一、环境搭建

1、使用昇腾开发者套件进行一键制卡；

      制卡参考：https://www.hiascend.com/document/detail/zh/Atlas200IDKA2DeveloperKit/23.0.RC2/qs/qs_0018.html

2、环境依赖

一、模型格式转换

将pt模型文件转为onnx

import argparse
from ultralytics import YOLO

def main():
    model = YOLO("yolo11s.pt")
    onnx_model = model.export(format="onnx", dynamic=False, simplify=True, opset=11)

if __name__ == '__main__':
    main()

使用ATC工具将onnx转为昇腾支持的om

atc --model=yolo11s.onnx --framework=5 --output=yolo11s  --input_format=NCHW --input_shape="images:1,3,640,640" --soc_version=Ascend310B4

二、推理代码

创建一个py文件，将代码复制，运行；

import cv2
import numpy as np
from ais_bench.infer.interface import InferSession

CLASSES = {
    0: 'person', 1: 'bicycle', 2: 'car', 3: 'motorcycle', 4: 'airplane', 5: 'bus', 6: 'train', 7: 'truck',
    8: 'boat', 9: 'traffic light', 10: 'fire hydrant', 11: 'stop sign', 12: 'parking meter', 13: 'bench',
    14: 'bird', 15: 'cat', 16: 'dog', 17: 'horse', 18: 'sheep', 19: 'cow', 20: 'elephant', 21: 'bear',
    22: 'zebra', 23: 'giraffe', 24: 'backpack', 25: 'umbrella', 26: 'handbag', 27: 'tie', 28: 'suitcase',
    29: 'frisbee', 30: 'skis', 31: 'snowboard', 32: 'sports ball', 33: 'kite', 34: 'baseball bat',
    35: 'baseball glove', 36: 'skateboard', 37: 'surfboard', 38: 'tennis racket', 39: 'bottle',
    40: 'wine glass', 41: 'cup', 42: 'fork', 43: 'knife', 44: 'spoon', 45: 'bowl', 46: 'banana', 47: 'apple',
    48: 'sandwich', 49: 'orange', 50: 'broccoli', 51: 'carrot', 52: 'hot dog', 53: 'pizza', 54: 'donut',
    55: 'cake', 56: 'chair', 57: 'couch', 58: 'potted plant', 59: 'bed', 60: 'dining table', 61: 'toilet',
    62: 'tv', 63: 'laptop', 64: 'mouse', 65: 'remote', 66: 'keyboard', 67: 'cell phone', 68: 'microwave',
    69: 'oven', 70: 'toaster', 71: 'sink', 72: 'refrigerator', 73: 'book', 74: 'clock', 75: 'vase',
    76: 'scissors', 77: 'teddy bear', 78: 'hair drier', 79: 'toothbrush'
}

# 置信度阈值
CONFIDENCE = 0.4
# NMS 的 IoU 阈值
IOU = 0.45

# 为每个类别分配随机颜色
colors = np.random.uniform(0, 255, size=(len(CLASSES), 3))


def draw_bounding_box(img, class_id, confidence, x, y, x_plus_w, y_plus_h):

    label = "{} {:.2f}".format(CLASSES[class_id], confidence)
    color = colors[class_id]

    cv2.rectangle(img, (x, y), (x_plus_w, y_plus_h), color, 2)

    label_size, _ = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1)
    label_width, label_height = label_size

    label_x = x
    label_y = y - 10 if y - 10 > label_height else y + 10

    cv2.rectangle(img, (label_x, label_y - label_height),
                  (label_x + label_width, label_y + label_height), color, cv2.FILLED)
    cv2.putText(img, label, (label_x, label_y), cv2.FONT_HERSHEY_SIMPLEX,
                0.5, (0, 0, 0), 1, cv2.LINE_AA)


def main(session, original_image):

    height, width, _ = original_image.shape
    length = max(height, width)
    image = np.zeros((length, length, 3), np.uint8)
    image[0:height, 0:width] = original_image
    scale = length / 640
    blob = cv2.dnn.blobFromImage(image, scalefactor=1.0 / 255, size=(640, 640), swapRB=True)
    outputs = session.infer(feeds=blob, mode="static")
    outputs = np.array([cv2.transpose(outputs[0][0])])
    rows = outputs.shape[1]
    boxes = []
    scores = []
    class_ids = []

    for i in range(rows):
        classes_scores = outputs[0][i][4:]
        (minScore, maxScore, minClassLoc, (x, maxClassIndex)) = cv2.minMaxLoc(classes_scores)
        if maxScore >= CONFIDENCE:
            box = [
                (outputs[0][i][0] - outputs[0][i][2] / 2) * scale,  
                (outputs[0][i][1] - outputs[0][i][3] / 2) * scale,  
                outputs[0][i][2] * scale,  
                outputs[0][i][3] * scale   
            ]
            boxes.append(box)
            scores.append(maxScore)
            class_ids.append(maxClassIndex)

    result_boxes = cv2.dnn.NMSBoxes(boxes, scores, CONFIDENCE, IOU, 0.5)

    detections = []

    for i in range(len(result_boxes)):
        index = result_boxes[i]
        box = boxes[index]
        detection = {
            "class_id": class_ids[index],
            "class_name": CLASSES[class_ids[index]],
            "confidence": scores[index],
            "box": box,
            "scale": scale,
        }
        detections.append(detection)
        draw_bounding_box(
            original_image,
            class_ids[index],
            scores[index],
            round(box[0]),
            round(box[1]),
            round(box[0] + box[2]),
            round(box[1] + box[3])
        )

    return original_image, detections

if __name__ == "__main__":
    model_path = "yolo11s.om"
    session = InferSession(device_id=0, model_path=model_path)
    input_image_path = "street.jpg"
    image = cv2.imread(input_image_path)
    draw_image, _ = main(session, image)
    cv2.imwrite("output_image.jpg", draw_image)
    cv2.waitKey(0)
    cv2.destroyAllWindows()

运行结果：

[INFO] acl init success
[INFO] open device 0 success
[INFO] load model yolo11s.om success
[INFO] create model description success
[INFO] unload model success, model Id is 1
[INFO] end to destroy context
[INFO] end to reset device is 0
[INFO] end to finalize acl