System Settings
The VisionAI Observ smart detection platform system can manage current machine resources and understand their utilization, effectively leveraging existing resources to maximize computation.
Last updated
The VisionAI Observ smart detection platform system can manage current machine resources and understand their utilization, effectively leveraging existing resources to maximize computation.
Last updated
Manage your system for a clear view of resources. Click on the video below for a quick overview:
Enter "System Management" to view the current status of computing machine resources. Click "Config" to edit.
Type: Machine type, currently supports general x86 servers, cloud servers (Azure, AWS, GCP, etc.), and Orin NX type AIoT computing resources.
Name: Machine name.
Cluster: The cluster to which the machine belongs. Currently, the Kubernetes system architecture automatically allocates the computational resources needed for tasks within a cluster.
IP: Machine IP address.
Status: The current connection status of the machine.
CPU / Memory / Disk: The usage of the machine's CPU, Memory, and Disk. If resource usage exceeds 85%, it is necessary to be cautious of potential overloading and the risk of unstable detection or operation.
Deployed Model: The deployed models on this machine. Clicking "Config" allows you to switch the AI model in operation (compatibility of AI models with the machine should be noted).
After clicking "Config," you can decide on the AI models to run on server machines (on-premise x86 servers or cloud machines):
The system displays the name of the GPU on the current machine and its GPU Memory / Utility usage. If the machine has multiple GPUs, multiple fields will be shown (as in the following example).
You can decide to deploy the AI models you need on any GPU of the machine.
Depending on the computing power of different types of machines, up to 20 AI models can be placed.
Clicking "Apply" will apply the new AI model settings.
Tip: Applying and deploying a new AI model takes time, possibly several minutes or more depending on network speed. During this time, tasks using this AI Model will be paused until the new AI model setup is complete. Please be patient and wait for all settings to be properly finalized.
Note: If the GPU Memory is fully loaded, adding new AI models to run may fail. You can solve this problem by shutting down some AI models that are not in use.
After clicking "Config," you can configure the AIoT machine:
Name: Machine name.
Cluster: Machine Cluster name.
Organization: The organization to which the machine belongs, related to which organization's tasks can use this machine. You can use this method to isolate and manage resource usage.
License: When adding an AIoT machine for the first time, it needs to be bound with a license. The license number will determine the following contents of this machine:
Streams: Authorized number of streams.
Scenario: Authorized detection scenarios.
Period: License validity period.
Status: License status.
Webhook: Enter the URL endpoint where the Webhook should send notifications. This URL is your listener endpoint, a server specifically designed to receive incoming HTTP/HTTP POST notification messages triggered by events (Example: https://www.yourwebsite.com/webhook-listener).
Click "Save" to modify settings.
Note: When the license expires, the system will automatically terminate the running tasks, but task data will be retained until then.
You can understand the current status of machine resource utilization through System Management, effectively using existing resources to maximize computation.
