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

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