7

当我检测到我的 tflite 文件时，问题就发生了。

我写的命令。

python detect.py --weights ./checkpoints/yolov4-tiny-tf.tflite --size 416 --model yolov4 --image D:\yolov4\training\tensorflow-yolov4-tflite-master\data\rice.jpg --framework tflite --tiny true

和错误的信息：

cv2.rectangle(image, c1, c2, bbox_color, bbox_thick)
cv2.error: OpenCV(4.5.2) :-1: error: (-5:Bad argument) in function 'rectangle'
> Overload resolution failed:
>  - Can't parse 'pt1'. Sequence item with index 0 has a wrong type
>  - Can't parse 'pt1'. Sequence item with index 0 has a wrong type
>  - Can't parse 'rec'. Expected sequence length 4, got 2
>  - Can't parse 'rec'. Expected sequence length 4, got 2

这是相关代码。（core/utils.py）

fontScale = 0.5
    score = out_scores[0][i]
    class_ind = int(out_classes[0][i])
    bbox_color = colors[class_ind]
    bbox_thick = int(0.6 * (image_h + image_w) / 600)
    c1, c2 = (coor[1], coor[0]), (coor[3], coor[2])
    cv2.rectangle(image, c1, c2, bbox_color, bbox_thick)

    if show_label:
        bbox_mess = '%s: %.2f' % (classes[class_ind], score)
        t_size = cv2.getTextSize(bbox_mess, 0, fontScale, thickness=bbox_thick // 2)[0]
        c3 = (c1[0] + t_size[0], c1[1] - t_size[1] - 3)
        cv2.rectangle(image, c1, (np.float32(c3[0]), np.float32(c3[1])), bbox_color, -1) #filled

        cv2.putText(image, bbox_mess, (c1[0], np.float32(c1[1] - 2)), cv2.FONT_HERSHEY_SIMPLEX,
                    fontScale, (0, 0, 0), bbox_thick // 2, lineType=cv2.LINE_AA)
return image

我已将其更改为

fontScale = 0.5
    score = out_scores[0][i]
    class_ind = int(out_classes[0][i])
    bbox_color = colors[class_ind]
    bbox_thick = int(0.6 * (image_h + image_w) / 600)
    c1, c2 = (int(coor[1]), int(coor[0])), (int(coor[3]), int(coor[2]))
    print(c1, c2, bbox_color, bbox_thick)
    cv2.rectangle(image, (int(coor[1]), int(coor[0])), (int(coor[3]), int(coor[2])), bbox_color, -1)

    if show_label:
        bbox_mess = '%s: %.2f' % (classes[class_ind], score)
        t_size = cv2.getTextSize(bbox_mess, 0, fontScale, thickness=bbox_thick // 2)[0]
        c3 = (c1[0] + t_size[0], c1[1] - t_size[1] - 3)
        cv2.rectangle(image, (int(coor[1]), int(coor[0])), (int(c3[0]), int(c3[1])), (255, 0, 0), -1) #filled

        cv2.putText(image, bbox_mess, (int(c1[0]), int(c1[1] - 2)), cv2.FONT_HERSHEY_SIMPLEX,
                    fontScale, (0, 0, 0), bbox_thick // 2, lineType=cv2.LINE_AA)
return image

由于它没有出错，它仍然没有显示图像。

    [{'name': 'input_1', 'index': 0, 'shape': array([  1, 416, 416,   3]), 'shape_signature': array([ -1, 416, 416,   3]), 'dtype': <class 'numpy.float32'>, 'quantization': (0.0, 0), 'quantization_parameters': {'scales': array([], dtype=float32), 'zero_points': array([], dtype=int32), 'quantized_dimension': 0}, 'sparsity_parameters': {}}]
[{'name': 'Identity', 'index': 232, 'shape': array([   1, 2535,    4]), 'shape_signature': array([ 1, -1,  4]), 'dtype': <class 'numpy.float32'>, 'quantization': (0.0, 0), 'quantization_parameters': {'scales': array([], dtype=float32), 'zero_points': array([], dtype=int32), 'quantized_dimension': 0}, 'sparsity_parameters': {}}, {'name': 'Identity_1', 'index': 211, 'shape': array([   1, 2535,    2]), 'shape_signature': array([ 1, -1,  2]), 'dtype': <class 'numpy.float32'>, 'quantization': (0.0, 0), 'quantization_parameters': {'scales': array([], dtype=float32), 'zero_points': array([], dtype=int32), 'quantized_dimension': 0}, 'sparsity_parameters': {}}]

最后一条消息

有没有人有任何想法来解决它？谢谢你的帮助！

这是我的文件：https ://github.com/piggychu0w0/food-image-detection

4

2 回答 2

10

问题是您将带有浮点数的元组作为点传递到函数的参数中。这是重现的错误：

import cv2
import numpy as np

img = np.zeros((600, 600), 'uint8')

c1 = 50.2, 12.4
c2 = 88.8, 40.8

cv2.rectangle(img, c1, c2, (255, 0, 0), -1)

输出：

Traceback (most recent call last):
  File "C:/Users/User/Desktop/temp.py", line 9, in <module>
    cv2.rectangle(img, c1, c2, (255, 0, 0), -1)
cv2.error: OpenCV(4.5.2) :-1: error: (-5:Bad argument) in function 'rectangle'
> Overload resolution failed:
>  - Can't parse 'pt1'. Sequence item with index 0 has a wrong type
>  - Can't parse 'pt1'. Sequence item with index 0 has a wrong type
>  - Can't parse 'rec'. Expected sequence length 4, got 2
>  - Can't parse 'rec'. Expected sequence length 4, got 2

要修复它，只需int()在坐标周围使用包装器：

import cv2
import numpy as np

img = np.zeros((600, 600), 'uint8')

c1 = 50.2, 12.4
c2 = 88.8, 40.8

cv2.rectangle(img, (int(c1[0]), int(c1[1])), (int(c2[0]), int(c2[1])), (255, 0, 0), -1)
于 2021-06-10T12:41:38.010 回答
2

只需尝试以下对我有用的更改。

fontScale = 0.5
    score = out_scores[i]
    class_ind = int(out_classes[i])
    bbox_color = colors[class_ind]
    bbox_thick = int(0.6 * (image_h + image_w) / 600)
    c1, c2 = (coor[0], coor[1]), (coor[2], coor[3])
    print(c1, c2, bbox_color, bbox_thick)
    cv2.rectangle(image, (int(c1[0]), int(c1[1])), (int(c2[0]), int(c2[1])), bbox_color, bbox_thick)

    if show_label:
        bbox_mess = '%s: %.2f' % (classes[class_ind], score)
        t_size = cv2.getTextSize(bbox_mess, 0, fontScale, thickness=bbox_thick // 2)[0]
        c3 = (c1[0] + t_size[0], c1[1] - t_size[1] - 3)
        cv2.rectangle(image, (int(c1[0]), int(c1[1])), (int(c3[0]), int(c3[1])), (255, 0, 0), -1) #filled

        cv2.putText(image, bbox_mess, (int(c1[0]), int(c1[1] - 2)), cv2.FONT_HERSHEY_SIMPLEX,
                    fontScale, (0, 0, 0), bbox_thick // 2, lineType=cv2.LINE_AA)
return image
于 2021-06-19T04:39:38.567 回答