使用ultralytics 工程（https://github.com/ultralytics/ultralytics）导出onnx模型：

from ultralytics import RTDETR

# Load a model
model = RTDETR("rtdetr-l.pt")

# Export the model
model.export(format="onnx")
model.export(format="engine")  

onnxruntime推理

import cv2
import math
import numpy as np
import onnxruntime


class_names = ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
        'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
        'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
        'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
        'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
        'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
        'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
        'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
        'hair drier', 'toothbrush'] #coco80类别 
input_shape = (640, 640) 
score_threshold = 0.5 
nms_threshold = 0.5


def nms(boxes, scores, score_threshold, nms_threshold):
    x1 = boxes[:, 0]
    y1 = boxes[:, 1]
    x2 = boxes[:, 2]
    y2 = boxes[:, 3]
    areas = (y2 - y1 + 1) * (x2 - x1 + 1)
    keep = []
    index = scores.argsort()[::-1] 

    while index.size > 0:
        i = index[0]
        keep.append(i)
        x11 = np.maximum(x1[i], x1[index[1:]]) 
        y11 = np.maximum(y1[i], y1[index[1:]])
        x22 = np.minimum(x2[i], x2[index[1:]])
        y22 = np.minimum(y2[i], y2[index[1:]])
        w = np.maximum(0, x22 - x11 + 1)                              
        h = np.maximum(0, y22 - y11 + 1) 
        overlaps = w * h
        ious = overlaps / (areas[i] + areas[index[1:]] - overlaps)
        idx = np.where(ious <= nms_threshold)[0]
        index = index[idx + 1]
    return keep


def xywh2xyxy(x):
    y = np.copy(x)
    y[:, 0] = x[:, 0] - x[:, 2] / 2
    y[:, 1] = x[:, 1] - x[:, 3] / 2
    y[:, 2] = x[:, 0] + x[:, 2] / 2
    y[:, 3] = x[:, 1] + x[:, 3] / 2
    return y


def filter_box(output): #过滤掉无用的框    
    output = np.squeeze(output)
     
    boxes = []
    scores = []
    class_ids = []    
    output = output[output[..., 4] > score_threshold] 
    for i in range(output.shape[0]):
        boxes.append(output[i, :6])
        scores.append(output[i][4])
        class_ids.append(output[i][5])  
            
    boxes = np.array(boxes)
    boxes = xywh2xyxy(boxes)
    boxes[..., [0, 2]] *= input_shape[0]
    boxes[..., [1, 3]] *= input_shape[1]
    return boxes


def letterbox(im, new_shape=(416, 416), color=(114, 114, 114)):
    # Resize and pad image while meeting stride-multiple constraints
    shape = im.shape[:2]  # current shape [height, width]

    # Scale ratio (new / old)
    r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
    
    # Compute padding
    new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))    
    dw, dh = (new_shape[1] - new_unpad[0])/2, (new_shape[0] - new_unpad[1])/2  # wh padding 
    top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
    left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
    
    if shape[::-1] != new_unpad:  # resize
        im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
    im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
    return im


def scale_boxes(boxes, output_shape):
    # Rescale boxes (xyxy) from self.input_shape to shape
    gain = min(input_shape[0] / output_shape[0], input_shape[1] / output_shape[1])  # gain  = old / new
    pad = (input_shape[1] - output_shape[1] * gain) / 2, (input_shape[0] - output_shape[0] * gain) / 2  # wh padding
    boxes[..., [0, 2]] -= pad[0]  # x padding
    boxes[..., [1, 3]] -= pad[1]  # y padding
    boxes[..., :4] /= gain
    boxes[..., [0, 2]] = boxes[..., [0, 2]].clip(0, output_shape[1])  # x1, x2
    boxes[..., [1, 3]] = boxes[..., [1, 3]].clip(0, output_shape[0])  # y1, y2
    return boxes


def draw(image, box_data):
    box_data = scale_boxes(box_data, image.shape)
    boxes = box_data[...,:4].astype(np.int32) 
    scores = box_data[...,4]
    classes = box_data[...,5].astype(np.int32)
   
    for box, score, cl in zip(boxes, scores, classes):
        top, left, right, bottom = box
        cv2.rectangle(image, (top, left), (right, bottom), (255, 0, 0), 1)
        cv2.putText(image, '{0} {1:.2f}'.format(class_names[cl], score), (top, left), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 1)


if __name__=="__main__":
    image = cv2.imread('bus.jpg', -1)
    input = letterbox(image, input_shape)
    input = input[:, :, ::-1].transpose(2, 0, 1).astype(dtype=np.float32)  #BGR2RGB和HWC2CHW
    input = input / 255.0
    input_tensor = []
    input_tensor.append(input)
    
    onnx_session = onnxruntime.InferenceSession('rtdetr-l.onnx', providers=['CPUExecutionProvider', 'CUDAExecutionProvider'])
        
    input_name = []
    for node in onnx_session.get_inputs():
        input_name.append(node.name)

    output_name = []
    for node in onnx_session.get_outputs():
        output_name.append(node.name)

    inputs = {}
    for name in input_name:
        inputs[name] =  np.array(input_tensor)
  
    outputs = onnx_session.run(None, inputs)[0]
    
    boxes = filter_box(outputs)
    draw(image, boxes)
    cv2.imwrite('result.jpg', image)

tensorrt推理

import cv2
import math
import numpy as np
import tensorrt as trt
import pycuda.autoinit 
import pycuda.driver as cuda 


class_names = ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
        'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
        'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
        'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
        'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
        'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
        'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
        'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
        'hair drier', 'toothbrush'] #coco80类别 
input_shape = (640, 640) 
score_threshold = 0.5 
nms_threshold = 0.5


def nms(boxes, scores, score_threshold, nms_threshold):
    x1 = boxes[:, 0]
    y1 = boxes[:, 1]
    x2 = boxes[:, 2]
    y2 = boxes[:, 3]
    areas = (y2 - y1 + 1) * (x2 - x1 + 1)
    keep = []
    index = scores.argsort()[::-1] 

    while index.size > 0:
        i = index[0]
        keep.append(i)
        x11 = np.maximum(x1[i], x1[index[1:]]) 
        y11 = np.maximum(y1[i], y1[index[1:]])
        x22 = np.minimum(x2[i], x2[index[1:]])
        y22 = np.minimum(y2[i], y2[index[1:]])
        w = np.maximum(0, x22 - x11 + 1)                              
        h = np.maximum(0, y22 - y11 + 1) 
        overlaps = w * h
        ious = overlaps / (areas[i] + areas[index[1:]] - overlaps)
        idx = np.where(ious <= nms_threshold)[0]
        index = index[idx + 1]
    return keep


def xywh2xyxy(x):
    y = np.copy(x)
    y[:, 0] = x[:, 0] - x[:, 2] / 2
    y[:, 1] = x[:, 1] - x[:, 3] / 2
    y[:, 2] = x[:, 0] + x[:, 2] / 2
    y[:, 3] = x[:, 1] + x[:, 3] / 2
    return y


def filter_box(output): #过滤掉无用的框    
    output = np.squeeze(output)
     
    boxes = []
    scores = []
    class_ids = []    
    output = output[output[..., 4] > score_threshold] 
    for i in range(output.shape[0]):
        boxes.append(output[i, :6])
        scores.append(output[i][4])
        class_ids.append(output[i][5])  
            
    boxes = np.array(boxes)
    boxes = xywh2xyxy(boxes)
    boxes[..., [0, 2]] *= input_shape[0]
    boxes[..., [1, 3]] *= input_shape[1]
    return boxes

def letterbox(im, new_shape=(416, 416), color=(114, 114, 114)):
    # Resize and pad image while meeting stride-multiple constraints
    shape = im.shape[:2]  # current shape [height, width]

    # Scale ratio (new / old)
    r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
    
    # Compute padding
    new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))    
    dw, dh = (new_shape[1] - new_unpad[0])/2, (new_shape[0] - new_unpad[1])/2  # wh padding 
    top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
    left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
    
    if shape[::-1] != new_unpad:  # resize
        im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
    im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
    return im


def scale_boxes(boxes, output_shape):
    # Rescale boxes (xyxy) from self.input_shape to shape
    gain = min(input_shape[0] / output_shape[0], input_shape[1] / output_shape[1])  # gain  = old / new
    pad = (input_shape[1] - output_shape[1] * gain) / 2, (input_shape[0] - output_shape[0] * gain) / 2  # wh padding
    boxes[..., [0, 2]] -= pad[0]  # x padding
    boxes[..., [1, 3]] -= pad[1]  # y padding
    boxes[..., :4] /= gain
    boxes[..., [0, 2]] = boxes[..., [0, 2]].clip(0, output_shape[1])  # x1, x2
    boxes[..., [1, 3]] = boxes[..., [1, 3]].clip(0, output_shape[0])  # y1, y2
    return boxes


def draw(image, box_data):
    box_data = scale_boxes(box_data, image.shape)
    boxes = box_data[...,:4].astype(np.int32) 
    scores = box_data[...,4]
    classes = box_data[...,5].astype(np.int32)
   
    for box, score, cl in zip(boxes, scores, classes):
        top, left, right, bottom = box
        cv2.rectangle(image, (top, left), (right, bottom), (255, 0, 0), 1)
        cv2.putText(image, '{0} {1:.2f}'.format(class_names[cl], score), (top, left), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 1)


if __name__=="__main__":
    logger = trt.Logger(trt.Logger.WARNING)
    with open("rtdetr-l.engine", "rb") as f, trt.Runtime(logger) as runtime:
        engine = runtime.deserialize_cuda_engine(f.read())
    context = engine.create_execution_context()
    inputs_host = cuda.pagelocked_empty(trt.volume(context.get_binding_shape(0)), dtype=np.float32)
    outputs_host = cuda.pagelocked_empty(trt.volume(context.get_binding_shape(1)), dtype=np.float32)
    inputs_device = cuda.mem_alloc(inputs_host.nbytes)
    outputs_device = cuda.mem_alloc(outputs_host.nbytes)
    stream = cuda.Stream()
    
    image = cv2.imread('bus.jpg', -1)
    input = letterbox(image, input_shape)
    input = input[:, :, ::-1].transpose(2, 0, 1).astype(dtype=np.float32)  #BGR2RGB和HWC2CHW
    input = input / 255.0
    input = np.expand_dims(input, axis=0)     
    np.copyto(inputs_host, input.ravel())

    with engine.create_execution_context() as context:
        cuda.memcpy_htod_async(inputs_device, inputs_host, stream)
        context.execute_async_v2(bindings=[int(inputs_device), int(outputs_device)], stream_handle=stream.handle)
        cuda.memcpy_dtoh_async(outputs_host, outputs_device, stream)
        stream.synchronize()  
        boxes = filter_box(outputs_host.reshape(context.get_binding_shape(1)))
        draw(image, boxes)
        cv2.imwrite('result.jpg', image)