Chiebot-Mirror
/
ultralytics
9
0
Fork 1
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Optimize Sony IMX500 doc (#19421)

Browse Source
pull/19122/head^2
Lakshantha Dissanayake 2 weeks ago committed by GitHub
parent c23f68ac67
commit 941c1743e6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 17 additions and 17 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 34
      docs/en/integrations/sony-imx500.md

34
docs/en/integrations/sony-imx500.md
Unescape View File

@ -54,7 +54,7 @@ Export an Ultralytics YOLOv8 model to IMX500 format and run inference with the e
model = YOLO("yolov8n.pt")
# Export the model
model.export(format="imx") # exports with PTQ quantization by default
model.export(format="imx", data="coco8.yaml") # exports with PTQ quantization by default
# Load the exported model
imx_model = YOLO("yolov8n_imx_model")
@ -67,12 +67,23 @@ Export an Ultralytics YOLOv8 model to IMX500 format and run inference with the e
```bash
# Export a YOLOv8n PyTorch model to imx format with Post-Training Quantization (PTQ)
yolo export model=yolov8n.pt format=imx
yolo export model=yolov8n.pt format=imx data=coco8.yaml
# Run inference with the exported model
yolo predict model=yolov8n_imx_model source='https://ultralytics.com/images/bus.jpg'
```
## Export Arguments
| Argument | Type | Default | Description |
| -------- | ---------------- | -------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `format` | `str` | `'imx'` | Target format for the exported model, defining compatibility with various deployment environments. |
| `imgsz` | `int` or `tuple` | `640` | Desired image size for the model input. Can be an integer for square images or a tuple `(height, width)` for specific dimensions. |
| `int8` | `bool` | `True` | Activates INT8 quantization, further compressing the model and speeding up inference with minimal [accuracy](https://www.ultralytics.com/glossary/accuracy) loss, primarily for edge devices. |
| `data` | `str` | `'coco8.yaml'` | Path to the [dataset](https://docs.ultralytics.com/datasets) configuration file (default: `coco8.yaml`), essential for quantization. |
For more details about the export process, visit the [Ultralytics documentation page on exporting](../modes/export.md).
The export process will create an ONNX model for quantization validation, along with a directory named `<model-name>_imx_model`. This directory will include the `packerOut.zip` file, which is essential for packaging the model for deployment on the IMX500 hardware. Additionally, the `<model-name>_imx_model` folder will contain a text file (`labels.txt`) listing all the labels associated with the model.
```bash
@ -85,17 +96,6 @@ yolov8n_imx_model
└── yolov8n_imx500_model.pbtxt
```
## Export Arguments
| Argument | Type | Default | Description |
| -------- | ---------------- | -------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `format` | `str` | `'imx'` | Target format for the exported model, defining compatibility with various deployment environments. |
| `imgsz` | `int` or `tuple` | `640` | Desired image size for the model input. Can be an integer for square images or a tuple `(height, width)` for specific dimensions. |
| `int8` | `bool` | `True` | Activates INT8 quantization, further compressing the model and speeding up inference with minimal [accuracy](https://www.ultralytics.com/glossary/accuracy) loss, primarily for edge devices. |
| `data` | `str` | `'coco8.yaml'` | Path to the [dataset](https://docs.ultralytics.com/datasets) configuration file (default: `coco8.yaml`), essential for quantization. |
For more details about the export process, visit the [Ultralytics documentation page on exporting](../modes/export.md).
## Using IMX500 Export in Deployment
After exporting Ultralytics YOLOv8n model to IMX500 format, it can be deployed to Raspberry Pi AI Camera for inference.
@ -163,7 +163,7 @@ cd examples/imx500
Step 3: Run YOLOv8 object detection, using the labels.txt file that has been generated during the IMX500 export.
```bash
python imx500_object_detection_demo.py --model <path to network.rpk> --fps 25 --bbox-normalization --ignore-dash-labels --bbox-order xy --labels <path to labels.txt>
python imx500_object_detection_demo.py --model <path to network.rpk> --fps 17 --bbox-normalization --ignore-dash-labels --bbox-order xy --labels <path to labels.txt>
```
Then you will be able to see live inference output as follows
@ -178,7 +178,7 @@ YOLOv8 benchmarks below were run by the Ultralytics team on Raspberry Pi AI Came
| Model | Format | Status | Size (MB) | mAP50-95(B) | Inference time (ms/im) |
| ------- | ------ | ------ | --------- | ----------- | ---------------------- |
| YOLOv8n | imx | ✅ | 2.9 | 0.522 | 66.66 |
| YOLOv8n | imx | ✅ | 2.9 | 0.522 | 58.82 |
!!! note
@ -296,7 +296,7 @@ Software:
Based on Ultralytics benchmarks on Raspberry Pi AI Camera:
- YOLOv8n achieves 66.66ms inference time per image
- YOLOv8n achieves 58.82ms inference time per image
- mAP50-95 of 0.522 on COCO8 dataset
- Model size of only 2.9MB after quantization
@ -322,5 +322,5 @@ After exporting to IMX500 format:
3. Run inference using the generated RPK file:
```bash
python imx500_object_detection_demo.py --model <path to network.rpk> --fps 25 --bbox-normalization --labels <path to labels.txt>
python imx500_object_detection_demo.py --model <path to network.rpk> --fps 17 --bbox-normalization --labels <path to labels.txt>
```

Write Preview
Loading…
Cancel
Save