Image Classification

Overview

Image Classification node predicts the most likely class label for the entire input frame using a loaded model.

Unlike object detection, this node classifies the frame as a whole rather than locating individual objects within it. Use this node when you need to categorize scenes (for example pass/fail, empty/occupied) or distinguish between broad image types.

Input

Input Image

image required

The image frame to classify. Connect this to a camera or upstream processing output.

Model Directory Path

string required

Path to the model directory to load for classification. See Model Directory Path for details.

Confidence Threshold

number required

Minimum confidence score for a label to be included in the output. Results below this value are suppressed. See Confidence Threshold for tuning guidance.

Ignore Labels

array

List of label strings to exclude from the output. Useful for suppressing catch-all or background labels that are rarely actionable.

Overlay Results

boolean required

When enabled, draws the top predicted label and confidence score as text on the output frame. See Overlay Results.

Custom Model Configs

boolean

Reveals extra framework and architecture fields for non-.nam models. See Custom Model Configs.

Model Color Format

Color format of the image data sent to the model. If left blank, the default for the chosen architecture is used. Adjust if your model was trained with a different color format.

• RGB — Red, Green, Blue channel order.
• BGR — Blue, Green, Red channel order.

Scale

Multiplicative factor for the R, G, and B channels of the image before sending to the neural network. If left blank, the default for the chosen architecture is used. Used to normalize pixel values to the range expected by the model.

Mean

Mean values for the R, G, and B channels that are subtracted from the image before sending to the neural network. If left blank, the default for the chosen architecture is used. Used to normalize the image to match the data distribution the model was trained on.

Input Format

Tensor format for the image data sent to the neural network. If left blank, the default for the chosen architecture is used.

• NHWC — Batch × Height × Width × Channel (channels last).
• NCHW — Batch × Channel × Height × Width (channels first).

Input Type

Data type of the image input sent to the neural network.

• Uint8 — Pixel values are integers in the range 0–255.
• Float32 — Pixel values are 32-bit floating point numbers, often in the range 0.0–1.0 or normalized according to the model's training.

Post Process Type

Method for processing the raw output from the neural network before producing the final classification result. If left blank, the default for the chosen architecture is used.

• imgclass_onnx-logit
  • [1,C] e.g. [[class_a_logit, class_b_logit, ...]]
  • Applies a softmax function to the raw output logits from an ONNX model to calculate class probabilities, then filters by confidence threshold.
• imgclass_opencv-prob
  • [1,C] e.g. [[class_a_score, class_b_score, ...]]

Output

Overlay Image

image

Output frame from the node. If overlays are enabled, the top predicted label and score are drawn as text on this frame.

Classification

object

Classification result object containing:

• label string: The predicted class label.
• confidence number: Confidence score for the prediction.