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

Update RT-DETR and YOLOX

Browse Source
This commit is contained in:
Marcos Luciano
2024-11-14 23:52:05 -03:00
parent f5c486cb7f
commit 0cc84af9b9
7 changed files with 50 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@@ -222,6 +222,7 @@ NVIDIA DeepStream SDK 7.1 / 7.0 / 6.4 / 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 /
* [DAMO-YOLO](https://github.com/tinyvision/DAMO-YOLO) * [DAMO-YOLO](https://github.com/tinyvision/DAMO-YOLO)
* [PP-YOLOE / PP-YOLOE+](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyoloe) * [PP-YOLOE / PP-YOLOE+](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/ppyoloe)
* [YOLO-NAS](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md) * [YOLO-NAS](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md)
* [RT-DETR](https://github.com/lyuwenyu/RT-DETR)
## ##

2
config_infer_primary_yolox.txt
View File

@@ -1,7 +1,7 @@
[property] [property]
gpu-id=0 gpu-id=0
net-scale-factor=1 net-scale-factor=1
model-color-format=0 model-color-format=1
onnx-file=yolox_s.onnx onnx-file=yolox_s.onnx
model-engine-file=model_b1_gpu0_fp32.engine model-engine-file=model_b1_gpu0_fp32.engine
#int8-calib-file=calib.table #int8-calib-file=calib.table

9
docs/RTDETR_Paddle.md
View File

@@ -141,6 +141,15 @@ maintain-aspect-ratio=0
... ...
``` ```
**NOTE**: The **RT-DETR** do not require NMS. To get better accuracy, use
```
[property]
...
cluster-mode=4
...
```
## ##
### Edit the deepstream_app_config file ### Edit the deepstream_app_config file

9
docs/RTDETR_PyTorch.md
View File

@@ -160,6 +160,15 @@ maintain-aspect-ratio=0
... ...
``` ```
**NOTE**: The **RT-DETR** do not require NMS. To get better accuracy, use
```
[property]
...
cluster-mode=4
...
```
## ##
### Edit the deepstream_app_config file ### Edit the deepstream_app_config file

9
docs/RTDETR_Ultralytics.md
View File

@@ -160,6 +160,15 @@ maintain-aspect-ratio=0
... ...
``` ```
**NOTE**: The **RT-DETR Ultralytics** do not require NMS. To get better accuracy, use
```
[property]
...
cluster-mode=4
...
```
## ##
### Edit the deepstream_app_config file ### Edit the deepstream_app_config file

18
docs/YOLOX.md
View File

@@ -143,6 +143,24 @@ symmetric-padding=0
... ...
``` ```
**NOTE**: The **YOLOX** uses BGR color format for the image input. It is important to change the `model-color-format` according to the trained values.
```
[property]
...
model-color-format=1
...
```
**NOTE**: The **YOLOX legacy** uses RGB color format for the image input. It is important to change the `model-color-format` according to the trained values.
```
[property]
...
model-color-format=0
...
```
**NOTE**: The **YOLOX** uses no normalization on the image preprocess. It is important to change the `net-scale-factor` according to the trained values. **NOTE**: The **YOLOX** uses no normalization on the image preprocess. It is important to change the `net-scale-factor` according to the trained values.
``` ```

6
nvdsinfer_custom_impl_Yolo/yolo.cpp
View File

@@ -146,9 +146,9 @@ Yolo::createEngine(nvinfer1::IBuilder* builder)
"config_infer file to get better accuracy\n" << std::endl; "config_infer file to get better accuracy\n" << std::endl;
} }
} }
if (m_ClusterMode != 2) { if (m_ClusterMode != 2 && m_ClusterMode != 4) {
std::cout << "NOTE: Wrong cluster-mode is set, make sure to set cluster-mode=2 on the config_infer file\n" << std::cout << "NOTE: Wrong cluster-mode is set, make sure to set cluster-mode=4 (RT-DETR or custom NMS) or " <<
std::endl; "cluster-mode=2 on the config_infer file\n" << std::endl;
} }
if (m_NetworkMode == "FP16") { if (m_NetworkMode == "FP16") {