ImageDev

OnnxModel

Contains all the information necessary to run a ONNX command.

Information about the measurement named measurement can be accessed by using the method measurementInformation() which returns a FieldInformation
Information about the measurement named measurement can be accessed by using the property measurementInformation which returns a FieldInformation
Information about the measurement named measurement can be accessed by using the property measurement_information which returns a FieldInformation

Object members

Measurement name DescriptionElement typeIndexingPhysical Information
inputCount The number of inputs of the model. Unsigned integer None COUNT
inputDimensionCount The number of dimensions expected by the model for the input tensors.
It is generally 4 for 2D images, and 5 for 3D volumes.
Unsigned integer [inputIndex] COUNT
inputName The inputs'names. String [inputIndex] UNKNOWN
inputShape The input tensors'shapes.
The tensor layout depends on how it has been defined in the model. It is generally NCHW or NHWC in 2D, and NDHWC or NCDHW in 3D where N is the number of images contained in the batch, C is the number of channels, D is the volume depth in 3D, H is the image height, or number of rows, and W is the image width, or number of columns.
Integer [inputIndex, dimension] UNKNOWN
inputType The inputs'data types. String [inputIndex] UNKNOWN
outputCount The number of outputs of the model. Unsigned integer None COUNT
outputDimensionCount The number of dimensions expected for the output tensors. Unsigned integer [outputIndex] COUNT
outputName The outputs'names. String [outputIndex] UNKNOWN
outputShape The output tensors'shapes. Integer [outputIndex, dimension] UNKNOWN
outputType The outputs'data types. String [outputIndex] UNKNOWN
inputOnnxType The inputs'data ONNX types. String [inputIndex] UNKNOWN
outputOnnxType The outputs'data ONNX types. String [outputIndex] UNKNOWN
metadata The metadata of the model.
It contains all information that can be useful at the inference step such as the inference type, the data format expected by the model, the compatible image size required pre processing, the input and output normalization information ot the tile overlap.
String None UNKNOWN
path The path of the file used to load the Onnx model. String None UNKNOWN
runnerType The type of runner.
It depends of the capacities of the hosting machine and defines if the model will be applied on CPU or on GPU.
String None UNKNOWN

Object methods

Method Description
void toDataFrame() Convert the measurement to an IOLink.DataFrame
One or more "index" columns will be added at the beginning of the dataframe to identify the different elements. For instance:
  • index [label]: The index of the label. This index systematically starts from 0 and is the label value minus 1 when all label values are represented. When there are some missing label values, the corresponding label value cannot be directly deduced from this index.
  • index [time]: The sequence index of a time series or of an image stack.
Method Description
void ToDataFrame() Convert the measurement to an IOLink.DataFrame
One or more "index" columns will be added at the beginning of the dataframe to identify the different elements. For instance:
  • index [label]: The index of the label. This index systematically starts from 0 and is the label value minus 1 when all label values are represented. When there are some missing label values, the corresponding label value cannot be directly deduced from this index.
  • index [time]: The sequence index of a time series or of an image stack.
Method Description
void to_data_frame() Convert the measurement to an IOLink.DataFrame
One or more "index" columns will be added at the beginning of the dataframe to identify the different elements. For instance:
  • index [label]: The index of the label. This index systematically starts from 0 and is the label value minus 1 when all label values are represented. When there are some missing label values, the corresponding label value cannot be directly deduced from this index.
  • index [time]: The sequence index of a time series or of an image stack.

Related algorithms




© 2026 Thermo Fisher Scientific Inc. All rights reserved.