Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.
Comment: image update

Inspection shows how the input image is processed for each module, where detected objects are displayed for each image, providing detailed information such as rectangle coordinates, ID, image size, confidence percentage, etc.

The Context (application variable), is displayed in JSON format for each module. The data will be available in Inspection after you activate a model for any module within the Flow.

Image Removedinspection showcase.pngImage Added

Module-independent data

Image Dimension (Pixels)

Code Block
languagepy
{
  "globalData": null,
  "image": {
    "type": "<numpy>",
    "shape": [
      837,
      1305,
      3
    ]
  }

Anomaly Detector - JSON Data

Detected Rectangle Data - XY Coordinates, Dimension[px], Area[px], ID, Color, Class Name

Code Block
languagepy
  "detectedRectangles": [
    {
      "x": 1086,
      "y": 510,
      "width": 3,
      "height": 3,
      "area": 2,
      "id": 1603111484990003,
      "classNames": [
        {
          "color": "#ff00ff",
          "color_bgr": [
            255,
            0,
            255
          ],
          "id": 1603111688057,
          "label": "Scratch"
        }
        ....

Heatmap Data - Dimension, Color, ID & Class Name

Code Block
languagepy
 "heatmaps": [
    [
      {
        "type": "<numpy>",
        "shape": [
          768,
          1024,
          1
        ]
      },
      {
        "color": "#ff0000",
        "color_bgr": [
          0,
          0,
          255
        ],
        "id": 1,
        "label": "Defect"
      }
    ]
    ....

Classifier - JSON Data

Detected Rectangle Data - Class Names, ID & Confidence % (Accuracy)

Info

Accuracy is represented as [0-1] value. To get the percentage → Accuracy * 100 = Accuracy %

Info

Detected Rectangle for Product A has 99.99% confidence

Code Block
languagepy
"detectedRectangles": [
    {
      "classNames": [
        {
          "label": "Product A",
          "id": 1579785458561,
          "accuracy": 0.9999566078186035
        },
        {
          "label": "Product B",
          "id": 1563879945497,
          "accuracy": 0.000023665264961891808
        },
        {
          "label": "Product C",
          "id": 1579785458074,
          "accuracy": 0.00001757865356921684
        },
        {
          "label": "Missing",
          "id": 1579785459058,
          "accuracy": 0.0000020917841538903303
        },
        {
          "label": "Product D",
          "id": 1563879965635,
          "accuracy": 2.7898661159042604e-8
        }
      ]

Surface Detection - JSON Data

Detected Rectangle Data - XY Coordinates, Dimension, Area, ID, Color, Class Name

Code Block
languagepy
"detectedRectangles": [
    {
      "x": 35,
      "y": 681,
      "width": 30,
      "height": 33,
      "area": 718.5,
      "id": 1603111484990000,
      "classNames": [
        {
          "color": "#ff0000",
          "color_bgr": [
            0,
            0,
            255
          ],
          "id": 1,
          "label": "Defect"
        }

Heatmap Data - Dimension, Color, ID & Class Name

Code Block
languagepy
"heatmaps": [
    [
      {
        "type": "<numpy>",
        "shape": [
          837,
          1305,
          1
        ]
      },
      {
        "color": "#ff0000",
        "color_bgr": [
          0,
          0,
          255
        ],
        "id": 1,
        "label": "Defect"
      }

Detector - JSON Data

Detected Rectangle Data - Coordinates, Dimension, ID, Class Name, Confidence Percentage

Info

Accuracy is represented as [0-1] value. To get the percentage → Accuracy * 100 = Accuracy %

Info

Detected Rectangle for label = "Screw02" has 99.18% confidence

Code Block
languagepy
  "detectedRectangles": [
    {
      "x": 456,
      "y": 361,
      "width": 165,
      "height": 163,
      "id": 1604385708721000,
      "confidence": 0.9918909072875977,
      "classNames": [
        {
          "id": 1604385716945,
          "label": "Screw02",
          "confidence": 0.9918909072875977
        }
      ]
    },
  ...

OCR - JSON Data

Detected Rectangle Info - ID, Dimension, OCR Text, Confidence Percentage

Info

Accuracy is represented as [0-1] value. To get the percentage → Accuracy * 100 = Accuracy %

Info

Detected Rectangle for ''text=Today'' has 99.71% confidence

Code Block
languagepy
"detectedRectangles": [
    {
      "rotate": 0,
      "x": 97,
      "y": 87,
      "width": 366,
      "height": 60,
      "classNames": [
        {
          "label": "16/02/2022",
          "id": -1,
          "confidence": 0.8683
        }
      ],
      "confidence": 0.8683,
      "ocv_result": "not_activated",
      "ocv_value": 0,
      "id": 1
    }...

Measure - JSON Data

Lines - Name, Start & End coordinates, Angle, Measured length

Code Block
languagepy
"lines": [
    {
      "id": 1651502661344,
      "label": "Line1",
      "start": {
        "x": 165,
        "y": 479
      },
      "end": {
        "x": 158,
        "y": 4
      },
      "angle": 1.5560605513728232,
      "length": 475
    },
    {
      "id": 1651502665897,
      "label": "Line2",
      "start": {
        "x": 436,
        "y": 479
      },
      "end": {
        "x": 436,
        "y": 4
      },
      "angle": 1.5707963267948966,
      "length": 475
    }
  ]