I/O information

The following information is required by the qaic-smart-nms tools for processing of the input/outputfiles. The “qaic-smart-nms“ tools read the AIC hardware output files from aic-output-dir.

The Smart-NMS: user-config file (I/O information) parameters are:

  • model-output-dir: Specify the directory to look for object detection model outputs from AIC/CPU runtime.

    Required

    Type: PATH

  • model-output-extension: Looks for these extension files while reading inference output files from model-output-dir.

    Optional. Default: “.bin”

    Type: String

  • model-num-outputs: Process that many numbers of boxes, scores, landmarks from model-output-dir.

    Optional. Default: 1

    Type: Int

  • abp-output-dir: Specify the directory to store smart-nms outputs.

    Required

    Type: PATH

  • model-run-time: “AIC” / “CPU”

    Required

    Type: String

  • aic-model-info

    • model-binary-dir: Path of binary directory file generated after compilation of object-detection model.

      Required. If model-run-time: “AIC”

      Type: PATH

    • skip-transform-value: Specify the value for different transformation from LRT. Skip Transform Supported Types:

      • 1 = On (initial)

      • 2 = Quantize

      • 3 = Transpose

      • 4 = Convert

      • 5 = Off (Transformed) Required. If model-run-time: “AIC . Default : 5

      Type: Int

    • model-output-suffix: Append this value to output node names while reading output files from model-output-dir if model-run-time: “AIC”.

      Optional. Default: “-activation-0-inf-”

      Type: String

  • cpu-model-info

    • model-output-suffix: Append this value to output node names while reading output files from model-output-dir if model-run-time: “CPU”.

      Optional. Default: “”

      Type: String

    • model-outputs

      • names: Names of all output nodes in the model

        Required. If model-run-time: “CPU”

        Type: List of String

      • shapes: Respectively, shapes as a list for each model output, the shape for next model output should be provided in the next line.

        Required. If model-run-time: “CPU”

        Type: List of lists

      • types: List of type model output nodes given in names, respectively. Supported types “float”, “float16”, “int8Q”, “uint8Q”,”int16Q”, “int32Q”, “int32I”, “int64I”, “bool”.

        Required. If model-run-time: “CPU”

        Type: List of String

      • offsets: List of offsets for model output nodes given in names, respectively. Offsets and scales are required for [“int8Q”,”uint8Q”, “int16Q”, “int32Q”] types.

        Required. If model-run-time: “CPU” and types is quantized the value will be ignored.

        Type: List

      • scales: List of scales for model output nodes given in names, respectively. Offsets and scales are required for [“int8Q”,”uint8Q”, “int16Q”, “int32Q”] types.

        Required. If model-run-time: “CPU” and types is quantized else the value will be ignored.

        Type: List

    • model-inputs

      • names: Names of all output nodes in the model.

        Required. Names of all output nodes in the model.

        Type: List

      • shapes: Respectively, shapes as a list for each model output, the shape for next model output should be provided in the next line.

        Required. If model-run-time: “CPU”

        Type: List of List

    • prior-filepath: Prior refers to a predefined collection of boxes with encoded widths and heights chosen to match the widths and heights of objects in a dataset. With respect to prior information all the final predicted boxes are adjusted. The Yolo family does not require the prior files. In that case, an empty path can be provided.

      PATH

  • input-info

    • input-layout: Input image layout. Options for layout (“NCD”,”NDC”,”NHWC”,”NCHW”,”NAWHC”).

      Optional

      Type: String