Add support for YOLO-World

config_infer_primary_yoloWorld.txt

@@ -0,0 +1,28 @@
+[property]
+gpu-id=0
+net-scale-factor=0.0039215697906911373
+model-color-format=0
+onnx-file=yolov8l-worldv2.onnx
+model-engine-file=model_b1_gpu0_fp32.engine
+#int8-calib-file=calib.table
+labelfile-path=labels.txt
+batch-size=1
+network-mode=0
+num-detected-classes=80
+interval=0
+gie-unique-id=1
+process-mode=1
+network-type=0
+cluster-mode=2
+maintain-aspect-ratio=1
+symmetric-padding=1
+#workspace-size=2000
+parse-bbox-func-name=NvDsInferParseYolo
+#parse-bbox-func-name=NvDsInferParseYoloCuda
+custom-lib-path=nvdsinfer_custom_impl_Yolo/libnvdsinfer_custom_impl_Yolo.so
+engine-create-func-name=NvDsInferYoloCudaEngineGet
+
+[class-attrs-all]
+nms-iou-threshold=0.45
+pre-cluster-threshold=0.25
+topk=300

docs/YOLO_World.md

@@ -0,0 +1,205 @@
+# YOLO World usage
+
+**NOTE**: The yaml file is not required.
+
+* [Convert model](#convert-model)
+* [Compile the lib](#compile-the-lib)
+* [Edit the config_infer_primary_yoloWorld file](#edit-the-config_infer_primary_yoloWorld-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 World repo and install the requirements
+
+```
+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 `export_yoloWorld.py` file from `DeepStream-Yolo/utils` directory to the `ultralytics` folder.
+
+#### 3. Download the model
+
+Download the `pt` file from [YOLO-World](https://docs.ultralytics.com/models/yolo-world/#key-features) releases (example for yolov8l-worldv2.pt)
+
+```
+wget https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8l-worldv2.pt
+```
+
+**NOTE**: You can use your custom model.
+
+#### 4. Convert model
+
+Generate the ONNX model file (example for yolov8l-worldv2.pt)
+
+```
+python3 export_yoloWorld.py -w yolov8l-worldv2.pt --dynamic --simplify
+```
+
+**NOTE**: To set custom classes
+```
+python3 export_yoloWorld.py -w yolov8l-worldv2.pt --dynamic --simplify --custom-classes "person, dachshund, navy tie"
+```
+
+**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
+```
+
+**NOTE**: To simplify the ONNX model (DeepStream >= 6.0)
+
+```
+--simplify
+```
+
+**NOTE**: To use dynamic batch-size (DeepStream >= 6.1)
+
+```
+--dynamic
+```
+
+**NOTE**: To use static batch-size (example for batch-size = 4)
+
+```
+--batch 4
+```
+
+**NOTE**: If you are using the DeepStream 5.1, remove the `--dynamic` arg and use opset 12 or lower. The default opset is 16.
+
+```
+--opset 12
+```
+
+#### 5. Copy generated files
+
+Copy the generated ONNX model file and labels.txt file (if generated) to the `DeepStream-Yolo` folder.
+
+##
+
+### Compile the lib
+
+Open the `DeepStream-Yolo` folder and compile the lib
+
+* DeepStream 6.3 on x86 platform
+
+  ```
+  CUDA_VER=12.1 make -C nvdsinfer_custom_impl_Yolo
+  ```
+
+* 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 5.1 on x86 platform
+
+  ```
+  CUDA_VER=11.1 make -C nvdsinfer_custom_impl_Yolo
+  ```
+
+* DeepStream 6.3 / 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 / 5.1 on Jetson platform
+
+  ```
+  CUDA_VER=10.2 make -C nvdsinfer_custom_impl_Yolo
+  ```
+
+##
+
+### Edit the config_infer_primary_yoloWorld file
+
+Edit the `config_infer_primary_yoloWorld.txt` file according to your model (example for yolov8l-worldv2.pt with 80 classes)
+
+```
+[property]
+...
+onnx-file=yolov8l-worldv2.onnx
+...
+num-detected-classes=80
+...
+parse-bbox-func-name=NvDsInferParseYolo
+...
+```
+
+**NOTE**: The **YOLOv8** resizes the input with center padding. To get better accuracy, use
+
+```
+[property]
+...
+maintain-aspect-ratio=1
+symmetric-padding=1
+...
+```
+
+##
+
+### Edit the deepstream_app_config file
+
+```
+...
+[primary-gie]
+...
+config-file=config_infer_primary_yoloWorld.txt
+```
+
+##
+
+### Testing the model
+
+```
+deepstream-app -c deepstream_app_config.txt
+```
+
+**NOTE**: The TensorRT engine file may take a very long time to generate (sometimes more than 10 minutes).
+
+**NOTE**: For more information about custom models configuration (`batch-size`, `network-mode`, etc), please check the [`docs/customModels.md`](customModels.md) file.

utils/export_yoloWorld.py

@@ -0,0 +1,138 @@
+import os
+import sys
+import argparse
+import warnings
+import onnx
+import torch
+import torch.nn as nn
+from copy import deepcopy
+from ultralytics import YOLOWorld
+from ultralytics.utils.torch_utils import select_device
+from ultralytics.nn.modules import C2f, WorldDetect
+
+
+class DeepStreamOutput(nn.Module):
+    def __init__(self):
+        super().__init__()
+
+    def forward(self, x):
+        x = x.transpose(1, 2)
+        boxes = x[:, :, :4]
+        scores, classes = torch.max(x[:, :, 4:], 2, keepdim=True)
+        classes = classes.float()
+        return boxes, scores, classes
+
+
+def suppress_warnings():
+    warnings.filterwarnings('ignore', category=torch.jit.TracerWarning)
+    warnings.filterwarnings('ignore', category=UserWarning)
+    warnings.filterwarnings('ignore', category=DeprecationWarning)
+
+
+def yolow_export(model, device):
+    for p in model.parameters():
+        p.requires_grad = False
+    model.eval()
+    model.float()
+    model = model.fuse()
+    for k, m in model.named_modules():
+        if isinstance(m, WorldDetect):
+            m.dynamic = False
+            m.export = True
+            m.format = 'onnx'
+        elif isinstance(m, C2f):
+            m.forward = m.forward_split
+    return model
+
+
+def main(args):
+    suppress_warnings()
+
+    print('\nStarting: %s' % args.weights)
+
+    print('Opening YOLO World model\n')
+
+    model = YOLOWorld(args.weights)
+    print(f"{'#'*10} Original Model Names {'#'*10}\n{model.names}\n")
+
+
+    # set custom classes
+    if args.custom_classes is not None:
+        custom_class_list = [item.strip() for item in args.custom_classes.split(',')]
+
+        model.set_classes(custom_class_list)
+        model.model.txt_feats = model.model.txt_feats.detach()
+        print(f"{'#'*10} Custom Model Names {'#'*10}\n{model.names}\n")
+
+
+    # create labels.txt
+    if len(model.names.keys()) > 0:
+        print('\nCreating labels.txt file')
+        f = open('labels.txt', 'w')
+        for name in model.names.values():
+            f.write(name + '\n')
+        f.close()
+
+
+    device = select_device('cpu')
+    model = deepcopy(model.model).to(device)
+    model = yolow_export(model, device)
+
+    model = nn.Sequential(model, DeepStreamOutput())
+
+    img_size = args.size * 2 if len(args.size) == 1 else args.size
+
+    onnx_input_im = torch.zeros(args.batch, 3, *img_size).to(device)
+    onnx_output_file = os.path.basename(args.weights).split('.pt')[0] + '.onnx'
+
+    dynamic_axes = {
+        'input': {
+            0: 'batch'
+        },
+        'boxes': {
+            0: 'batch'
+        },
+        'scores': {
+            0: 'batch'
+        },
+        'classes': {
+            0: 'batch'
+        }
+    }
+
+    print('\nExporting the model to ONNX')
+    torch.onnx.export(model, onnx_input_im, onnx_output_file, verbose=False, opset_version=args.opset,
+                      do_constant_folding=True, input_names=['input'], output_names=['boxes', 'scores', 'classes'],
+                      dynamic_axes=dynamic_axes if args.dynamic else None)
+
+    if args.simplify:
+        print('Simplifying the ONNX model')
+        import onnxsim
+        model_onnx = onnx.load(onnx_output_file)
+        model_onnx, _ = onnxsim.simplify(model_onnx)
+        onnx.save(model_onnx, onnx_output_file)
+
+    print('Done: %s\n' % onnx_output_file)
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description='DeepStream YOLO World conversion')
+    parser.add_argument('-w', '--weights', required=True, help='Input weights (.pt) file path (required)')
+    parser.add_argument('-s', '--size', nargs='+', type=int, default=[640], help='Inference size [H,W] (default [640])')
+    parser.add_argument('--opset', type=int, default=16, help='ONNX opset version')
+    parser.add_argument('--simplify', action='store_true', help='ONNX simplify model')
+    parser.add_argument('--dynamic', action='store_true', help='Dynamic batch-size')
+    parser.add_argument('--batch', type=int, default=1, help='Static batch-size')
+    parser.add_argument('--custom-classes', type=str, help='Define custom classes, separated by comma')
+
+    args = parser.parse_args()
+    if not os.path.isfile(args.weights):
+        raise SystemExit('Invalid weights file')
+    if args.dynamic and args.batch > 1:
+        raise SystemExit('Cannot set dynamic batch-size and static batch-size at same time')
+    return args
+
+
+if __name__ == '__main__':
+    args = parse_args()
+    sys.exit(main(args))