thebears/deepstream_yolo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fixes

Browse Source
This commit is contained in:
Marcos Luciano
2023-06-05 18:33:03 -03:00
parent 79d4a0a8cd
commit 9fd80c5248
25 changed files with 108 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docs/DAMOYOLO.md
View File

@@ -40,16 +40,16 @@ wget https://idstcv.oss-cn-zhangjiakou.aliyuncs.com/DAMO-YOLO/release_model/clea
Generate the ONNX model file (example for DAMO-YOLO-S*)
```
python3 export_damoyolo.py -w damoyolo_tinynasL25_S_477.pth -c configs/damoyolo_tinynasL25_S.py --simplify --dynamic
python3 export_damoyolo.py -w damoyolo_tinynasL25_S_477.pth -c configs/damoyolo_tinynasL25_S.py --dynamic
```
**NOTE**: To simplify the ONNX model
**NOTE**: To simplify the ONNX model (DeepStream >= 6)
```
--simplify
```
**NOTE**: To use dynamic batch-size
**NOTE**: To use dynamic batch-size (DeepStream >= 6)
```
--dynamic
@@ -61,7 +61,7 @@ python3 export_damoyolo.py -w damoyolo_tinynasL25_S_477.pth -c configs/damoyolo_
--batch 4
```
**NOTE**: If you are using DeepStream 5.1, use opset 11 or lower.
**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 11 or lower. The default opset is 11.
```
--opset 11

8
docs/PPYOLOE.md
View File

@@ -38,16 +38,16 @@ Generate the ONNX model file (example for PP-YOLOE+_s)
```
pip3 install onnx onnxsim onnxruntime
python3 export_ppyoloe.py -w ppyoloe_plus_crn_s_80e_coco.pdparams -c configs/ppyoloe/ppyoloe_plus_crn_s_80e_coco.yml --simplify --dynamic
python3 export_ppyoloe.py -w ppyoloe_plus_crn_s_80e_coco.pdparams -c configs/ppyoloe/ppyoloe_plus_crn_s_80e_coco.yml --dynamic
```
**NOTE**: To simplify the ONNX model
**NOTE**: To simplify the ONNX model (DeepStream >= 6)
```
--simplify
```
**NOTE**: To use dynamic batch-size
**NOTE**: To use dynamic batch-size (DeepStream >= 6)
```
--dynamic
@@ -59,7 +59,7 @@ python3 export_ppyoloe.py -w ppyoloe_plus_crn_s_80e_coco.pdparams -c configs/ppy
--batch 4
```
**NOTE**: If you are using DeepStream 5.1, use opset 12 or lower. The default opset is 11.
**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 11.
```
--opset 12

8
docs/YOLONAS.md
View File

@@ -43,16 +43,16 @@ wget https://sghub.deci.ai/models/yolo_nas_s_coco.pth
Generate the ONNX model file (example for YOLO-NAS S)
```
python3 export_yolonas.py -m yolo_nas_s -w yolo_nas_s_coco.pth --simplify --dynamic
python3 export_yolonas.py -m yolo_nas_s -w yolo_nas_s_coco.pth --dynamic
```
**NOTE**: To simplify the ONNX model
**NOTE**: To simplify the ONNX model (DeepStream >= 6)
```
--simplify
```
**NOTE**: To use dynamic batch-size
**NOTE**: To use dynamic batch-size (DeepStream >= 6)
```
--dynamic
@@ -64,7 +64,7 @@ python3 export_yolonas.py -m yolo_nas_s -w yolo_nas_s_coco.pth --simplify --dyna
--batch 4
```
**NOTE**: If you are using DeepStream 5.1, use opset 12 or lower. The default opset is 14.
**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 14.
```
--opset 12

10
docs/YOLOR.md
View File

@@ -44,7 +44,7 @@ Generate the ONNX model file
Example for YOLOR-CSP
```
python3 export_yolor.py -w yolor_csp.pt -c cfg/yolor_csp.cfg --simplify --dynamic
python3 export_yolor.py -w yolor_csp.pt -c cfg/yolor_csp.cfg --dynamic
```
- Paper branch
@@ -52,16 +52,16 @@ Generate the ONNX model file
Example for YOLOR-P6
```
python3 export_yolor.py -w yolor-p6.pt --simplify --dynamic
python3 export_yolor.py -w yolor-p6.pt --dynamic
```
**NOTE**: To simplify the ONNX model
**NOTE**: To simplify the ONNX model (DeepStream >= 6)
```
--simplify
```
**NOTE**: To use dynamic batch-size
**NOTE**: To use dynamic batch-size (DeepStream >= 6)
```
--dynamic
@@ -73,7 +73,7 @@ Generate the ONNX model file
--batch 4
```
**NOTE**: If you are using DeepStream 5.1, use opset 12 or lower. The default opset is 12.
**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 12.
```
--opset 12

8
docs/YOLOX.md
View File

@@ -43,16 +43,16 @@ wget https://github.com/Megvii-BaseDetection/YOLOX/releases/download/0.1.1rc0/yo
Generate the ONNX model file (example for YOLOX-s)
```
python3 export_yolox.py -w yolox_s.pth -c exps/default/yolox_s.py --simplify --dynamic
python3 export_yolox.py -w yolox_s.pth -c exps/default/yolox_s.py --dynamic
```
**NOTE**: To simplify the ONNX model
**NOTE**: To simplify the ONNX model (DeepStream >= 6)
```
--simplify
```
**NOTE**: To use dynamic batch-size
**NOTE**: To use dynamic batch-size (DeepStream >= 6)
```
--dynamic
@@ -64,7 +64,7 @@ python3 export_yolox.py -w yolox_s.pth -c exps/default/yolox_s.py --simplify --d
--batch 4
```
**NOTE**: If you are using DeepStream 5.1, use opset 12 or lower. The default opset is 11.
**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 11.
```
--opset 12

8
docs/YOLOv5.md
View File

@@ -44,16 +44,16 @@ wget https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5s.pt
Generate the ONNX model file (example for YOLOv5s)
```
python3 export_yoloV5.py -w yolov5s.pt --simplify --dynamic
python3 export_yoloV5.py -w yolov5s.pt --dynamic
```
**NOTE**: To simplify the ONNX model
**NOTE**: To simplify the ONNX model (DeepStream >= 6)
```
--simplify
```
**NOTE**: To use dynamic batch-size
**NOTE**: To use dynamic batch-size (DeepStream >= 6)
```
--dynamic
@@ -65,7 +65,7 @@ python3 export_yoloV5.py -w yolov5s.pt --simplify --dynamic
--batch 4
```
**NOTE**: If you are using DeepStream 5.1, use opset 12 or lower. The default opset is 17.
**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 17.
```
--opset 12

8
docs/YOLOv6.md
View File

@@ -44,16 +44,16 @@ wget https://github.com/meituan/YOLOv6/releases/download/0.4.0/yolov6s.pt
Generate the ONNX model file (example for YOLOv6-S 4.0)
```
python3 export_yoloV6.py -w yolov6s.pt --simplify --dynamic
python3 export_yoloV6.py -w yolov6s.pt --dynamic
```
**NOTE**: To simplify the ONNX model
**NOTE**: To simplify the ONNX model (DeepStream >= 6)
```
--simplify
```
**NOTE**: To use dynamic batch-size
**NOTE**: To use dynamic batch-size (DeepStream >= 6)
```
--dynamic
@@ -65,7 +65,7 @@ python3 export_yoloV6.py -w yolov6s.pt --simplify --dynamic
--batch 4
```
**NOTE**: If you are using DeepStream 5.1, use opset 12 or lower. The default opset is 13.
**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 13.
```
--opset 12

8
docs/YOLOv7.md
View File

@@ -46,16 +46,16 @@ wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt
Generate the ONNX model file (example for YOLOv7)
```
python3 export_yoloV7.py -w yolov7.pt --simplify --dynamic
python3 export_yoloV7.py -w yolov7.pt --dynamic
```
**NOTE**: To simplify the ONNX model
**NOTE**: To simplify the ONNX model (DeepStream >= 6)
```
--simplify
```
**NOTE**: To use dynamic batch-size
**NOTE**: To use dynamic batch-size (DeepStream >= 6)
```
--dynamic
@@ -67,7 +67,7 @@ python3 export_yoloV7.py -w yolov7.pt --simplify --dynamic
--batch 4
```
**NOTE**: If you are using DeepStream 5.1, use opset 12 or lower. The default opset is 12.
**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 12.
```
--opset 12

8
docs/YOLOv8.md
View File

@@ -43,16 +43,16 @@ wget https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt
Generate the ONNX model file (example for YOLOv8s)
```
python3 export_yoloV8.py -w yolov8s.pt --simplify --dynamic
python3 export_yoloV8.py -w yolov8s.pt --dynamic
```
**NOTE**: To simplify the ONNX model
**NOTE**: To simplify the ONNX model (DeepStream >= 6)
```
--simplify
```
**NOTE**: To use dynamic batch-size
**NOTE**: To use dynamic batch-size (DeepStream >= 6)
```
--dynamic
@@ -64,7 +64,7 @@ python3 export_yoloV8.py -w yolov8s.pt --simplify --dynamic
--batch 4
```
**NOTE**: If you are using DeepStream 5.1, use opset 12 or lower. The default opset is 16.
**NOTE**: If you are using DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 16.
```
--opset 12