Transformer based object detector with ResNet101 backbone.
DETR is a machine learning model that can detect objects (trained on COCO dataset).
SC8380
Inference Time : 15.2 ms
Memory Usage : 3 MB
Layers : 992 NPU
Model checkpoint:ResNet101
Input resolution:480x480
Number of parameters:60.3M
Model size:230 MB
Applicable Scenarios : Factory Automation, Robotic Navigation, Camera
SC8380
Source Model: APACHE-2.0
Deployable Model: AI Model Hub License