DenseNet-121: Optimized for Qualcomm Devices

Densenet is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.

This is based on the implementation of DenseNet-121 found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime	Precision	Chipset	SDK Versions	Download
ONNX	float	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
QNN_DLC	w8a8_mixed_int16	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit DenseNet-121 on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

• Custom weights (e.g., fine-tuned checkpoints)
• Custom input shapes
• Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for DenseNet-121 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

• Model checkpoint: Imagenet
• Input resolution: 224x224
• Number of parameters: 7.99M
• Model size (float): 30.5 MB
• Model size (w8a16): 8.72 MB
• Model size (w8a8): 8.30 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
DenseNet-121	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	0.678 ms	0 - 47 MB	NPU
DenseNet-121	ONNX	float	Snapdragon® 8 Elite Mobile	0.783 ms	0 - 46 MB	NPU
DenseNet-121	ONNX	float	Snapdragon® X2 Elite	0.742 ms	16 - 16 MB	NPU
DenseNet-121	ONNX	float	Snapdragon® X Elite	1.75 ms	15 - 15 MB	NPU
DenseNet-121	ONNX	float	Snapdragon® X Elite	1.75 ms	15 - 15 MB	NPU
DenseNet-121	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.064 ms	0 - 90 MB	NPU
DenseNet-121	ONNX	float	Qualcomm® QCS8550 (Proxy)	1.519 ms	0 - 18 MB	NPU
DenseNet-121	ONNX	float	Qualcomm® QCS9075	2.611 ms	1 - 3 MB	NPU
DenseNet-121	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.783 ms	0 - 46 MB	NPU
DenseNet-121	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	0.72 ms	1 - 42 MB	NPU
DenseNet-121	QNN_DLC	float	Snapdragon® 8 Elite Mobile	0.884 ms	0 - 42 MB	NPU
DenseNet-121	QNN_DLC	float	Snapdragon® X2 Elite	0.944 ms	1 - 1 MB	NPU
DenseNet-121	QNN_DLC	float	Snapdragon® X Elite	2.044 ms	1 - 1 MB	NPU
DenseNet-121	QNN_DLC	float	Snapdragon® X Elite	2.044 ms	1 - 1 MB	NPU
DenseNet-121	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.215 ms	1 - 78 MB	NPU
DenseNet-121	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	7.866 ms	1 - 38 MB	NPU
DenseNet-121	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	1.807 ms	1 - 2 MB	NPU
DenseNet-121	QNN_DLC	float	Qualcomm® SA8775P	2.696 ms	1 - 41 MB	NPU
DenseNet-121	QNN_DLC	float	Qualcomm® SA8775P	2.696 ms	1 - 41 MB	NPU
DenseNet-121	QNN_DLC	float	Qualcomm® SA8775P	2.696 ms	1 - 41 MB	NPU
DenseNet-121	QNN_DLC	float	Qualcomm® QCS9075	2.761 ms	1 - 3 MB	NPU
DenseNet-121	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	3.287 ms	0 - 75 MB	NPU
DenseNet-121	QNN_DLC	float	Qualcomm® SA7255P	7.866 ms	1 - 38 MB	NPU
DenseNet-121	QNN_DLC	float	Qualcomm® SA8295P	3.066 ms	0 - 35 MB	NPU
DenseNet-121	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.884 ms	0 - 42 MB	NPU
DenseNet-121	QNN_DLC	w8a8_mixed_int16	Snapdragon® 8 Elite Gen 5 Mobile	1.164 ms	0 - 69 MB	NPU
DenseNet-121	QNN_DLC	w8a8_mixed_int16	Snapdragon® 8 Elite Mobile	1.563 ms	0 - 57 MB	NPU
DenseNet-121	QNN_DLC	w8a8_mixed_int16	Snapdragon® X2 Elite	1.457 ms	0 - 0 MB	NPU
DenseNet-121	QNN_DLC	w8a8_mixed_int16	Snapdragon® X Elite	3.216 ms	0 - 0 MB	NPU
DenseNet-121	QNN_DLC	w8a8_mixed_int16	Snapdragon® X Elite	3.216 ms	0 - 0 MB	NPU
DenseNet-121	QNN_DLC	w8a8_mixed_int16	Snapdragon® 8 Gen 3 Mobile	2.09 ms	0 - 81 MB	NPU
DenseNet-121	QNN_DLC	w8a8_mixed_int16	Qualcomm® QCS8275 (Proxy)	5.93 ms	0 - 63 MB	NPU
DenseNet-121	QNN_DLC	w8a8_mixed_int16	Qualcomm® QCS8550 (Proxy)	2.915 ms	0 - 2 MB	NPU
DenseNet-121	QNN_DLC	w8a8_mixed_int16	Qualcomm® SA8775P	3.273 ms	0 - 63 MB	NPU
DenseNet-121	QNN_DLC	w8a8_mixed_int16	Qualcomm® SA8775P	3.273 ms	0 - 63 MB	NPU
DenseNet-121	QNN_DLC	w8a8_mixed_int16	Qualcomm® SA8775P	3.273 ms	0 - 63 MB	NPU
DenseNet-121	QNN_DLC	w8a8_mixed_int16	Qualcomm® QCS9075	3.256 ms	2 - 4 MB	NPU
DenseNet-121	QNN_DLC	w8a8_mixed_int16	Qualcomm® SA7255P	5.93 ms	0 - 63 MB	NPU
DenseNet-121	QNN_DLC	w8a8_mixed_int16	Snapdragon® 8 Elite For Galaxy Mobile	1.563 ms	0 - 57 MB	NPU
DenseNet-121	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	0.722 ms	0 - 56 MB	NPU
DenseNet-121	TFLITE	float	Snapdragon® 8 Elite Mobile	0.884 ms	0 - 57 MB	NPU
DenseNet-121	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.215 ms	0 - 94 MB	NPU
DenseNet-121	TFLITE	float	Qualcomm® QCS8275 (Proxy)	7.947 ms	0 - 52 MB	NPU
DenseNet-121	TFLITE	float	Qualcomm® QCS8550 (Proxy)	1.828 ms	0 - 6 MB	NPU
DenseNet-121	TFLITE	float	Qualcomm® SA8775P	2.73 ms	0 - 56 MB	NPU
DenseNet-121	TFLITE	float	Qualcomm® SA8775P	2.73 ms	0 - 56 MB	NPU
DenseNet-121	TFLITE	float	Qualcomm® SA8775P	2.73 ms	0 - 56 MB	NPU
DenseNet-121	TFLITE	float	Qualcomm® QCS9075	2.811 ms	0 - 18 MB	NPU
DenseNet-121	TFLITE	float	Qualcomm® QCS8450 (Proxy)	3.286 ms	0 - 86 MB	NPU
DenseNet-121	TFLITE	float	Qualcomm® SA7255P	7.947 ms	0 - 52 MB	NPU
DenseNet-121	TFLITE	float	Qualcomm® SA8295P	3.056 ms	0 - 49 MB	NPU
DenseNet-121	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.884 ms	0 - 57 MB	NPU

License

• The license for the original implementation of DenseNet-121 can be found here.

References

• Densely Connected Convolutional Networks
• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.