From 758b7a0bb715837623176f1e531d692f7de21f03 Mon Sep 17 00:00:00 2001 From: Marcos Luciano Date: Thu, 23 Nov 2023 21:08:37 -0300 Subject: [PATCH] Add RT-DETR Ultralytics --- README.md | 2 + docs/RTDETR.md | 4 +- docs/RTDETR_Ultralytics.md | 199 +++++++++++++++++++++++++++++ utils/export_rtdetr_ultralytics.py | 124 ++++++++++++++++++ 4 files changed, 327 insertions(+), 2 deletions(-) create mode 100644 docs/RTDETR_Ultralytics.md create mode 100755 utils/export_rtdetr_ultralytics.py diff --git a/README.md b/README.md index 20d3cd3..0cd4ad4 100644 --- a/README.md +++ b/README.md @@ -30,6 +30,7 @@ NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 configuration * INT8 calibration (PTQ) for Darknet and ONNX exported models * New output structure (fix wrong output on DeepStream < 6.2) - it need to export the ONNX model with the new export file, generate the TensorRT engine again with the updated files, and use the new config_infer_primary file according to your model * **RT-DETR (https://github.com/lyuwenyu/RT-DETR/tree/main/rtdetr_pytorch)** +* **RT-DETR Ultralytics (https://docs.ultralytics.com/models/rtdetr)** ## @@ -53,6 +54,7 @@ NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 configuration * [PP-YOLOE / PP-YOLOE+ usage](docs/PPYOLOE.md) * [YOLO-NAS usage](docs/YOLONAS.md) * [RT-DETR usage](docs/RTDETR.md) +* [RT-DETR Ultralytics usage](docs/RTDETR_Ultralytics.md) * [Using your custom model](docs/customModels.md) * [Multiple YOLO GIEs](docs/multipleGIEs.md) diff --git a/docs/RTDETR.md b/docs/RTDETR.md index 666b492..2f19a15 100644 --- a/docs/RTDETR.md +++ b/docs/RTDETR.md @@ -1,6 +1,6 @@ -# RT_DETR usage +# RT-DETR usage -**NOTE**: For it is supported only the https://github.com/lyuwenyu/RT-DETR/tree/main/rtdetr_pytorch version. +**NOTE**: https://github.com/lyuwenyu/RT-DETR/tree/main/rtdetr_pytorch version. * [Convert model](#convert-model) * [Compile the lib](#compile-the-lib) diff --git a/docs/RTDETR_Ultralytics.md b/docs/RTDETR_Ultralytics.md new file mode 100644 index 0000000..389c298 --- /dev/null +++ b/docs/RTDETR_Ultralytics.md @@ -0,0 +1,199 @@ +# RT-DETR Ultralytics usage + +**NOTE**: Ultralytics (https://docs.ultralytics.com/models/rtdetr) version. + +* [Convert model](#convert-model) +* [Compile the lib](#compile-the-lib) +* [Edit the config_infer_primary_rtdetr file](#edit-the-config_infer_primary_rtdetr-file) +* [Edit the deepstream_app_config file](#edit-the-deepstream_app_config-file) +* [Testing the model](#testing-the-model) + +## + +### Convert model + +#### 1. Download the Ultralytics 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_rtdetr_ultralytics.py` file from `DeepStream-Yolo/utils` directory to the `ultralytics` folder. + +#### 3. Download the model + +Download the `pt` file from [Ultralytics](https://github.com/ultralytics/assets/releases/) releases (example for RT-DETR-l) + +``` +wget https://github.com/ultralytics/assets/releases/download/v0.0.0/rtdetr-l.pt +``` + +**NOTE**: You can use your custom model. + +#### 4. Convert model + +Generate the ONNX model file (example for RT-DETR-l) + +``` +python3 export_rtdetr_ultralytics.py -w rtdetr-l.pt --dynamic +``` + +**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_rtdetr file + +Edit the `config_infer_primary_rtdetr.txt` file according to your model (example for RT-DETR-l with 80 classes) + +``` +[property] +... +onnx-file=rtdetr-l.onnx +... +num-detected-classes=80 +... +parse-bbox-func-name=NvDsInferParseYolo +... +``` + +**NOTE**: The **RT-DETR Ultralytics** do not resize the input with padding. To get better accuracy, use + +``` +[property] +... +maintain-aspect-ratio=0 +... +``` + +## + +### Edit the deepstream_app_config file + +``` +... +[primary-gie] +... +config-file=config_infer_primary_rtdetr.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. diff --git a/utils/export_rtdetr_ultralytics.py b/utils/export_rtdetr_ultralytics.py new file mode 100755 index 0000000..5041811 --- /dev/null +++ b/utils/export_rtdetr_ultralytics.py @@ -0,0 +1,124 @@ +import os +import sys +import argparse +import warnings +import onnx +import torch +import torch.nn as nn +from copy import deepcopy +from ultralytics import RTDETR +from ultralytics.utils.torch_utils import select_device +from ultralytics.nn.modules import C2f, Detect, RTDETRDecoder + + +class DeepStreamOutput(nn.Module): + def __init__(self, img_size): + self.img_size = img_size + super().__init__() + + def forward(self, x): + boxes = x[:, :, :4] + boxes[:, :, [0, 2]] *= self.img_size[1] + boxes[:, :, [1, 3]] *= self.img_size[0] + 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 rtdetr_ultralytics_export(weights, device): + model = RTDETR(weights) + model = deepcopy(model.model).to(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, (Detect, RTDETRDecoder)): + 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 RT-DETR Ultralytics model\n') + + device = select_device('cpu') + model = rtdetr_ultralytics_export(args.weights, device) + + 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() + + img_size = args.size * 2 if len(args.size) == 1 else args.size + + model = nn.Sequential(model, DeepStreamOutput(img_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 RT-DETR Ultralytics 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') + 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))