图片中有多辆车时报错

请看是否可以解决一下？
image 1/4 inference\images\1.png: torch.Size([1, 20160, 6])
E:\traffic_violation_detection\gitee_jiangmaowei\utils\utils.py:883: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at C:\cb\pytorch_1000000000000\work\torch\csrc\utils\tensor_new.cpp:264.)
  preds = model(torch.Tensor(ims).to(d.device))  # classifier prediction
b'truck 0.86' 0 51 265 334
E:\traffic_violation_detection\gitee_jiangmaowei\utils\utils_1.py:82: UserWarning: The torch.cuda.*DtypeTensor constructors are no longer recommended. It's best to use methods such as torch.tensor(data, dtype=*, device='cuda') to create tensors. (Triggered internally at C:\cb\pytorch_1000000000000\work\torch\csrc\tensor\python_tensor.cpp:85.)
  anchor_w = FloatTensor(scaled_anchors).index_select(1, LongTensor([0]))
image 2/4 inference\images\2.png: torch.Size([1, 12600, 6])
Traceback (most recent call last):
  File "E:\traffic_violation_detection\gitee_jiangmaowei\detect_car.py", line 188, in <module>
    detect()
  File "E:\traffic_violation_detection\gitee_jiangmaowei\detect_car.py", line 80, in detect
    pred, plat_num = apply_classifier(pred, modelc, img, im0s)
  File "E:\traffic_violation_detection\gitee_jiangmaowei\utils\utils.py", line 910, in apply_classifier
    plat_num=np.array(preb_labels)
ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (3,) + inhomogeneous part.

蒋茂苇/车辆检测计数+车牌定位+车牌识别的融合技术

内容风险标识

评论 (0)

蒋茂苇/车辆检测计数+车牌定位+车牌识别的融合技术 .gitee-modal { width: 500px !important; }

内容风险标识