Inspection shows how the input image is processed in individual modules that it is passing through. It offers a look at how the picture changes during its passage. Detected objects are displayed for individual images. Testing can only be performed on images uploaded in the application. Each module has the time of processing displayed. After clicking on the module, a larger image opens. Only modules which are enabled (have a model assigned) are displayed.
Context
Below the modules, a serialized /wiki/spaces/CONFLUENCE/pages/7569551 is displayed in JSON formatfor 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/validade a model for any module within the Flow.
...
Anomaly of Surface - JSON Data
Image Dimension (Pixels)
| Code Block |
|---|
|
{
"globalData": null,
"image": {
"type": "<numpy>",
"shape": [
837,
1305,
3
]
} |
Detected Rectangle Data - XY Coordinates, Dimension[px], Area[px], ID, Color, Class Name
| Code Block |
|---|
|
"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 |
|---|
|
"heatmaps": [
[
{
"type": "<numpy>",
"shape": [
768,
1024,
1
]
},
{
"color": "#ff0000",
"color_bgr": [
0,
0,
255
],
"id": 1,
"label": "Defect"
}
]
.... |
Classifier - JSON Data
Image Dimension [px]
| Code Block |
|---|
|
{
"globalData": null,
"image": {
"type": "<numpy>",
"shape": [
837,
1305,
3
]
} |
Detected Retangle Data - Class Names, ID & Confidence % (Accuracy)
| Info |
|---|
Acurracy * 100 = Accuracy % |
| Info |
|---|
Detected Rectangle for Product A has 99.99% confidence |
| Code Block |
|---|
|
"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
Image Dimension (Pixels)
| Code Block |
|---|
|
{
"globalData": null,
"image": {
"type": "<numpy>",
"shape": [
837,
1305,
3
]
} |
Detected Rectangle Data - XY Coordinates, Dimension, Area, ID, Color, Class Name
| Code Block |
|---|
|
"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 |
|---|
|
"heatmaps": [
[
{
"type": "<numpy>",
"shape": [
837,
1305,
1
]
},
{
"color": "#ff0000",
"color_bgr": [
0,
0,
255
],
"id": 1,
"label": "Defect"
} |
Detector - JSON Data
Image Dimension (Pixels)
| Code Block |
|---|
|
{
"globalData": null,
"image": {
"type": "<numpy>",
"shape": [
837,
1305,
3
]
} |
Detected Rectangle Data - Coordinates, Dimension, ID, Class Name, Confidence Percentage
| Info |
|---|
Acurracy * 100 = Accuracy % |
| Info |
|---|
Detected Rectangle for ''id=…1000'' has 99.18% confidence |
| Code Block |
|---|
|
"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
Image Dimension (Pixels)
| Code Block |
|---|
|
{
"globalData": null,
"image": {
"type": "<numpy>",
"shape": [
837,
1305,
3
]
} |
Detected Rectangle Info - ID, Dimension, OCR Text, Confidence Percentage
| Info |
|---|
Acurracy * 100 = Accuracy % |
| Info |
|---|
Detected Rectangle for ''text=Today'' has 99.71% confidence |
| Code Block |
|---|
|
"ocr": [
{
"id": 1615382086440,
"width": 109,
"height": 38,
"x": 169.11210023365456,
"y": 420.09002285870446,
"text": "Today",
"confidence": 0.997153103351593
... |