Qualcomm® AI HubAI Hub
HomeCompute ModelsDETR-ResNet50

DETR-ResNet50

Transformer based object detector with ResNet50 backbone.

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

Snapdragon® X Elite
TorchScripttoONNX Runtime
16.9ms
Inference Time
111MB
Memory Usage
737NPU
Layers

Technical Details

Model checkpoint:ResNet50
Input resolution:480x480
Number of parameters:41.3M
Model size:158 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