Why DeGirum?
Access Models in Minutes
Run pre-trained models instantly.
Hardware Agnostic
Test and prototype on diverse edge devices.
Flexible Workflows
Use browser-based no-code tools or PySDK for coding.
Edge-Optimized Hardware
Maximize performance with Orca accelerators.
Start Prototyping Today
Choose your workflow—run models effortlessly in your browser or dive into code-based development with PySDK.
// initiate DeGirum SDK package
let dg = new dg_sdk();
// load mobilenet model from deGirum's public model zoo to run in the cloud
const secretToken = prompt('Enter secret token:');
let zoo = await dg.connect('cloud', 'https://рhub.degirum.com/degirum/public', secretToken);
let model = await zoo.loadModel('mobilenet_v2_ssd_coco--300x300_quant_n2x_orca1_1', { autoScaleDrawing: true, overlayShowProbabilities: true});
// perform AI inference of an image specified by URL
const result = await model.predict('https://raw.githubusercontent.com/DeGirum/PySDKExamples/main/images/TwoCats.jpg');
// print numeric results
console.log('Result:', result);
// show graphical results
let canvas = document.getElementById('outputCanvas');
model.displayResultToCanvas(result, canvas);
# import DeGirum PySDK package
import degirum as dg
# load mobilenet model from deGirum's public model zoo to run in the cloud
model = dg.load_model(
model_name = "mobilenet_v2_ssd_coco--300x300_quant_n2x_orca1_1",
inference_host_address = dg.CLOUD,
zoo_url = "degirum/public",
token = "your_cloud_access_token",
image_backend='pil'
)
# perform AI inference of an image specified by URL
result = model("https://raw.githubusercontent.com/DeGirum/PySDKExamples/main/images/TwoCats.jpg")
# print numeric results
print(result)
# show graphical results
result.image_overlay.show()
