Elgato_dark/ultralytics
1
0
Fork 0
mirror of https://github.com/ultralytics/ultralytics synced 2026-05-23 17:18:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

Update DeepStream doc with YOLO11 support (#19958)

Browse source
This commit is contained in:
Lakshantha Dissanayake 2025-04-01 04:18:33 -07:00 committed by GitHub
parent d650885b2e
commit bf6602af98
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 10 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
docs/en/guides/deepstream-nvidia-jetson.md
View file

@ -66,17 +66,13 @@ Here we are using [marcoslucianops/DeepStream-Yolo](https://github.com/marcosluc
git clone https://github.com/marcoslucianops/DeepStream-Yolo
```
3. Copy the `export_yoloV8.py` file from `DeepStream-Yolo/utils` directory to the `ultralytics` folder
3. Copy the `export_yolo11.py` file from `DeepStream-Yolo/utils` directory to the `ultralytics` folder
```bash
cp ~/DeepStream-Yolo/utils/export_yoloV8.py ~/ultralytics
cp ~/DeepStream-Yolo/utils/export_yolo11.py ~/ultralytics
cd ultralytics
```
!!! note
`export_yoloV8.py` works for both YOLOv8 and YOLO11 models.
4. Download Ultralytics YOLO11 detection model (.pt) of your choice from [YOLO11 releases](https://github.com/ultralytics/assets/releases). Here we use [yolo11s.pt](https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11s.pt).
```bash
@ -90,12 +86,12 @@ Here we are using [marcoslucianops/DeepStream-Yolo](https://github.com/marcosluc
5. Convert model to ONNX
```bash
python3 export_yoloV8.py -w yolo11s.pt
python3 export_yolo11.py -w yolo11s.pt
```
!!! note "Pass the below arguments to the above command"
For DeepStream 6.0.1, use opset 12 or lower. The default opset is 16.
For DeepStream 5.1, remove the `--dynamic` arg and use `opset` 12 or lower. The default `opset` is 17.
```bash
--opset 12
@ -169,7 +165,7 @@ Here we are using [marcoslucianops/DeepStream-Yolo](https://github.com/marcosluc
make -C nvdsinfer_custom_impl_Yolo clean && make -C nvdsinfer_custom_impl_Yolo
```
9. Edit the `config_infer_primary_yoloV8.txt` file according to your model (for YOLO11s with 80 classes)
9. Edit the `config_infer_primary_yolo11.txt` file according to your model (for YOLO11s with 80 classes)
```bash
[property]
@ -186,7 +182,7 @@ Here we are using [marcoslucianops/DeepStream-Yolo](https://github.com/marcosluc
...
[primary-gie]
...
config-file=config_infer_primary_yoloV8.txt
config-file=config_infer_primary_yolo11.txt
```
11. You can also change the video source in `deepstream_app_config` file. Here a default video file is loaded
@ -212,7 +208,7 @@ deepstream-app -c deepstream_app_config.txt
!!! tip
If you want to convert the model to FP16 precision, simply set `model-engine-file=model_b1_gpu0_fp16.engine` and `network-mode=2` inside `config_infer_primary_yoloV8.txt`
If you want to convert the model to FP16 precision, simply set `model-engine-file=model_b1_gpu0_fp16.engine` and `network-mode=2` inside `config_infer_primary_yolo11.txt`
## INT8 Calibration
@ -271,7 +267,7 @@ If you want to use INT8 precision for inference, you need to follow the steps be
Higher INT8_CALIB_BATCH_SIZE values will result in more accuracy and faster calibration speed. Set it according to you GPU memory.
8. Update the `config_infer_primary_yoloV8.txt` file
8. Update the `config_infer_primary_yolo11.txt` file
From
@ -417,12 +413,12 @@ Yes, the guide for deploying Ultralytics YOLO11 with the DeepStream SDK and Tens
### How can I convert a YOLO11 model to ONNX for DeepStream?
To convert a YOLO11 model to ONNX format for deployment with DeepStream, use the `utils/export_yoloV8.py` script from the [DeepStream-Yolo](https://github.com/marcoslucianops/DeepStream-Yolo) repository.
To convert a YOLO11 model to ONNX format for deployment with DeepStream, use the `utils/export_yolo11.py` script from the [DeepStream-Yolo](https://github.com/marcoslucianops/DeepStream-Yolo) repository.
Here's an example command:
```bash
python3 utils/export_yoloV8.py -w yolo11s.pt --opset 12 --simplify
python3 utils/export_yolo11.py -w yolo11s.pt --opset 12 --simplify
```
For more details on model conversion, check out our [model export section](../modes/export.md).