Tensorflow 对象检测中的裁剪框并将其显示为 jpg 图像 [英] Crop Boxes in Tensorflow Object Detection and display it as jpg image

问题描述

我正在使用 tensorflow 对象检测来检测护照上的特定数据，例如全名和其他内容.我已经训练了数据，一切正常.它使用边界框完美地识别周围的数据.但是，现在我只想裁剪检测到的框.

I'm using the tensorflow objection detection to detect specific data on passports like full name and other things. I've already trained the data and everything is working fine. It perfectly identifies data surrounding it with a bounding box. However, now I just want to crop the detected boxes.

代码:

import os
import cv2
import numpy as np
import tensorflow as tf
import sys

sys.path.append("..")

from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util

MODEL_NAME = 'inference_graph'

CWD_PATH = os.getcwd()

PATH_TO_CKPT = 'C:/Users/UI UX/Desktop/Captcha 3/CAPTCHA_frozen_inference_graph.pb'

PATH_TO_LABELS = 'C:/Users/UI UX/Desktop/Captcha 3/CAPTCHA_labelmap.pbtxt'

PATH_TO_IMAGE = 'C:/Users/UI UX/Desktop/(47).jpg'

NUM_CLASSES = 11

label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)

detection_graph = tf.Graph()
with detection_graph.as_default():
    od_graph_def = tf.GraphDef()
    with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
        serialized_graph = fid.read()
        od_graph_def.ParseFromString(serialized_graph)
        tf.import_graph_def(od_graph_def, name='')

    sess = tf.Session(graph=detection_graph)

image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')

detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')

detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')

num_detections = detection_graph.get_tensor_by_name('num_detections:0')

image = cv2.imread(PATH_TO_IMAGE)

image_np = cv2.resize(image, (0, 0), fx=2.0, fy=2.0)

image_expanded = np.expand_dims(image_np, axis=0)

(boxes, scores, classes, num) = sess.run(
    [detection_boxes, detection_scores, detection_classes, num_detections],
    feed_dict={image_tensor: image_expanded})

vis_util.visualize_boxes_and_labels_on_image_array(
    image_np,
    np.squeeze(boxes),
    np.squeeze(classes).astype(np.int32),
    np.squeeze(scores),
    category_index,
    use_normalized_coordinates=True,
    line_thickness=2,
    min_score_thresh=0.60)

width, height = image_np.shape[:2]
for i, box in enumerate(np.squeeze(boxes)):
      if(np.squeeze(scores)[i] > 0.80):
        (ymin, xmin, ymax, xmax) = (box[0]*height, box[1]*width, box[2]*height, box[3]*width)
        cropped_image = tf.image.crop_to_bounding_box(image_np, ymin, xmin, ymax - ymin, xmax - xmin)
        cv2.imshow('cropped_image', image_np)
        cv2.waitKey(0)

cv2.imshow('Object detector', image_np)

cv2.waitKey(0)

cv2.destroyAllWindows()

但收到此错误:

回溯(最近一次调用最后一次):文件C:/Users/UI UX/PycharmProjects/pythonProject1/vedio_object_detection.py"，第 71 行，在cropped_image = tf.image.crop_to_bounding_box(image_np, ymin, xmin, ymax - ymin, xmax - xmin)文件C:\ProgramData\Anaconda2\envs\tf_cpu\lib\site-packages\tensorflow_core\python\ops\image_ops_impl.py"，第875行，在crop_to_bounding_boxarray_ops.stack([-1, target_height, target_width, -1]))文件C:\ProgramData\Anaconda2\envs\tf_cpu\lib\site-packages\tensorflow_core\python\ops\array_ops.py"，第 855 行，切片返回 gen_array_ops.slice(input, begin, size, name=name)文件C:\ProgramData\Anaconda2\envs\tf_cpu\lib\site-packages\tensorflow_core\python\ops\gen_array_ops.py"，第 9222 行，在 _slice 中切片"，输入=输入，开始=开始，大小=大小，名称=名称)文件C:\ProgramData\Anaconda2\envs\tf_cpu\lib\site-packages\tensorflow_core\python\framework\op_def_library.py"，第 632 行，在 _apply_op_helper参数名称=输入名称)文件C:\ProgramData\Anaconda2\envs\tf_cpu\lib\site-packages\tensorflow_core\python\framework\op_def_library.py"，第 61 行，在 _SatisfiesTypeConstraint", ".join(dtypes.as_dtype(x).name for x in allowed_list)))类型错误:传递给参数开始"的值的数据类型 float32 不在允许值列表中:int32、int64

but get this error:

Traceback (most recent call last): File "C:/Users/UI UX/PycharmProjects/pythonProject1/vedio_object_detection.py", line 71, in cropped_image = tf.image.crop_to_bounding_box(image_np, ymin, xmin, ymax - ymin, xmax - xmin) File "C:\ProgramData\Anaconda2\envs\tf_cpu\lib\site-packages\tensorflow_core\python\ops\image_ops_impl.py", line 875, in crop_to_bounding_box array_ops.stack([-1, target_height, target_width, -1])) File "C:\ProgramData\Anaconda2\envs\tf_cpu\lib\site-packages\tensorflow_core\python\ops\array_ops.py", line 855, in slice return gen_array_ops.slice(input, begin, size, name=name) File "C:\ProgramData\Anaconda2\envs\tf_cpu\lib\site-packages\tensorflow_core\python\ops\gen_array_ops.py", line 9222, in _slice "Slice", input=input, begin=begin, size=size, name=name) File "C:\ProgramData\Anaconda2\envs\tf_cpu\lib\site-packages\tensorflow_core\python\framework\op_def_library.py", line 632, in _apply_op_helper param_name=input_name) File "C:\ProgramData\Anaconda2\envs\tf_cpu\lib\site-packages\tensorflow_core\python\framework\op_def_library.py", line 61, in _SatisfiesTypeConstraint ", ".join(dtypes.as_dtype(x).name for x in allowed_list))) TypeError: Value passed to parameter 'begin' has DataType float32 not in list of allowed values: int32, int64

有什么帮助吗?

推荐答案

我通过在此行末尾添加以下代码找到了解决方案:

I found the solution of this by add this pice of code after end of this line:

(boxes, scores, classes, num) = sess.run([detection_boxes, detection_scores, detection_classes, num_detections],feed_dict={image_tensor: image_expanded})

我补充一下:

(frame_height, frame_width) = image.shape[:2]

for i in range(len(np.squeeze(scores))):
#print(np.squeeze(boxes)[i])
ymin = int((np.squeeze(boxes)[i][0]*frame_height))
xmin = int((np.squeeze(boxes)[i][1]*frame_width))
ymax = int((np.squeeze(boxes)[i][2]*frame_height))
xmax = int((np.squeeze(boxes)[i][3]*frame_width))
cropped_img = image[ymax:ymin,xmax:xmin]
cv2.imwrite(f'/your/path/img_{i}.png', cropped_img)

这篇关于Tensorflow 对象检测中的裁剪框并将其显示为 jpg 图像的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！