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

Big update

Browse Source
This commit is contained in:
Marcos Luciano
2023-05-19 03:05:43 -03:00
parent 68f762d5bd
commit 07feae9509
86 changed files with 1523 additions and 5223 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
docs/PPYOLOE.md
View File

@@ -1,5 +1,7 @@
# PP-YOLOE / PP-YOLOE+ usage
**NOTE**: You can use the release/2.6 branch of the PPYOLOE repo to convert all model versions.
* [Convert model](#convert-model)
* [Compile the lib](#compile-the-lib)
* [Edit the config_infer_primary_ppyoloe_plus file](#edit-the-config_infer_primary_ppyoloe_plus-file)
@@ -12,35 +14,36 @@
#### 1. Download the PaddleDetection repo and install the requirements
https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/docs/tutorials/INSTALL.md
https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.6/docs/tutorials/INSTALL.md
**NOTE**: It is recommended to use Python virtualenv.
#### 2. Copy conversor
Copy the `gen_wts_ppyoloe.py` file from `DeepStream-Yolo/utils` directory to the `PaddleDetection` folder.
Copy the `export_ppyoloe.py` file from `DeepStream-Yolo/utils` directory to the `PaddleDetection` folder.
#### 3. Download the model
Download the `pdparams` file from [PP-YOLOE](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/ppyoloe) releases (example for PP-YOLOE+_s)
Download the `pdparams` file from [PP-YOLOE](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.6/configs/ppyoloe) releases (example for PP-YOLOE+_s)
```
wget https://paddledet.bj.bcebos.com/models/ppyoloe_plus_crn_s_80e_coco.pdparams
```
**NOTE**: You can use your custom model, but it is important to keep the YOLO model reference (`ppyoloe_`) in you `cfg` and `weights`/`wts` filenames to generate the engine correctly.
**NOTE**: You can use your custom model.
#### 4. Convert model
Generate the `cfg` and `wts` files (example for PP-YOLOE+_s)
Generate the ONNX model file (example for PP-YOLOE+_s)
```
python3 gen_wts_ppyoloe.py -w ppyoloe_plus_crn_s_80e_coco.pdparams -c configs/ppyoloe/ppyoloe_plus_crn_s_80e_coco.yml
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
```
#### 5. Copy generated files
Copy the generated `cfg` and `wts` files to the `DeepStream-Yolo` folder.
Copy the generated ONNX model file to the `DeepStream-Yolo` folder.
##
@@ -93,11 +96,13 @@ Edit the `config_infer_primary_ppyoloe_plus.txt` file according to your model (e
```
[property]
...
custom-network-config=ppyoloe_plus_crn_s_80e_coco.cfg
model-file=ppyoloe_plus_crn_s_80e_coco.wts
onnx-file=ppyoloe_plus_crn_s_80e_coco.onnx
model-engine-file=ppyoloe_plus_crn_s_80e_coco.onnx_b1_gpu0_fp32.engine
...
num-detected-classes=80
...
parse-bbox-func-name=NvDsInferParseYoloE
...
```
**NOTE**: If you use the **legacy** model, you should edit the `config_infer_primary_ppyoloe.txt` file.

171
docs/YOLONAS.md Normal file
View File

@@ -0,0 +1,171 @@
# YOLONAS usage
**NOTE**: The yaml file is not required.
* [Convert model](#convert-model)
* [Compile the lib](#compile-the-lib)
* [Edit the config_infer_primary_yolonas file](#edit-the-config_infer_primary_yolonas-file)
* [Edit the deepstream_app_config file](#edit-the-deepstream_app_config-file)
* [Testing the model](#testing-the-model)
##
### Convert model
#### 1. Download the YOLO-NAS repo and install the requirements
```
git clone https://github.com/Deci-AI/super-gradients.git
cd super-gradients
pip3 install -r requirements.txt
python3 setup.py install
pip3 install onnx onnxsim onnxruntime
```
**NOTE**: It is recommended to use Python virtualenv.
#### 2. Copy conversor
Copy the `export_yolonas.py` file from `DeepStream-Yolo/utils` directory to the `super-gradients` folder.
#### 3. Download the model
Download the `pth` file from [YOLO-NAS](https://sghub.deci.ai/) website (example for YOLO-NAS S)
```
wget https://sghub.deci.ai/models/yolo_nas_s_coco.pth
```
**NOTE**: You can use your custom model.
#### 4. Convert model
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
```
**NOTE**: Model names
```
-m yolo_nas_s
```
or
```
-m yolo_nas_m
```
or
```
-m yolo_nas_l
```
**NOTE**: To change the inference size (defaut: 640)
```
-s SIZE
--size SIZE
-s HEIGHT WIDTH
--size HEIGHT WIDTH
```
Example for 1280
```
-s 1280
```
or
```
-s 1280 1280
```
#### 5. Copy generated files
Copy the generated ONNX model file to the `DeepStream-Yolo` folder.
##
### Compile the lib
Open the `DeepStream-Yolo` folder and compile the lib
* DeepStream 6.2 on x86 platform
```
CUDA_VER=11.8 make -C nvdsinfer_custom_impl_Yolo
```
* DeepStream 6.1.1 on x86 platform
```
CUDA_VER=11.7 make -C nvdsinfer_custom_impl_Yolo
```
* DeepStream 6.1 on x86 platform
```
CUDA_VER=11.6 make -C nvdsinfer_custom_impl_Yolo
```
* DeepStream 6.0.1 / 6.0 on x86 platform
```
CUDA_VER=11.4 make -C nvdsinfer_custom_impl_Yolo
```
* DeepStream 6.2 / 6.1.1 / 6.1 on Jetson platform
```
CUDA_VER=11.4 make -C nvdsinfer_custom_impl_Yolo
```
* DeepStream 6.0.1 / 6.0 on Jetson platform
```
CUDA_VER=10.2 make -C nvdsinfer_custom_impl_Yolo
```
##
### Edit the config_infer_primary_yolonas file
Edit the `config_infer_primary_yolonas.txt` file according to your model (example for YOLO-NAS S with 80 classes)
```
[property]
...
onnx-file=yolo_nas_s_coco.onnx
model-engine-file=yolo_nas_s_coco.onnx_b1_gpu0_fp32.engine
...
num-detected-classes=80
...
parse-bbox-func-name=NvDsInferParseYoloE
...
```
##
### Edit the deepstream_app_config file
```
...
[primary-gie]
...
config-file=config_infer_primary_yolonas.txt
```
##
### Testing the model
```
deepstream-app -c deepstream_app_config.txt
```
**NOTE**: For more information about custom models configuration (`batch-size`, `network-mode`, etc), please check the [`docs/customModels.md`](customModels.md) file.

60
docs/YOLOR.md
View File

@@ -1,8 +1,8 @@
# YOLOR usage
**NOTE**: You need to use the main branch of the YOLOR repo to convert the model.
**NOTE**: Select the correct branch of the YOLOR repo before the conversion.
**NOTE**: The cfg file is required.
**NOTE**: The cfg file is required for the main branch.
* [Convert model](#convert-model)
* [Compile the lib](#compile-the-lib)
@@ -20,31 +20,71 @@
git clone https://github.com/WongKinYiu/yolor.git
cd yolor
pip3 install -r requirements.txt
pip3 install onnx onnxsim onnxruntime
```
**NOTE**: It is recommended to use Python virtualenv.
#### 2. Copy conversor
Copy the `gen_wts_yolor.py` file from `DeepStream-Yolo/utils` directory to the `yolor` folder.
Copy the `export_yolor.py` file from `DeepStream-Yolo/utils` directory to the `yolor` folder.
#### 3. Download the model
Download the `pt` file from [YOLOR](https://github.com/WongKinYiu/yolor) repo.
**NOTE**: You can use your custom model, but it is important to keep the YOLO model reference (`yolor_`) in you `cfg` and `weights`/`wts` filenames to generate the engine correctly.
**NOTE**: You can use your custom model.
#### 4. Convert model
Generate the `cfg` and `wts` files (example for YOLOR-CSP)
Generate the ONNX model file
- Main branch
Example for YOLOR-CSP
```
python3 export_yolor.py -w yolor_csp.pt -c cfg/yolor_csp.cfg --simplify
```
- Paper branch
Example for YOLOR-P6
```
python3 export_yolor.py -w yolor-p6.pt --simplify
```
**NOTE**: To convert a P6 model
```
python3 gen_wts_yolor.py -w yolor_csp.pt -c cfg/yolor_csp.cfg
--p6
```
**NOTE**: To change the inference size (defaut: 640)
```
-s SIZE
--size SIZE
-s HEIGHT WIDTH
--size HEIGHT WIDTH
```
Example for 1280
```
-s 1280
```
or
```
-s 1280 1280
```
#### 5. Copy generated files
Copy the generated `cfg` and `wts` files to the `DeepStream-Yolo` folder
Copy the generated ONNX model file to the `DeepStream-Yolo` folder
##
@@ -97,11 +137,13 @@ Edit the `config_infer_primary_yolor.txt` file according to your model (example
```
[property]
...
custom-network-config=yolor_csp.cfg
model-file=yolor_csp.wts
onnx-file=yolor_csp.onnx
model-engine-file=yolor_csp.onnx_b1_gpu0_fp32.engine
...
num-detected-classes=80
...
parse-bbox-func-name=NvDsInferParseYolo
...
```
##

20
docs/YOLOX.md
View File

@@ -1,5 +1,7 @@
# YOLOX usage
**NOTE**: You can use the main branch of the YOLOX repo to convert all model versions.
**NOTE**: The yaml file is not required.
* [Convert model](#convert-model)
@@ -18,13 +20,15 @@
git clone https://github.com/Megvii-BaseDetection/YOLOX.git
cd YOLOX
pip3 install -r requirements.txt
python3 setup.py develop
pip3 install onnx onnxsim onnxruntime
```
**NOTE**: It is recommended to use Python virtualenv.
#### 2. Copy conversor
Copy the `gen_wts_yolox.py` file from `DeepStream-Yolo/utils` directory to the `YOLOX` folder.
Copy the `export_yolox.py` file from `DeepStream-Yolo/utils` directory to the `YOLOX` folder.
#### 3. Download the model
@@ -34,19 +38,19 @@ Download the `pth` file from [YOLOX](https://github.com/Megvii-BaseDetection/YOL
wget https://github.com/Megvii-BaseDetection/YOLOX/releases/download/0.1.1rc0/yolox_s.pth
```
**NOTE**: You can use your custom model, but it is important to keep the YOLO model reference (`yolox_`) in you `cfg` and `weights`/`wts` filenames to generate the engine correctly.
**NOTE**: You can use your custom model.
#### 4. Convert model
Generate the `cfg` and `wts` files (example for YOLOX-s standard)
Generate the ONNX model file (example for YOLOX-s standard)
```
python3 gen_wts_yolox.py -w yolox_s.pth -e exps/default/yolox_s.py
python3 export_yolox.py -w yolox_s.pth -c exps/default/yolox_s.py --simplify
```
#### 5. Copy generated files
Copy the generated `cfg` and `wts` files to the `DeepStream-Yolo` folder.
Copy the generated ONNX model file to the `DeepStream-Yolo` folder.
##
@@ -99,11 +103,13 @@ Edit the `config_infer_primary_yolox.txt` file according to your model (example
```
[property]
...
custom-network-config=yolox_s.cfg
model-file=yolox_s.wts
onnx-file=yolox_s.onnx
model-engine-file=yolox_s.onnx_b1_gpu0_fp32.engine
...
num-detected-classes=80
...
parse-bbox-func-name=NvDsInferParseYolo
...
```
**NOTE**: If you use the **legacy** model, you should edit the `config_infer_primary_yolox_legacy.txt` file.

23
docs/YOLOv5.md
View File

@@ -1,6 +1,6 @@
# YOLOv5 usage
**NOTE**: You can use the main branch of the YOLOv5 repo to convert all model versions.
**NOTE**: You can use the master branch of the YOLOv5 repo to convert all model versions.
**NOTE**: The yaml file is not required.
@@ -20,30 +20,31 @@
git clone https://github.com/ultralytics/yolov5.git
cd yolov5
pip3 install -r requirements.txt
pip3 install onnx onnxsim onnxruntime
```
**NOTE**: It is recommended to use Python virtualenv.
#### 2. Copy conversor
Copy the `gen_wts_yoloV5.py` file from `DeepStream-Yolo/utils` directory to the `yolov5` folder.
Copy the `export_yoloV5.py` file from `DeepStream-Yolo/utils` directory to the `yolov5` folder.
#### 3. Download the model
Download the `pt` file from [YOLOv5](https://github.com/ultralytics/yolov5/releases/) releases (example for YOLOv5s 6.1)
Download the `pt` file from [YOLOv5](https://github.com/ultralytics/yolov5/releases/) releases (example for YOLOv5s 7.0)
```
wget https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5s.pt
wget https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5s.pt
```
**NOTE**: You can use your custom model, but it is important to keep the YOLO model reference (`yolov5_`) in you `cfg` and `weights`/`wts` filenames to generate the engine correctly.
**NOTE**: You can use your custom model.
#### 4. Convert model
Generate the `cfg` and `wts` files (example for YOLOv5s)
Generate the ONNX model file (example for YOLOv5s)
```
python3 gen_wts_yoloV5.py -w yolov5s.pt
python3 export_yoloV5.py -w yolov5s.pt --simplify
```
**NOTE**: To convert a P6 model
@@ -75,7 +76,7 @@ or
#### 5. Copy generated files
Copy the generated `cfg` and `wts` files to the `DeepStream-Yolo` folder.
Copy the generated ONNX model file to the `DeepStream-Yolo` folder.
##
@@ -128,11 +129,13 @@ Edit the `config_infer_primary_yoloV5.txt` file according to your model (example
```
[property]
...
custom-network-config=yolov5s.cfg
model-file=yolov5s.wts
onnx-file=yolov5s.onnx
model-engine-file=yolov5s.onnx_b1_gpu0_fp32.engine
...
num-detected-classes=80
...
parse-bbox-func-name=NvDsInferParseYolo
...
```
##

17
docs/YOLOv6.md
View File

@@ -18,13 +18,14 @@
git clone https://github.com/meituan/YOLOv6.git
cd YOLOv6
pip3 install -r requirements.txt
pip3 install onnx onnxsim onnxruntime
```
**NOTE**: It is recommended to use Python virtualenv.
#### 2. Copy conversor
Copy the `gen_wts_yoloV6.py` file from `DeepStream-Yolo/utils` directory to the `YOLOv6` folder.
Copy the `export_yoloV6.py` file from `DeepStream-Yolo/utils` directory to the `YOLOv6` folder.
#### 3. Download the model
@@ -34,14 +35,14 @@ Download the `pt` file from [YOLOv6](https://github.com/meituan/YOLOv6/releases/
wget https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6s.pt
```
**NOTE**: You can use your custom model, but it is important to keep the YOLO model reference (`yolov6_`) in you `cfg` and `weights`/`wts` filenames to generate the engine correctly.
**NOTE**: You can use your custom model.
#### 4. Convert model
Generate the `cfg` and `wts` files (example for YOLOv6-S 3.0)
Generate the ONNX model file (example for YOLOv6-S 3.0)
```
python3 gen_wts_yoloV6.py -w yolov6s.pt
python3 export_yoloV6.py -w yolov6s.pt --simplify
```
**NOTE**: To convert a P6 model
@@ -73,7 +74,7 @@ or
#### 5. Copy generated files
Copy the generated `cfg` and `wts` files to the `DeepStream-Yolo` folder.
Copy the generated ONNX model file to the `DeepStream-Yolo` folder.
##
@@ -126,11 +127,13 @@ Edit the `config_infer_primary_yoloV6.txt` file according to your model (example
```
[property]
...
custom-network-config=yolov6s.cfg
model-file=yolov6s.wts
onnx-file=yolov6s.onnx
model-engine-file=yolov6s.onnx_b1_gpu0_fp32.engine
...
num-detected-classes=80
...
parse-bbox-func-name=NvDsInferParseYolo
...
```
##

19
docs/YOLOv7.md
View File

@@ -18,13 +18,14 @@
git clone https://github.com/WongKinYiu/yolov7.git
cd yolov7
pip3 install -r requirements.txt
pip3 install onnx onnxsim onnxruntime
```
**NOTE**: It is recommended to use Python virtualenv.
#### 2. Copy conversor
Copy the `gen_wts_yoloV7.py` file from `DeepStream-Yolo/utils` directory to the `yolov7` folder.
Copy the `export_yoloV7.py` file from `DeepStream-Yolo/utils` directory to the `yolov7` folder.
#### 3. Download the model
@@ -34,18 +35,18 @@ Download the `pt` file from [YOLOv7](https://github.com/WongKinYiu/yolov7/releas
wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt
```
**NOTE**: You can use your custom model, but it is important to keep the YOLO model reference (`yolov7_`) in you `cfg` and `weights`/`wts` filenames to generate the engine correctly.
**NOTE**: You can use your custom model.
#### 4. Reparameterize your model
[YOLOv7](https://github.com/WongKinYiu/yolov7/releases/) and it's variants can't be directly converted to engine file. Therefore, you will have to reparameterize your model using the code [here](https://github.com/WongKinYiu/yolov7/blob/main/tools/reparameterization.ipynb). Make sure to convert your checkpoints in yolov7 repository, and then save your reparmeterized checkpoints for conversion in the next step.
[YOLOv7](https://github.com/WongKinYiu/yolov7/releases/) and its variants cannot be directly converted to engine file. Therefore, you will have to reparameterize your model using the code [here](https://github.com/WongKinYiu/yolov7/blob/main/tools/reparameterization.ipynb). Make sure to convert your custom checkpoints in yolov7 repository, and then save your reparmeterized checkpoints for conversion in the next step.
#### 5. Convert model
Generate the `cfg` and `wts` files (example for YOLOv7)
Generate the ONNX model file (example for YOLOv7)
```
python3 gen_wts_yoloV7.py -w yolov7.pt
python3 export_yoloV7.py -w yolov7.pt --simplify
```
**NOTE**: To convert a P6 model
@@ -77,7 +78,7 @@ or
#### 6. Copy generated files
Copy the generated `cfg` and `wts` files to the `DeepStream-Yolo` folder.
Copy the generated ONNX model file to the `DeepStream-Yolo` folder.
##
@@ -130,11 +131,13 @@ Edit the `config_infer_primary_yoloV7.txt` file according to your model (example
```
[property]
...
custom-network-config=yolov7.cfg
model-file=yolov7.wts
onnx-file=yolov7.onnx
model-engine-file=yolov7.onnx_b1_gpu0_fp32.engine
...
num-detected-classes=80
...
parse-bbox-func-name=NvDsInferParseYolo
...
```
##

18
docs/YOLOv8.md
View File

@@ -18,13 +18,15 @@
git clone https://github.com/ultralytics/ultralytics.git
cd ultralytics
pip3 install -r requirements.txt
python3 setup.py install
pip3 install onnx onnxsim onnxruntime
```
**NOTE**: It is recommended to use Python virtualenv.
#### 2. Copy conversor
Copy the `gen_wts_yoloV8.py` file from `DeepStream-Yolo/utils` directory to the `ultralytics` folder.
Copy the `export_yoloV8.py` file from `DeepStream-Yolo/utils` directory to the `ultralytics` folder.
#### 3. Download the model
@@ -34,14 +36,14 @@ Download the `pt` file from [YOLOv8](https://github.com/ultralytics/assets/relea
wget https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt
```
**NOTE**: You can use your custom model, but it is important to keep the YOLO model reference (`yolov8_`) in you `cfg` and `weights`/`wts` filenames to generate the engine correctly.
**NOTE**: You can use your custom model.
#### 4. Convert model
Generate the `cfg`, `wts` and `labels.txt` (if available) files (example for YOLOv8s)
Generate the ONNX model file (example for YOLOv8s)
```
python3 gen_wts_yoloV8.py -w yolov8s.pt
python3 export_yoloV8.py -w yolov8s.pt --simplify
```
**NOTE**: To change the inference size (defaut: 640)
@@ -67,7 +69,7 @@ or
#### 5. Copy generated files
Copy the generated `cfg`, `wts` and `labels.txt` (if generated), files to the `DeepStream-Yolo` folder.
Copy the generated ONNX model file to the `DeepStream-Yolo` folder.
##
@@ -120,11 +122,13 @@ Edit the `config_infer_primary_yoloV8.txt` file according to your model (example
```
[property]
...
custom-network-config=yolov8s.cfg
model-file=yolov8s.wts
onnx-file=yolov8s.onnx
model-engine-file=yolov8s.onnx_b1_gpu0_fp32.engine
...
num-detected-classes=80
...
parse-bbox-func-name=NvDsInferParseYolo
...
```
##

27
docs/customModels.md
View File

@@ -19,9 +19,7 @@ cd DeepStream-Yolo
#### 2. Copy the class names file to DeepStream-Yolo folder and remane it to `labels.txt`
#### 3. Copy the `cfg` and `weights`/`wts` files to DeepStream-Yolo folder
**NOTE**: It is important to keep the YOLO model reference (`yolov4_`, `yolov5_`, `yolor_`, etc) in you `cfg` and `weights`/`wts` filenames to generate the engine correctly.
#### 3. Copy the `onnx` or `cfg` and `weights` files to DeepStream-Yolo folder
##
@@ -189,24 +187,25 @@ To understand and edit `config_infer_primary.txt` file, read the [DeepStream Plu
model-color-format=0
```
**NOTE**: Set it according to the number of channels in the `cfg` file (1=GRAYSCALE, 3=RGB).
**NOTE**: Set it according to the number of channels in the `cfg` file (1=GRAYSCALE, 3=RGB for Darknet YOLO) or your model configuration (ONNX).
* custom-network-config
* custom-network-config and model-file (Darknet YOLO)
* Example for custom YOLOv4 model
```
custom-network-config=yolov4_custom.cfg
```
* model-file
* Example for custom YOLOv4 model
```
model-file=yolov4_custom.weights
```
* onnx-file (ONNX)
* Example for custom YOLOv8 model
```
onnx-file=yolov8s_custom.onnx
```
* model-engine-file
* Example for `batch-size=1` and `network-mode=2`
@@ -233,7 +232,7 @@ To understand and edit `config_infer_primary.txt` file, read the [DeepStream Plu
model-engine-file=model_b2_gpu0_fp32.engine
```
**NOTE**: To change the generated engine filename, you need to edit and rebuild the `nvdsinfer_model_builder.cpp` file (`/opt/nvidia/deepstream/deepstream/sources/libs/nvdsinfer/nvdsinfer_model_builder.cpp`, lines 825-827)
**NOTE**: To change the generated engine filename (Darknet YOLO), you need to edit and rebuild the `nvdsinfer_model_builder.cpp` file (`/opt/nvidia/deepstream/deepstream/sources/libs/nvdsinfer/nvdsinfer_model_builder.cpp`, lines 825-827)
```
suggestedPathName =
@@ -260,7 +259,7 @@ To understand and edit `config_infer_primary.txt` file, read the [DeepStream Plu
num-detected-classes=80
```
**NOTE**: Set it according to number of classes in `cfg` file.
**NOTE**: Set it according to number of classes in `cfg` file (Darknet YOLO) or your model configuration (ONNX).
* interval

26
docs/multipleGIEs.md
View File

@@ -26,9 +26,7 @@ cd DeepStream-Yolo
#### 3. Copy the class names file to each GIE folder and remane it to `labels.txt`
#### 4. Copy the `cfg` and `weights`/`wts` files to each GIE folder
**NOTE**: It is important to keep the YOLO model reference (`yolov4_`, `yolov5_`, `yolor_`, etc) in you `cfg` and `weights`/`wts` filenames to generate the engine correctly.
#### 4. Copy the `onnx` or `cfg` and `weights` files to each GIE folder
##
@@ -92,22 +90,36 @@ const char* YOLOLAYER_PLUGIN_VERSION {"2"};
### Edit the config_infer_primary files
**NOTE**: Edit the files according to the model you will use (YOLOv4, YOLOv5, YOLOR, etc).
**NOTE**: Edit the files according to the model you will use (YOLOv8, YOLOv5, YOLOv4, etc).
**NOTE**: Do it for each GIE folder.
* Edit the path of the `cfg` file
Example for gie1
Example for gie1 (Darknet YOLO)
```
custom-network-config=gie1/yolo.cfg
```
model-file=yolo.weights
```
Example for gie2
Example for gie2 (Darknet YOLO)
```
custom-network-config=gie2/yolo.cfg
model-file=yolo.weights
```
Example for gie1 (ONNX)
```
onnx-file=yolo.onnx
```
Example for gie2 (ONNX)
```
onnx-file=yolo.onnx
```
* Edit the gie-unique-id