Qualcomm® AI HubAI Hub
HomeCompute ModelsDETR-ResNet50-DC5

DETR-ResNet50-DC5

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

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

Snapdragon® X Elite
TorchScripttoONNX Runtime
117ms
Inference Time
21MB
Memory Usage
737NPU
Layers

Technical Details

Model checkpoint:ResNet50-DC5
Input resolution:480x480
Number of parameters:42.2M
Model size:159 MB

Applicable Scenarios

  • Factory Automation
  • Robotic Navigation
  • Camera

Licenses

Source Model:APACHE-2.0
Deployable Model:AI Model Hub License

Supported Compute Chipsets

  • Snapdragon® X Elite