YOLO11 自定义数据集从训练到部署

准备好数据集以后，直接按下面的命令行运行即可：

yolo train model=yolo11n.pt data=cbc_dataset.yaml epochs=25 imgsz=640 batch=4

模型导出与测试

yolo export model=cbc_11.pt format=onnxyolo predict model=cbc_11.pt source=./cbc

转成ONNX格式文件以后，基于OpenVINO-Python部署推理，相关代码如下

frame = cv.imread(os.path.join("D:/cbc_analysis/data/", f))bgr = format_yolov8(frame)img_h, img_w, img_c = bgr.shape

start = time.time()image = cv.dnn.blobFromImage(bgr, 1 / 255.0, (640, 640), swapRB=True, crop=False)

res = compiled_model([image])[output_layer] # 1x84x8400rows = np.squeeze(res, 0).Tclass_ids = []confidences = []boxes = []x_factor = img_w / 640y_factor = img_h / 640

for r in range(rows.shape[0]):row = rows[r]classes_scores = row[4:]_, _, _, max_indx = cv.minMaxLoc(classes_scores)class_id = max_indx[1]if (classes_scores[class_id] > .25):confidences.append(classes_scores[class_id])class_ids.append(class_id)x, y, w, h = row[0].item(), row[1].item(), row[2].item(), row[3].item()left = int((x - 0.5 * w) * x_factor)top = int((y - 0.5 * h) * y_factor)width = int(w * x_factor)height = int(h * y_factor)box = np.array([left, top, width, height])boxes.append(box)

indexes = cv.dnn.NMSBoxes(boxes, confidences, 0.25, 0.45)for index in indexes:box = boxes[index]color = colors[int(class_ids[index]) % len(colors)]rr = int((box[2] + box[3])/4)cv.circle(frame, (box[0]+int(box[2]/2), box[1]+int(box[3]/2)), rr-4, color, 2)cv.putText(frame, class_list[class_ids[index]], (box[0] + int(box[2] / 2), box[1] + int(box[3] / 2)),   cv.FONT_HERSHEY_SIMPLEX, .5, (0, 0, 0))cv.putText(frame, "gloomyfish@2024", (20, 45), cv.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2)

cv.imshow("YOLO11+OpenVINO2024 RBC(Red Blood Cell) Count", frame)cv.imwrite("D:/rbc_result.jpg", frame)cv.waitKey(0)

推荐阅读

OpenCV4.8+YOLOv8对象检测C++推理演示