Python 将边界框提取为.jpg

提取检测到的对象以及边界框，并将其保存为磁盘上的图像

我学习了Edge Electronics的代码，并成功地对模型进行了培训和测试。我在我的图像上得到了边界框

import os
import cv2
import numpy as np
import tensorflow as tf
import sys
from glob import glob
import glob
import csv
from PIL import Image
import json

sys.path.append("..")

# Import utilites
from utils import label_map_util
from utils import visualization_utils as vis_util

MODEL_NAME = 'inference_graph'

CWD_PATH = os.getcwd()

PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,'frozen_inference_graph.pb')

PATH_TO_LABELS = os.path.join(CWD_PATH,'training','labelmap.pbtxt')

PATH_TO_IMAGE = list(glob.glob("C:\\new_multi_cat\\models\\research\\object_detection\\img_test\\*jpeg"))

NUM_CLASSES = 3

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')


for paths in range(len(PATH_TO_IMAGE)):
    image = cv2.imread(PATH_TO_IMAGE[paths])
    image_expanded = np.expand_dims(image, 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.squeeze(boxes),
    np.squeeze(classes).astype(np.int32),
    np.squeeze(scores),
    category_index,
    use_normalized_coordinates=True,
    line_thickness=4,
    min_score_thresh=0.80)


    white_bg_img = 255*np.ones(PATH_TO_IMAGE[paths].shape, np.uint8)
    vis_util.draw_bounding_boxes_on_image(
    white_bg_img ,
    np.squeeze(boxes),
    color='red',
    thickness=4)
    cv2.imwrite("bounding_boxes.jpg", white_bg_img)

    boxes = np.squeeze(boxes)
    for i in range(len(boxes)):
        box[0]=box[0]*height
        box[1]=box[1]*width
        box[2]=box[2]*height
        box[3]=box[3]*width
    roi = image[box[0]:box[2],box[1]:box[3]].copy()
    cv2.imwrite("box_{}.jpg".format(str(i)), roi)

这就是我得到的错误：

Traceback（最近一次调用last）：文件“objd_1.py”，第行
75，在
白色\u bg\u img=255*np.one（路径到图像[PATH].shape，np.uint8）属性错误：“str”对象没有属性“shape”

---

我已经搜索了很多，但无法识别代码中的错误。为什么我无法将检测到的区域提取为图像？

您尝试从文件名而不是图像中提取

形状。替换

white_bg_img = 255*np.ones(PATH_TO_IMAGE[paths].shape, np.uint8)

到

编辑：已更正代码

import os
import cv2
import numpy as np
import tensorflow as tf
import sys
from glob import glob
import glob
import csv
from PIL import Image
import json

sys.path.append("..")

# Import utilites
from utils import label_map_util
from utils import visualization_utils as vis_util

MODEL_NAME = 'inference_graph'

CWD_PATH = os.getcwd()

PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,'frozen_inference_graph.pb')

PATH_TO_LABELS = os.path.join(CWD_PATH,'training','labelmap.pbtxt')

PATH_TO_IMAGE = list(glob.glob("C:\\new_multi_cat\\models\\research\\object_detection\\img_test\\*jpeg"))

NUM_CLASSES = 3

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')


for paths in range(len(PATH_TO_IMAGE)):
    image = cv2.imread(PATH_TO_IMAGE[paths])
    image_expanded = np.expand_dims(image, 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.squeeze(boxes),
    np.squeeze(classes).astype(np.int32),
    np.squeeze(scores),
    category_index,
    use_normalized_coordinates=True,
    line_thickness=4,
    min_score_thresh=0.80)


    white_bg_img = 255*np.ones(image.shape, np.uint8)
    vis_util.draw_bounding_boxes_on_image_array(
    white_bg_img ,
    np.squeeze(boxes),
    color='red',
    thickness=4)
    cv2.imwrite("bounding_boxes.jpg", white_bg_img)

    boxes = np.squeeze(boxes)
    for i in range(len(boxes)):
        box[0]=box[0]*height
        box[1]=box[1]*width
        box[2]=box[2]*height
        box[3]=box[3]*width
    roi = image[box[0]:box[2],box[1]:box[3]].copy()
    cv2.imwrite("box_{}.jpg".format(str(i)), roi)

我按照你的建议做了，但这又放弃了另一个错误。AttributeError:'numpy.ndarray'对象没有属性'load'，因为变量映像中的值是numpy ndarray。我在一个图像目录中循环，并在图像变量中读取它，就像这样，读取范围内的路径（len（PATH_TO_image））：image=cv2.imread（PATH_TO_image[paths]）@Ankit
pilImage=image.fromarray（image）
从numpy数组获取PIL图像。然后将此
pilmimage
传递给传递numpy数组的PIL函数（或期望PIL图像的其他函数）<代码>可视化\u框\u和\u标签\u在\u图像\u数组上

例如需要PIL图像。您的问题已明确说明为特定的错误消息。如果建议的解决方案解决了这个问题，请考虑接受答案。如果您有任何其他问题，请询问其他人question@Oliort：针对范围内的路径（len（PATH_TO_IMAGE））：IMAGE=cv2.imread（PATH_TO_IMAGE[paths]）pilImage=IMAGE.fromarray（IMAGE）和passed pilImage以可视化_IMAGE_数组上的_框和标签。获取错误np.copyto（image，np.array（image_pil））TypeError:copyto（）参数1必须是numpy.ndarray，而不是Image@Sharky如果有任何解决方案解决了我的问题，我一定会接受它作为解决方案answer@halfer我是新来的。为我的帖子道歉。我会记住你的建议

import os
import cv2
import numpy as np
import tensorflow as tf
import sys
from glob import glob
import glob
import csv
from PIL import Image
import json

sys.path.append("..")

# Import utilites
from utils import label_map_util
from utils import visualization_utils as vis_util

MODEL_NAME = 'inference_graph'

CWD_PATH = os.getcwd()

PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,'frozen_inference_graph.pb')

PATH_TO_LABELS = os.path.join(CWD_PATH,'training','labelmap.pbtxt')

PATH_TO_IMAGE = list(glob.glob("C:\\new_multi_cat\\models\\research\\object_detection\\img_test\\*jpeg"))

NUM_CLASSES = 3

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')


for paths in range(len(PATH_TO_IMAGE)):
    image = cv2.imread(PATH_TO_IMAGE[paths])
    image_expanded = np.expand_dims(image, 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.squeeze(boxes),
    np.squeeze(classes).astype(np.int32),
    np.squeeze(scores),
    category_index,
    use_normalized_coordinates=True,
    line_thickness=4,
    min_score_thresh=0.80)


    white_bg_img = 255*np.ones(image.shape, np.uint8)
    vis_util.draw_bounding_boxes_on_image_array(
    white_bg_img ,
    np.squeeze(boxes),
    color='red',
    thickness=4)
    cv2.imwrite("bounding_boxes.jpg", white_bg_img)

    boxes = np.squeeze(boxes)
    for i in range(len(boxes)):
        box[0]=box[0]*height
        box[1]=box[1]*width
        box[2]=box[2]*height
        box[3]=box[3]*width
    roi = image[box[0]:box[2],box[1]:box[3]].copy()
    cv2.imwrite("box_{}.jpg".format(str(i)), roi)