YOLOv5m 640x480

Model Overview

A YOLOv5m model for object detection optimized for 640x480 resolution, offering a balance between speed and accuracy.

The YOLOv5m 640x480 model is developed and optimized for the Synaptics Astra™ SL1680 processor NPU and SL1640 processor NPU.

Model Features

• Model Type: Object Detection
• Input Size: 640x480
• Output Size: 640x480

ℹ️ INFO: This model is ready to use on Synaptics Astra Machina boards. An NPU optimized version of the YOLOv5m 640x480 is installed in the Astra SDK Image.

Deployment on Synaptics Astra SL1600 Series

This particular model is compiled for Synaptics Astra SL1680 processor. You can find this model already pre-installed on Machina™ Dev kit with SL1680 processor.

You can also find the same model compiled for Synaptics Astra SL1640 processor pre-installed on Machina™ Dev kit with SL1640 processor.

Synaptics Astra Machina™ is Modular developer kit for Astra SL-Series of high-performance IoT processors with integrated Synaptics Veros™ wireless connectivity solution. Learn more here

Application binary

The synap_cli_od command line application allows running object detection models like YOLOv5m 640x480.

Inputs:

• The converted synap model (.synap extension)
• Optionally, a confidence threshold for detected objects
• One or more images (jpeg or png format)

Outputs:

• A list of detected objects for each input image, including:
  • Bounding box
  • Class index
  • Confidence score

Command line usage on Astra SL1680 and SL1640:

MODELS=/usr/share/synap/models/

cd $MODELS/object_detection/coco/model/yolo_v5/yolov5m-640x480

synap_cli_od -m model.synap input_image.jpg

Example output on SL1680:

Input image: input_image.jpg (w = 640, h = 480, c = 3)
Detection time: 118.82 ms
#   Score  Class  Position  Size     Description
0   0.95       0   94,193    62,143  person

ℹ️ INFO: JPEG/PNG input images are resized in software to the network input tensor size.

💡NOTE: Ensure the output format is defined during model conversion. Missing format details can result in errors such as "Failed to initialize detector".

Performance on NPU

Processors	Inference Time (ms)
SL1680	118.82
SL1640	178

Optimize and Customize the model

Advanced users may wish to customize the source model and recompile it for the Synaptics Astra NPU. Please refer to the Bring Your Own Model section for more information.

For reference, the .synap format model provided on the firmware image was compiled for the Synaptics Astra NPU with the following .yaml settings:

data_layout: default
outputs:
  - dequantize: true
    format: yolov5

License

Both the source model and the compiled model for on-device deployment are licensed under AGPL-3.0.

Learn More

• Synaptics AI Developer Zone: Get started with documentation, tutorials and resources for your Edge AI journey.
• Astra Support Portal: Connect with our engineering team and community.