将边界框提取为.jpg

Question

将检测到的对象与边界框一起提取，并将其另存为我的磁盘上的图像。

我已经采用了边缘电子的代码并成功地训练和测试了该模型。我的图像上有一个边界框。

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)

这是我得到的错误：

Traceback (most recent call last):   File "objd_1.py", line
75, in <module>
     white_bg_img = 255*np.ones(PATH_TO_IMAGE[paths].shape, np.uint8) AttributeError: 'str' object has no attribute 'shape' 

我搜索了很多，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？

Answer 1

您尝试从文件名而不是图像中获取shape。更换

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

至

white_bg_img = 255*np.ones(image.shape, np.uint8)

编辑：更正的代码

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)