Edge AI Manager settings

Persistent AI Manager settings are stored locally in the /opt/sclbl/etc/settings file. 
On installation
If it does not exist yet, the uimanager, the one-line install script, or Advantech ICR router will autogenerate the settings file by copying /opt/sclbl/etc/defaults to /opt/sclbl/etc/settings.
Default settings 
1
{
2
    "settings":
3
    {
4
        "SettingsSection": 1,
5
        "UserId":"",
6
        "LicenseKey":"",
7
        "DeviceId":"",
8
        "DeviceName": "My Device",
9
        "DeviceType": "CPU",
10
        "UserManagerUrl": "https://usermanager.sclbl.net/",
11
        "CdnLocation": "https://cdn.sclbl.net/file/",
12
        "AdminLocation": "https://admin.sclbl.net/",
13
        "RegId":"",
14
        "ModuleSocketName": "../sockets/sclblmod.sock",
15
        "DeamonSocketName": "../sockets/sclbld_%d.sock",
16
        "WebPort": 8081,
17
        "WebPortSecure": 8443,
18
        "OutputDistributorPort": 8012,
19
        "EdgeDeviceConnection": "no"
20
    },
21
    "module":
22
        {
23
        "ModuleSection":1,
24
        "Running":0,
25
        "AssignedModels": 
26
            [
27
                {
28
                    "AssignedModelCFID":"",
29
                    "AssignedModelSRPID":"",
30
                    "AssignedModelName":"",
31
                    "AssignedModelInput":"",
32
                    "AssignedModelNamedInput":"",
33
                    "AssignedInputO":null,
34
                    "AssignedInputC":null,
35
                    "AssignedInputH":null,
36
                    "AssignedInputW":null,
37
                    "AssignedInputMeans":"",
38
                    "AssignedInputVars":"",
39
                    "AssignedModelNamedOutput":"",
40
                    "AssignedModelOutput":"",
41
                    "AssignedModelOutputDetails":"",
42
                    "AssignedModelDetails":""
43
                }
44
            ],
45
        "InputDriver":"VIDEO",
46
        "InputCamera1IP":"",
47
        "InputCamera1Mask":"",
48
        "InputCamera1Username":"",
49
        "InputCamera1Pass":"",
50
        "InputCamera1Format":"",
51
        "InputCamera1Name":"",
52
        "InputCamera1C":"",
53
        "InputCamera1H":"",
54
        "InputCamera1W":"",
55
        "InputCamera1AspectRatio":1,
56
        "InputCamera1ShmF":25,
57
        "InputCamera1ShmH":360,
58
        "InputCamera1ShmW":640,
59
        "InputCamera1Location":"",
60
        "InputCamera1RoiX":0,
61
        "InputCamera1RoiY":0,
62
        "InputCamera1RoiW":0,
63
        "InputCamera1RoiH":0,
64
        "InputCamera1LineCrossingMaxNoCentroidsFollowingAtSameTime":5,
65
        "InputCamera1LineCrossingMaxFollowPathOfOneCentroidStep":4,
66
        "InputCamera1LineCrossingTopBottomMarginsOfThreshold":10,
67
        "InputCamera1LineCrossingKeepTrackOfCentroidWhenDisappearedStep":2,
68
        "InputCamera1LineCrossingDistanceThreshold":100,
69
        "InputCamera1LineCrossingX1":0,
70
        "InputCamera1LineCrossingY1":0,
71
        "InputCamera1LineCrossingX2":0,
72
        "InputCamera1LineCrossingY2":0,
73
        "InputCamera2IP":"",
74
        "InputCamera2Mask":"",
75
        "InputCamera2Username":"",
76
        "InputCamera2Pass":"",
77
        "InputCamera2Format":"",
78
        "InputCamera2Name":"",
79
        "InputCamera2C":"",
80
        "InputCamera2H":"",
81
        "InputCamera2W":"",
82
        "InputCamera2AspectRatio":1,
83
        "InputCamera2ShmF":25,
84
        "InputCamera2ShmH":360,
85
        "InputCamera2ShmW":640,
86
        "InputCamera2Location":"",
87
        "InputCamera2RoiX":0,
88
        "InputCamera2RoiY":0,
89
        "InputCamera2RoiW":0,
90
        "InputCamera2RoiH":0,
91
        "InputCamera2LineCrossingMaxNoCentroidsFollowingAtSameTime":5,
92
        "InputCamera2LineCrossingMaxFollowPathOfOneCentroidStep":4,
93
        "InputCamera2LineCrossingTopBottomMarginsOfThreshold":10,
94
        "InputCamera2LineCrossingKeepTrackOfCentroidWhenDisappearedStep":2,
95
        "InputCamera2LineCrossingDistanceThreshold":100,
96
        "InputCamera2LineCrossingX1":0,
97
        "InputCamera2LineCrossingY1":0,
98
        "InputCamera2LineCrossingX2":0,
99
        "InputCamera2LineCrossingY2":0,
100
        "InputCamera3IP":"",
101
        "InputCamera3Mask":"",
102
        "InputCamera3Username":"",
103
        "InputCamera3Pass":"",
104
        "InputCamera3Format":"",
105
        "InputCamera3Name":"",
106
        "InputCamera3C":"",
107
        "InputCamera3H":"",
108
        "InputCamera3W":"",
109
        "InputCamera3AspectRatio":1,
110
        "InputCamera3ShmF":25,
111
        "InputCamera3ShmH":360,
112
        "InputCamera3ShmW":640,
113
        "InputCamera3Location":"",
114
        "InputCamera3RoiX":0,
115
        "InputCamera3RoiY":0,
116
        "InputCamera3RoiW":0,
117
        "InputCamera3RoiH":0,
118
        "InputCamera3LineCrossingMaxNoCentroidsFollowingAtSameTime":5,
119
        "InputCamera3LineCrossingMaxFollowPathOfOneCentroidStep":4,
120
        "InputCamera3LineCrossingTopBottomMarginsOfThreshold":10,
121
        "InputCamera3LineCrossingKeepTrackOfCentroidWhenDisappearedStep":2,
122
        "InputCamera3LineCrossingDistanceThreshold":100,
123
        "InputCamera3LineCrossingX1":0,
124
        "InputCamera3LineCrossingY1":0,
125
        "InputCamera3LineCrossingX2":0,
126
        "InputCamera3LineCrossingY2":0,
127
        "InputCamera4IP":"",
128
        "InputCamera4Mask":"",
129
        "InputCamera4Username":"",
130
        "InputCamera4Pass":"",
131
        "InputCamera4Format":"",
132
        "InputCamera4Name":"",
133
        "InputCamera4C":"",
134
        "InputCamera4H":"",
135
        "InputCamera4W":"",
136
        "InputCamera4AspectRatio":1,
137
        "InputCamera4ShmF":25,
138
        "InputCamera4ShmH":360,
139
        "InputCamera4ShmW":640,
140
        "InputCamera4Location":"",
141
        "InputCamera4RoiX":0,
142
        "InputCamera4RoiY":0,
143
        "InputCamera4RoiW":0,
144
        "InputCamera4RoiH":0,
145
        "InputCamera4LineCrossingMaxNoCentroidsFollowingAtSameTime":5,
146
        "InputCamera4LineCrossingMaxFollowPathOfOneCentroidStep":4,
147
        "InputCamera4LineCrossingTopBottomMarginsOfThreshold":10,
148
        "InputCamera4LineCrossingKeepTrackOfCentroidWhenDisappearedStep":2,
149
        "InputCamera4LineCrossingDistanceThreshold":100,
150
        "InputCamera4LineCrossingX1":0,
151
        "InputCamera4LineCrossingY1":0,
152
        "InputCamera4LineCrossingX2":0,
153
        "InputCamera4LineCrossingY2":0,
154
        "GeneralFrameRate":0,
155
        "OutputLocation":"http://localhost:8012/output",
156
        "LocalPassword":"",
157
        "EnableLocalPassword":0,
158
        "OutputProtocol":"REST",
159
        "OutputFormat":"JSON",
160
        "OutputFrequency":-1,
161
        "OutputThresholdType":0,
162
        "SaveConditional":0,
163
        "SaveConditionalProbs":0,
164
        "SaveConditionalServer":"",
165
        "SaveImages":0,
166
        "SaveImagesPath":"",
167
        "ImageEndpoint":1,
168
        "SettingsUpload":0,
169
        "EmailOnAlarm":0,
170
        "UploadImageOnAlarm":0,
171
        "MaxVideoPreResize":640,
172
        "AlwaysOffline":0,
173
        "OnChange":0,
174
        "OnChangePixelThreshold":20,
175
        "OnChangeImageThreshold":5,
176
        "ExternalTrigger":0,
177
        "Clients":"",
178
        "NmsSensitivity":40
179
    },
180
    "advtech":
181
        {
182
        "MOD_SCLBL_ENABLED":0
183
        }
184
}
____________________________
Definitions of individual settings in the order they appear in the settings and defaults file.
UserId
The UserKey is a unique token that identifies a specific user. It is generated when registering at the Scailable platform. 
Without a UserId, LicenseKey and DeviceId the sclbld and sclblmod binaries will not start.
LicenseKey
The LicenseKey is a unique token that identifies a specific scailable license. It is generated when registering at the Scailable platform. 
Without a UserId, LicenseKey and DeviceId the sclbld and sclblmod binaries will not start.
DeviceId
The DeviceId is a unique token that identifies a specific device. It is generated when registering a device in the Scailable platform, and will not change for as long as the device's settings file is not deleted and regenerated. 
Without a UserId, LicenseKey and DeviceId the sclbld and sclblmod binaries will not start.
For non Advantech ICR devices, it is generated using the OS native machine UUID/GUID plus the first detected network card's MAC address: 
deviceid=MACHINENAME-FIRSTMACID
The MAC address is a unique identifier assigned to a network interface controller (NIC).
Machine IDs are usually generated during system installation and stay constant for all subsequent boots (though not for docker type instances). The following sources are used:
BSD uses /etc/hostid and smbios.system.uuid as a fallback
Linux uses /var/lib/dbus/machine-id
OS X uses IOPlatformUUID
Windows uses the MachineGuid from HKEY_LOCAL_MACHINE\SOFTWARE\Microsoft\Cryptography
For Advantech ICR devices, the Edge AI Manager equals the advantech device id.
DeviceName
A DeviceName is a human readable name chosen during device registration. The value does not have to be unique. 
DeviceType
A DeviceType is a human readable name representing the type of device chosen during device registration. The value does not have to be unique. 
UserManagerUrl
URL of the Scailable UserManager service. 
Default value: https://usermanager.sclbl.net/
This value generally does not have to be changed.
CdnLocation
URL of the Scailable CDN service file endpoint. 
Default value: https://cdn.sclbl.net/file/
This value generally does not have to be changed.
AdminLocation
URL of the Scailable Admin service. 
Default value: https://admin.sclbl.net/
This value generally does not have to be changed.
RegId
The RegistrationID is a unique token that identifies this specific device's registration.
ModuleSocketName
The AI Manager IO Module receives important information over a UNIX domain socket, such as control messages, triggers and tensor inputs. This setting controls the path to this socket and is expected to be relative to the executable.
Default value: ../sockets/sclblmod.sock
DeamonSocketName
The Scailable runtime and io module communicate with each other over a UNIX domain socket. Each instance of an Edge AI Manager within the same environment needs to have a unique socket name. 
Default value: ../sockets/sclbld_%d.sock 
WebPort
HTTP web server port of the uiprovider.
Default value: 8081 
WebPortSecure
HTTPS web server port of the uiprovider.
Default value: 8443
EdgeDeviceConnection
Whether or not to synchronize device settings with the Scailable cloud. This enables you to change settings such as the selected model, input and output settings from the cloud for this individual or whole groups of devices.
Default value: no
Running
Indicates if the AI Manager is currently running an inference(s). 
If the AI Manager is running its value is 1  
If the AI Manager is not running inferences its value is 0
Default value: 0
AssignedModels
The AssignedModels section of the settings is an array which can contain any number of assigned models. The individual model details should be automatically populated when selecting a model from the Cloud Admin.
The Edge AI Manager is designed in such a way that each assigned model will be run for inference on each incoming input. This means that if there are two assigned models, there will be two inferences run on each incoming tensor. The results of these inferences will be sent separately to whichever output is configured.
AssignedModelCFID
The AssignedModelCFID is a unique token that identifies the currently selected model.
AssignedModelSRPID
The AssignedModelSRPID is a unique token that identifies the currently selected model's group.
AssignedModelName
An AssignedModelName is the human readable name of the model. It is required, but does not have to be unique.
AssignedModelInput
AssignedModelnput is an optional field that can contain additional information regarding the currently selected model's input tensor(s) in JSON format.
AssignedModelInputNames
AssignedModelInputNames is a field that contains the names of each of the currently selected input tensors in JSON format. The names follow the order in which they were defined in the original ONNX file.
AssignedInputO
Image tensor order. Deep learning frameworks generally use either NCHW and NHWC layouts in memory  ONNX uses NCHW by default, but the AI Manager can convert between NCHW and NHWC input tensors.
NCHW order 0:
batch N, channels C, height H, width W
NHWC order 1:
batch N, height H, width W, channels C
Currently, the Scailable Edge AI Manager only supports N = 1
AssignedInputC
The integer number of colors / channels for image tensor inputs.
AssignedInputH
The integer image height for image tensor type input.
AssignedInputW
The integer image width for image tensor type input.
AssignedInputMeans
Image model mean normalization input values: output = (input - mean) / var
Has to be formatted as a JSON integer array. Default [0] per channel. 
For instance [0,0,0] for C = 3 
AssignedInputVars
Image model var normalization input values: output = (input - mean) / var
Image model mean normalization input values: output = (input - mean) / var
Has to be formatted as an JSON integer array. Default [1] per channel. 
For instance [1,1,1] for C = 3 
AssignedModelOutputNames
AssignedModelOutputNames is a field that contains the names of each of the currently selected output tensors in JSON format. The names follow the order in which they were defined in the original ONNX file.
AssignedModelOutput
AssignedModelOutput is an optional field that can contain additional information regarding the currently selected model's output tensor(s) in JSON format.
AssignedModelOutputDetails
Single string, sets postprocessing type.
Will be obsolete in the next AI Manager, but remain available for reverse compatibility.
AssignedModelDetails
AssignedModelDetails is a human readable description of the model. It does not have to be unique.
InputCameraXIP
InputCameraXIP defines the Xth camera's input address. Here, X is a value from 1 to N. 
For instance: InputCamera1IP=https://192.168.1.10
Depending on InputCameraXFormat, it can be one of the following:
InputCameraXFormat
Type of input
Example
Image (JPEG, GIF, PNG)
http:// or https:// URL
http://test.com/test.jpg
https://192.168.1.10
Image (JPEG, GIF, PNG)
local file URL
file://path/to/image/test.jpg
RTSP stream
rtsp:// URL
rtsp://test.com/stream.mjpg
MJPEG stream
http:// URL
http://test.com/stream.rtsp
V4L2 webcam
path to (usb) camera
/dev/video0
Gstreamer SHM
SHM path
/tmp/industrialcam
InputDriver
Controls through which mechanism the data gets to the AI Manager.
Currently there are two supported options:
VIDEO
When InputDriver is set to "VIDEO", the the AI Manager will fetch inputs from defined cameras, controlled by the InputCameraXIP setting.
SOCKET
When InputDriver is set to "SOCKET", the AI Manger will expect inputs received on its Unix socket. The path to this socket is controlled by the ModuleSocketName setting.
The module will wait for a message on the socket before performing inference.
InputCameraXAspectRatio
Determines how an input image is resized to model tensor input WxH dimensions. 
Description
Value
Image is fitted exactly to the tensor input dimensions without taking into account the original image's aspect ratio. As a result, the input tensor can be a "squashed" representation of the original input image.
0
Image is fitted to the tensor input aspect ratio by cutting edges of the image either vertically or horizontally in case the image aspect ratio differs from the tensor aspect ratio.. As a result, parts of the input image may not be part of the inference.
1
Image is fitted to the tensor input aspect ratio by adding black borders either horizontally or vertically in case the image aspect ratio differs from the tensor aspect ratio.
2
​
      0
​
      1
​
      2
InputCameraXMask
Coordinates of a polygon or polygons that the define an inverse mask or zone for camera no X. The area outside of the zone is "blacked out" and is not available to the model. The coordinates for two polygons A and B defined by three points, each existing of an integer X and Y coordinate, could be described as:
{"mask":[[A_X1,A_Y1,A_X2,A_Y2,A_X3,A_Y3],[B_X1,B_Y1,B_X2,B_Y2,B_X3,B_Y3]]}
A example using actual coordinates for a zone or inverse mask of one polygon defined by four points would be: 
{"mask":[[44,22,100,21,109,108,46,114]]}
The X and Y coordinates are defined relative to their position to the topleft 0,0 coordinate of the image input tensor:
​
​
Where Y is within H and X within W.
InputCameraXUsername
Optional username for camera X.
InputCameraXPass
Optional password for camera X.
InputCameraXFormat
Can be one of the following:
Description
Value
Image (JPEG, GIF, PNG)
jpg
RTSP stream
rtsp
MJPEG stream
mjpeg
V4L2 webcam
v4l2
Gstreamer SHM
shm
InputCameraXName
User defined name of camera X. 
InputCameraXC
Set automatically by the AI Manager. The number of channels / colors in the output of camera no X.
InputCameraXH
Set automatically by the AI Manager. The height of the output of camera X in pixels.
InputCameraXW
Set automatically by the AI Manager. The width of the output of camera X in pixels.
InputCameraXShmF
GStreamer shmsink video input frequency for camera X. Required when InputCameraXFormat is set to shm. Default 25 frames per second.
InputCameraXShmH
GStreamer shmsink video input height for camera X. Required when InputCameraXFormat is  set to shm. Default 360 pixels.
InputCameraXShmW
GStreamer shmsink video input width for camera X. Required when InputCameraXFormat is  set to shm. Default 640 pixels.
InputCameraXLocation
Human readable description of camera X's location
InputCameraXRoiX
Camera Region Of Interest top left integer coordinate X value in pixels. Defined relative to the top left (0,0) coordinate of the image input tensor WxH
InputCameraXRoiY
Camera Region Of Interest top left integer coordinate Y value in pixels. Defined relative to the top left (0,0) coordinate of the image input tensor WxH
InputCameraXRoiW
Camera Region Of Interest integer width within the coordinate space of the image input tensor WxH
InputCameraXRoiH
Camera Region Of Interest integer height within the coordinate space of the image input tensor WxH
InputCameraXLineCrossingX1
Camera x-coordinate of first point used to define the line used in line crossing within the coordinate space of the image input tensor WxH
For more information about the line-crossing algorithm integration, check the post-processing page.
InputCameraXLineCrossingY1
Camera y-coordinate of first point used to define the line used in line crossing within the coordinate space of the image input tensor WxH
InputCameraXLineCrossingX2
Camera x-coordinate of second point used to define the line used in line crossing within the coordinate space of the image input tensor WxH
InputCameraXLineCrossingY2
Camera y-coordinate of second point used to define the line used in line crossing within the coordinate space of the image input tensor WxH
The two points (X1, Y1) and (X2, Y2) defining a line.
InputCameraXLineCrossingKeepTrackOfCentroidWhenDisappearedStep
Camera's maximum number of frames to wait for an object to reappear before considering it left definitely.
InputCameraXLineCrossingTopBottomMarginOfThreshold
Camera's threshold distance, from line, to consider a centroid moved from one side to the other side of line.
InputCameraXLineCrossingMaxFollowPathOfOneCentroidStep
Camera's maximum number of recent positions the object has occupied. This serves to determine the direction of movement for each object.
InputCameraXLineCrossingMaxNoCentroidFollowingAtSameTime
Camera's maximum number of objects to keep track of at the same time. 
InputCameraXLineCrossingDistanceThreshold
Camera's threshold distance (in terms of pixels) between an existing centroid and a new object centroid, above which these two centroids cannot be paired together.
GeneralFrameRate
OutputLocation
REST Endpoint inference output location. For example, https://example.com/myendpoint
EnableLocalPassword
Whether to turn on HTTP Authentication password: 1 is on, 0 is off.
LocalPassword
HTTP Authentication password.
OutputProtocol
Output protocol. Default: REST
OutputFormat
Output format. Default: JSON
OutputFrequency
Select a maximum frequency limit for the inferences in milliseconds, to save bandwidth and/or power. The model may not be fast enough to reach this maximum, but the module will not attempt faster inferences.

Default: 2, that is, every two seconds. When set to 0 the output frequency is only limited by the inference speed.
OutputThresholdType
Inference results can be sent one at a time or aggregated.
If you aggregate the results over one input loop, the results for all input sources will be concatenated into one request to the logging server.
When you aggregate the inferences over time all results for all inputs will be combined into one request to the logging server.
Description
Value
Post each inference separately
-1
Aggregate inferences over one input loop
0
Aggregate every two seconds
2
Aggregate every ten seconds
10
Aggregate every thirty seconds
30
Aggregate every minute
60
Aggregate every X seconds
X
SaveConditional
Upload or post images below some certainty threshold. When posted, it converts the camera image(s) as a base64 encoded string to the defined endpoint. On when set to 1
SaveConditionalProbs
Probability threshold. Can be set to a value between 0.0 and 1.1. If the the threshold value is 0.0 no images will be sent to the API. If the threshold is higher than 0 the input image will be sent to the API when an inference result has a probability value below the threshold. If there are more detected classes, any detection in the result, independent of the detected class that is below the threshold will trigger that the image is sent to the API.
ImageEndpoint
Whether or not to make video stream images available through a shared memory interface (SHM).
Description
Value
No SHM images available
0
Input images available through SHM
1
Output images available through SHM
2
AlwaysOffline
Whether the Scailable AI Manager will be able to connect to the internet. If not, license and related settings will need to be configured explicitly. Contact us to get more information about our solutions for airgapped and other types of offline deployment.
Clients
Next to being able to control AI Managers through our cloud, it is also possible to then control multiple AI Managers through one central AI Manager. Contact us if you want to know more about this option.
NmsSensitivity
A percentage value, for the NMS post-processing, representing the confidence score below which some detected entities are considered false positives. For example, a value equal to 100 will result in less predictions than a value equal to 0. 
OnChange
Whether to only run inference when a change in the image is detected.
If 1 inference will only be run if a change between the current and previous frame is detected, controlled by OnChangePixelThreshold and OnChangeImageThreshold.
If 0 inference will be run on every frame received from the camera.
OnChangePixelThreshold
Threshold of change in a pixel value to be considered a changed pixel.
OnChangeImageThreshold
Percentage of pixels in frame necessary to be changed above OnChangePixelThresholdto be considered a changed frame.
ExternalTrigger
When this is activated, inference will not be run until a signal is received externally. A signal can be sent by calling the /triggerInference endpoint.
SaveImages
Whether to save input and/or output frames as images locally.
Base path of the save location is the full path set by SaveImagesPath. 
Description
Value
Do not save frames
0
Save full size input frames
1
Save model size input frames
2
​
SaveImagesPath
When SaveImages is not zero, images will be saved with the following directory structure:
[SaveImagesPath]/[%Y]/[%m]/[%d]
MOD_SCLBL_ENABLED
Advantech ICR router specific setting.
​
InputCameraXFormat	Type of input	Example
Image (JPEG, GIF, PNG)	http:// or https:// URL	http://test.com/test.jpg https://192.168.1.10
Image (JPEG, GIF, PNG)	local file URL	file://path/to/image/test.jpg
RTSP stream	rtsp:// URL	rtsp://test.com/stream.mjpg
MJPEG stream	http:// URL	http://test.com/stream.rtsp
V4L2 webcam	path to (usb) camera	/dev/video0
Gstreamer SHM	SHM path	/tmp/industrialcam
Description	Value
Image is fitted exactly to the tensor input dimensions without taking into account the original image's aspect ratio. As a result, the input tensor can be a "squashed" representation of the original input image.	0
Image is fitted to the tensor input aspect ratio by cutting edges of the image either vertically or horizontally in case the image aspect ratio differs from the tensor aspect ratio.. As a result, parts of the input image may not be part of the inference.	1
Image is fitted to the tensor input aspect ratio by adding black borders either horizontally or vertically in case the image aspect ratio differs from the tensor aspect ratio.	2
Description	Value
Image (JPEG, GIF, PNG)	jpg
RTSP stream	rtsp
MJPEG stream	mjpeg
V4L2 webcam	v4l2
Gstreamer SHM	shm
Description	Value
Post each inference separately	-1
Aggregate inferences over one input loop	0
Aggregate every two seconds	2
Aggregate every ten seconds	10
Aggregate every thirty seconds	30
Aggregate every minute	60
Aggregate every X seconds	X
Description	Value
No SHM images available	0
Input images available through SHM	1
Output images available through SHM	2
Description	Value
Do not save frames	0
Save full size input frames	1
Save model size input frames	2
Edge AI Manager structure
Edge AI Manager JSON Tensor Format
Last modified 11d ago