1. Cordatus Device Registration
In order to start using Cordatus on your devices, you need to register the device to platform by signing in to Cordatus first. You can log in with two different methods;
Login with Token
If you choose the Login with Token option, You will be prompted to enter a token for the authorization:
Open Cordatus Web Interface from your web browser and go to Devices tab from the upper pane.
Click on the Add Device button from the upper right and give your device a unique name and click Create button.
Your device will be listed as shown in the below picture:
Next, click on the Generate Token button and you will be given a fresh token that you can authorize your device with.
Copy the token and paste it to Cordatus Client App then clink on the LOG IN button.
Now you can see the main screen of the Cordatus Client App.
Also you can see your unique device on the list as online.
You can get usage metrics, see created containers and inspect system details by clicking your device from the list.
Login with Account Credentials
If you prefer to login to Cordatus with your email and password, just select the Email option from the login menu.
Next, enter your email address and password that you used to register to Cordatus.
Now you can see the main screen of the Cordatus Client App and your device listed as online on Cordatus Web Interface.
2. Claiming NVIDIA GPU Cloud (NGC) Token
In order to use NGC containers from within Cordatus, first you need to create an account on NGC from following this link and claim your API Key.
After you signup on NGC, you need to login to your account from https://ngc.nvidia.com/signin/email .
To claim your NGC Token:
- In the top right corner, click your user account icon and select Setup.
Click Get API key to open the Setup > API Key page. The API Key is the mechanism used to authenticate your access to the NGC container registry.
Click Generate API Key to generate your API key. A warning message appears to let you know that your old API key will become invalid if you create a new key.
- Click Confirm to generate the key. Your API key appears.
You only need to generate an API Key once. NGC does not save your key, so store it in a secure place. (You can copy your API Key to the clipboard by clicking the copy icon to the right of the API key. )
Should you lose your API Key, you can generate a new one from the NGC website. When you generate a new API Key, the old one is invalidated.
- Since now you have the NGC token, you can enter it on Cordatus Client App to use NGC containers from within Cordatus.
You can enter it from text input area in Settings > NGC tab and click Save button.
3. First Demo: Cordatus Inference Engine
In this very first demo of Cordatus AI Platform, you will see a high performance real-time object detection. You can use either any USB Webcam that is connected to your device or all cameras of your smartphone.
CIE Demo with Webcam
To utilize your webcams that is/are connected to your device with Cordatus Inference Engine;
First, open Cordatus Web Interface and navigate to Devices tab.
Next, click Start Application from the middle-left side of the page.
Choose the camera you prefer and click Test Camera button. You can now see the raw stream on the same page.
After the camera selection, navigate to the bottom of the page and click Next button.
In the second step of the demo, you need to choose a deep learning model from the model list provided under Deep Learning Models tab.
For the last step, you need to select a device that is going to process the stream. You can process your camera stream on any device you registered to Cordatus. It can be your PC, Workstation or any other remote server.
CIE Demo with Smartphone Camera
First, go to Cordatus Web Interface from your smartphone's web browser.
Open the menu from upper right pane and click Devices from the list.
Now you can see your PCs, Workstations or Remote Servers from the Device List.
To start the demo from your smartphone, select Start Application tab.
Your smartphone's cameras (Local Cameras) will be listed along with the cameras connected to your PCs, Workstations or Remote Servers (Remote Cameras). You can test and then select the camera you want.
After you choose the camera, scroll down and click Next Step.
Now you need to select a pre-trained deep learning model from the list.
As the last step, you need to select a device that will process the stream. This way, you can process your smartphone's camera stream on your GPU enabled PCs, Workstations or Remote Servers.
Select the processing device and click START APPLICATION button.