Qualcomm® AI HubAI Hub

DETR-ResNet50

Transformer based object detector with ResNet50 backbone.

DETR is a machine learning model that can detect objects (trained on COCO dataset).

Not supported

This model is currently not supported on any IoT chipset.

To see performance metrics for this model on other chipsets, click the button below.

View for other chipsets
Model RepositoryHugging FaceResearch Paper

Technical Details

Input resolution:480x480
Model checkpoint:ResNet50
Model size (float):158 MB
Number of parameters:41.4M

Applicable Scenarios

  • Factory Automation
  • Robotic Navigation
  • Camera

License

Model:APACHE-2.0

Supported IoT Devices

  • Dragonwing IQ-8275 EVK
  • Dragonwing IQ-9075 EVK
  • Dragonwing IQ-X5121
  • Dragonwing IQ-X7181
  • Dragonwing Q-8750
  • QCS8550 (Proxy)

Supported IoT Chipsets

  • Qualcomm® Dragonwing™ IQ-X7181
  • Qualcomm® Dragonwing™ QCS8275
  • Qualcomm® Dragonwing™ QCS8550 (Proxy)
  • Qualcomm® Dragonwing™ Q-8750
  • Qualcomm® Dragonwing™ IQ-9075

Related Models

See all models
View details for the DETR-ResNet50-DC5 model.

DETR-ResNet50-DC5

Transformer based object detector with ResNet50 backbone (dilated C5 stage).

View details for the DETR-ResNet101-DC5 model.

DETR-ResNet101-DC5

Transformer based object detector with ResNet101 backbone (dilated C5 stage).

View details for the DETR-ResNet101 model.

DETR-ResNet101

Transformer based object detector with ResNet101 backbone.

Looking for more? See models created by industry leaders.

Discover Model Makers