Edit model card

YOLOv8-Detection-Quantized: Optimized for Mobile Deployment

Quantized real-time object detection optimized for mobile and edge by Ultralytics

Ultralytics YOLOv8 is a machine learning model that predicts bounding boxes and classes of objects in an image. This model is post-training quantized to int8 using samples from the COCO dataset.

This model is an implementation of YOLOv8-Detection-Quantized found here.

More details on model performance accross various devices, can be found here.

Model Details

  • Model Type: Object detection
  • Model Stats:
    • Model checkpoint: YOLOv8-N
    • Input resolution: 640x640
    • Number of parameters: 3.18M
    • Model size: 3.26 MB
Model Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Precision Primary Compute Unit Target Model
YOLOv8-Detection-Quantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 1.912 ms 0 - 91 MB INT8 NPU --
YOLOv8-Detection-Quantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 2.249 ms 1 - 9 MB INT8 NPU --
YOLOv8-Detection-Quantized Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 5.532 ms 3 - 10 MB INT8 NPU --
YOLOv8-Detection-Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 1.275 ms 0 - 57 MB INT8 NPU --
YOLOv8-Detection-Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 1.495 ms 0 - 28 MB INT8 NPU --
YOLOv8-Detection-Quantized Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 4.081 ms 7 - 159 MB INT8 NPU --
YOLOv8-Detection-Quantized Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 1.007 ms 0 - 38 MB INT8 NPU --
YOLOv8-Detection-Quantized Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 1.421 ms 0 - 25 MB INT8 NPU --
YOLOv8-Detection-Quantized Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 3.975 ms 3 - 119 MB INT8 NPU --
YOLOv8-Detection-Quantized RB3 Gen 2 (Proxy) QCS6490 Proxy TFLITE 4.44 ms 0 - 42 MB INT8 NPU --
YOLOv8-Detection-Quantized RB3 Gen 2 (Proxy) QCS6490 Proxy QNN 5.809 ms 1 - 9 MB INT8 NPU --
YOLOv8-Detection-Quantized RB5 (Proxy) QCS8250 Proxy TFLITE 44.972 ms 3 - 11 MB INT8 NPU --
YOLOv8-Detection-Quantized QCS8550 (Proxy) QCS8550 Proxy TFLITE 1.89 ms 0 - 1 MB INT8 NPU --
YOLOv8-Detection-Quantized QCS8550 (Proxy) QCS8550 Proxy QNN 1.95 ms 1 - 2 MB INT8 NPU --
YOLOv8-Detection-Quantized SA8255 (Proxy) SA8255P Proxy TFLITE 1.9 ms 0 - 2 MB INT8 NPU --
YOLOv8-Detection-Quantized SA8255 (Proxy) SA8255P Proxy QNN 1.967 ms 1 - 3 MB INT8 NPU --
YOLOv8-Detection-Quantized SA8775 (Proxy) SA8775P Proxy TFLITE 1.911 ms 0 - 8 MB INT8 NPU --
YOLOv8-Detection-Quantized SA8775 (Proxy) SA8775P Proxy QNN 1.95 ms 1 - 2 MB INT8 NPU --
YOLOv8-Detection-Quantized SA8650 (Proxy) SA8650P Proxy TFLITE 1.907 ms 0 - 32 MB INT8 NPU --
YOLOv8-Detection-Quantized SA8650 (Proxy) SA8650P Proxy QNN 1.952 ms 1 - 2 MB INT8 NPU --
YOLOv8-Detection-Quantized SA8295P ADP SA8295P TFLITE 2.828 ms 0 - 37 MB INT8 NPU --
YOLOv8-Detection-Quantized SA8295P ADP SA8295P QNN 3.069 ms 1 - 7 MB INT8 NPU --
YOLOv8-Detection-Quantized QCS8450 (Proxy) QCS8450 Proxy TFLITE 2.12 ms 0 - 57 MB INT8 NPU --
YOLOv8-Detection-Quantized QCS8450 (Proxy) QCS8450 Proxy QNN 2.502 ms 1 - 30 MB INT8 NPU --
YOLOv8-Detection-Quantized Snapdragon X Elite CRD Snapdragon® X Elite QNN 2.279 ms 1 - 1 MB INT8 NPU --
YOLOv8-Detection-Quantized Snapdragon X Elite CRD Snapdragon® X Elite ONNX 6.307 ms 7 - 7 MB INT8 NPU --

License

  • The license for the original implementation of YOLOv8-Detection-Quantized can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Usage and Limitations

Model may not be used for or in connection with any of the following applications:

  • Accessing essential private and public services and benefits;
  • Administration of justice and democratic processes;
  • Assessing or recognizing the emotional state of a person;
  • Biometric and biometrics-based systems, including categorization of persons based on sensitive characteristics;
  • Education and vocational training;
  • Employment and workers management;
  • Exploitation of the vulnerabilities of persons resulting in harmful behavior;
  • General purpose social scoring;
  • Law enforcement;
  • Management and operation of critical infrastructure;
  • Migration, asylum and border control management;
  • Predictive policing;
  • Real-time remote biometric identification in public spaces;
  • Recommender systems of social media platforms;
  • Scraping of facial images (from the internet or otherwise); and/or
  • Subliminal manipulation
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Examples
Inference API (serverless) does not yet support pytorch models for this pipeline type.