DETR-ResNet50 is an efficient object detection model that combines DETR (DEtection TRansformers) with the ResNet-50 backbone network. DETR is an end-to-end object detection framework based on Transformer architecture, utilizing self-attention mechanisms to detect objects in images without relying on traditional region proposals. ResNet-50 serves as the backbone for feature extraction, leveraging residual connections to effectively learn multi-level features of the image, enhancing detection capability. DERT-ResNet50 strikes a balance between high detection accuracy and reduced complexity, making it suitable for object detection tasks in complex scenes, with applications in autonomous driving, video surveillance, and real-time object detection.

Source model

• Input shape: 480x480
• Number of parameters: 39.60M
• Model size: 158.03M
• Output shape: 1x100x92, 1x100x4

Source model repository: DETR-ResNet50

When the user has fine-tuned the source model, the model conversion process must be performed again.

Users can refer to either of the following two methods to complete the model conversion:

• Using AIMO for model conversion: Click Model Conversion Reference in the Performance Reference section on the right to view the conversion steps.

• Using Qualcomm QNN for model conversion: Please refer to the Qualcomm QNN Documentation.

The model performance benchmarks and example code provided by Model Farm are all implemented based on the AIDLux AidLite SDK.

For models in .bin format, you can use either of the following two inference engines to run inference on Qualcomm chips:

Inference using APLUX AidLite: please refer to the APLUX AidLite Developer Documentation

Inference using Qualcomm QNN: Please refer to the Qualcomm QNN Documentation

Inference Example Code

The inference example code is implemented using the AidLite SDK.

Click Model & Code to download the model files and the inference code package. The file structure is as follows:

/model_farm_{model_name}_aidlite
    
    |__ models # folder where model files are stored

    |__ python # aidlite python model inference example

    |__ cpp # aidlite cpp model inference example

    |__ README.md