From 496e6a3b8680e4ccd4f190e30841748aee2cb89c Mon Sep 17 00:00:00 2001 From: Amir Servi <131249114+ServiAmirPM@users.noreply.github.com> Date: Wed, 13 Nov 2024 21:15:45 +0200 Subject: [PATCH] Update sony-imx500.md (#17491) Co-authored-by: Glenn Jocher --- docs/en/integrations/sony-imx500.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/en/integrations/sony-imx500.md b/docs/en/integrations/sony-imx500.md index 335daf51fc..88338ebb67 100644 --- a/docs/en/integrations/sony-imx500.md +++ b/docs/en/integrations/sony-imx500.md @@ -29,7 +29,7 @@ The IMX500 works with quantized models. Quantization makes models smaller and fa **IMX500 Key Features:** -- **Metadata Output:** Instead of transmitting full images, the IMX500 outputs only metadata, minimizing data size, reducing bandwidth, and lowering costs. +- **Metadata Output:** Instead of transmitting images only, the IMX500 can output both image and metadata (inference result), and can output metadata only for minimizing data size, reducing bandwidth, and lowering costs. - **Addresses Privacy Concerns:** By processing data on the device, the IMX500 addresses privacy concerns, ideal for human-centric applications like person counting and occupancy tracking. - **Real-time Processing:** Fast, on-sensor processing supports real-time decisions, perfect for edge AI applications such as autonomous systems. @@ -247,7 +247,7 @@ Export to IMX500 format has wide applicability across industries. Here are some ## Conclusion -Exporting Ultralytics YOLOv8 models to Sony's IMX500 format allows you to deploy your models for efficient inference on IMX500-based cameras. By leveraging advanced quantization and pruning techniques, you can reduce model size and improve inference speed without significantly compromising accuracy. +Exporting Ultralytics YOLOv8 models to Sony's IMX500 format allows you to deploy your models for efficient inference on IMX500-based cameras. By leveraging advanced quantization techniques, you can reduce model size and improve inference speed without significantly compromising accuracy. For more information and detailed guidelines, refer to Sony's [IMX500 website](https://developer.aitrios.sony-semicon.com/en/raspberrypi-ai-camera). @@ -271,7 +271,7 @@ The export process will create a directory containing the necessary files for de The IMX500 format offers several important advantages for edge deployment: - On-chip AI processing reduces latency and power consumption -- Outputs metadata instead of full images, minimizing bandwidth usage +- Outputs both image and metadata (inference result) instead of images only - Enhanced privacy by processing data locally without cloud dependency - Real-time processing capabilities ideal for time-sensitive applications - Optimized quantization for efficient model deployment on resource-constrained devices