	yes	(none)	All
InputC	int	yes	(none)	All
InputType	string	No	"Image"	All
InputShape	int array	No	(none)	All
InputRawDataType	string	No	"DG_UINT8"	All
InputTensorLayout	string	No	"NHWC"	Image

• InputN The batch size for the input data tensor.

• InputH The height of the input data tensor.

• InputW The width of the input data tensor.

• InputC The number of channels in the input data tensor.

• InputType The model input type. The dimension order is defined by InputTensorLayout. This can be set to:

  • Image

  • Tensor

• InputShape The shape of the input data tensor in the format[<N>, <H>, <W>, <C>]. You may specify the shape with this parameter or with the InputN, InputH, InputW, and InputC parameters.

• InputRawDataType The data type of raw binary tensor elements (how the preprocessor treats client data). This is a runtime parameter that can be changed on the fly. This can be set to:

  • DG_UINT8 (unsigned 8-bit integer)

  • DG_FLT (32-bit floating point),

  • DG_INT16 (signed 16-bit integer).

• InputTensorLayout The dimensional layout of the raw binary tensor for inputs of raw image type and raw tensor type. This can be set to:

  • auto

  • NHWC

  • NCHW

---

Image Format & Manipulation

Governs the image input format, color space, resizing, padding, cropping, and slicing operations. These parameters are needed only when InputType is Image.

Parameter	Type	Mandatory	Default
ImageBackend	string	No	"auto"
InputResizeMethod	string	No	"bilinear"
InputPadMethod	string	No	"letterbox"
InputCropPercentage	double	No	1.0
InputImgFmt	string	No	"JPEG"
InputColorSpace	string	No	"RGB"

• ImageBackend The Python package used for image processing. When this is set to auto, the OpenCV backend will be tried first. This can be set to:

  • auto

  • pil

  • opencv

• InputResizeMethod The interpolation algorithm used for image resizing. This can be set to:

  • nearest

  • bilinear

  • area

  • bicubic

  • lanczos

• InputPadMethod Specifies how the input image is padded or cropped during resizing. This can be set to:

  • stretch

  • letterbox

  • crop-first

  • crop-last

• InputCropPercentage The crop percentage when InputPadMethod is set to crop-first or crop-last.

• InputImgFmt The image format for image inputs. Data type is defined by InputRawDataType. This can be set to:

  • JPEG

  • RAW

• InputColorSpace The color space required for image inputs. This can be set to RGB or BGR. If InputImgFmt is JPEG, the preprocessor automatically handles color conversion; if RAW, the raw tensor must be arranged accordingly.

---

Normalization

Defines how input data is normalized, including scale factors and per-channel adjustments, to ensure consistency across inputs.

Parameter	Type	Mandatory	Default	Models
InputScaleEn	bool	No	false	Image
InputScaleCoeff	double	No	1./255.	Image
InputNormMean	float array	No	[]	Image
InputNormStd	float array	No	[]	Image

• InputScaleEn Specifies whether global data normalization is applied.

• InputScaleCoeff The scale factor used for global data normalization when InputScaleEn is true.

• InputNormMean The mean values for per-channel normalization of image inputs (e.g., [0.485, 0.456, 0.406]).

• InputNormStd The standard deviation values for per-channel normalization of image inputs (e.g., [0.229, 0.224, 0.225]).

---

Quantization

Settings for converting input data into quantized formats to optimize processing efficiency and model performance.

Parameter	Type	Mandatory	Default	Models
InputQuantEn	bool	No	false	All
InputQuantOffset	float	No	0	All
InputQuantScale	float	No	1	All

• InputQuantEn Enables input quantization for image and raw tensor types, determining whether the model input is treated as uint8 or float32.

• InputQuantOffset The quantization zero offset for image and raw tensor inputs.

• InputQuantScale The quantization scale. When quantization is enabled, data is scaled before quantization using the provided formula.

---

Postprocessing Parameters

Section name in JSON: POST_PROCESS

These parameters transform model outputs into final, interpretable results.

General Behavior

General settings for the output postprocessing algorithm and how output tensors are managed.

Parameter	Type	Mandatory	Default
PythonFile	string	No	(none)
LabelsPath	string	No	""
OutputPostprocessType	string	No	None

• OutputPostprocessType The type of output postprocessing algorithm. This can be set to:

  • Classification

  • Detection

  • DetectionYolo

  • DetectionYoloPlates

  • DetectionYoloV8

  • FaceDetection

  • HandDetection

  • PoseDetection

  • PoseDetectionYoloV8

  • Segmentation

  • SegmentationYoloV8

  • None

• PythonFile The name of a Python file that contains server-side postprocessing code.

• LabelsPath The path to a label dictionary file.

• OutputPostprocessType The type of output post-processing algorithm.

---

Thresholds & Alignment

Thresholds and alignment adjustments used during postprocessing to filter and refine model outputs.

Parameter	Type	Mandatory	Default
OutputConfThreshold	double	No	0.1
OutputNMSThreshold	double	No	0.6
OutputClassIDAdjustment	int	No	0

• OutputConfThreshold The confidence threshold below which results are filtered out.

• OutputNMSThreshold The threshold for the Non-Max Suppression (NMS) algorithm.

• OutputClassIDAdjustment The adjustment for the index of the first non-background class.

---

Classification-Specific

Parameters tailored for classification tasks, such as enabling softmax and selecting the number of top classes.

Parameter	Type	Mandatory	Default
OutputSoftmaxEn	bool	No	false
OutputTopK	size_t	No	0

• OutputSoftmaxEn Specifies whether softmax is enabled during post-processing.

• OutputTopK The number of classes to include in the classification result. If set to zero, all classes above OutputConfThreshold are reported.

---

Detection-Specific

Parameters tailored for object detection, including detection limits, scaling coefficients, and non-max suppression parameters.

Parameter	Type	Mandatory	Default
XScale	double	conditional	1
YScale	double	conditional	1
HScale	double	conditional	1
WScale	double	conditional	1
OutputNumClasses	int	No	(none)
MaxDetectionsPerClass	int	No	100
MaxClassesPerDetection	int	No	30
UseRegularNMS	bool	No	true
MaxDetections	int	No	20
PoseThreshold	double	No	0.8
NMSRadius	double	No	10
Stride	int	No	16

• XScale The X scale coefficient used to convert box center coordinates to an anchor-based coordinate system.

• YScale The Y scale coefficient used to convert box center coordinates to an anchor-based coordinate system.

• HScale The height scale coefficient used to convert box size coordinates to an anchor-based coordinate system.

• WScale The width scale coefficient used to convert box size coordinates to an anchor-based coordinate system.

• OutputNumClasses The number of output classes for detection models.

• MaxDetectionsPerClass The maximum number of object detection results to report per class.

• MaxClassesPerDetection The maximum number of classes to report for each detection.

• UseRegularNMS Specifies whether to use a regular (non-batched) NMS algorithm for object detection.

• MaxDetections The maximum number of object detection results to report.

• PoseThreshold The pose score threshold below which low-confidence poses are filtered out.

• NMSRadius The NMS radius for pose detection—a keypoint candidate is rejected if it lies within this pixel range of a previously detected instance.

• Stride The stride scale coefficient used for pose detection.