python - 'numpy.ndarray' 类型的输出不能与“if”语句进行比较
问题描述
我目前正在从事 tensorflow 图像处理项目。标识了三类对象,分别标记为 1(公共汽车)、2(汽车)和 3(货车)。检测到的输出对象/objetcs 以“numpy.ndarray”类型输出给出。以下是我使用的代码。
# Import packages
import os
import cv2
import numpy as np
import tensorflow as tf
import sys
# This is needed since the notebook is stored in the object_detection
folder.
sys.path.append("..")
# Import utilites
from utils import label_map_util
from utils import visualization_utils as vis_util
# Name of the directory containing the object detection module we're using
MODEL_NAME = 'inference_graph'
# Grab path to current working directory
CWD_PATH = os.getcwd()
# Path to frozen detection graph .pb file, which contains the model that is
used
# for object detection.
PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,'frozen_inference_graph.pb')
# Path to label map file
PATH_TO_LABELS = os.path.join(CWD_PATH,'training','labelmap.pbtxt')
# Number of classes the object detector can identify
NUM_CLASSES = 3
## Load the label map.
# Label maps map indices to category names, so that when our convolution
# network predicts `5`, we know that this corresponds to `king`.
# Here we use internal utility functions, but anything that returns a
# dictionary mapping integers to appropriate string labels would be fine
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)
# Load the Tensorflow model into memory.
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)
# Define input and output tensors (i.e. data) for the object detection
classifier
# Input tensor is the image
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Output tensors are the detection boxes, scores, and classes
# Each box represents a part of the image where a particular object was
detected
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represents level of confidence for each of the objects.
# The score is shown on the result image, together with the class label.
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes =
detection_graph.get_tensor_by_name('detection_classes:0')
# Number of objects detected
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
# Initialize webcam feed
video = cv2.VideoCapture(0)
ret = video.set(3,1280)
ret = video.set(4,720)
while(True):
# Acquire frame and expand frame dimensions to have shape: [1, None,
None, 3]
# i.e. a single-column array, where each item in the column has the
pixel RGB value
ret, frame = video.read()
frame_expanded = np.expand_dims(frame, axis=0)
# Perform the actual detection by running the model with the image as
input
(boxes, scores, classes, num) = sess.run(
[detection_boxes, detection_scores, detection_classes,
num_detections],
feed_dict={image_tensor: frame_expanded})
s_class = classes[scores > 0.6]
print(s_class)
# Draw the results of the detection (aka 'visulaize the results')
vis_util.visualize_boxes_and_labels_on_image_array(
frame,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8,
min_score_thresh=0.60)
# All the results have been drawn on the frame, so it's time to display
it.
cv2.imshow('Object detector', frame)
# Press 'q' to quit
if cv2.waitKey(1) == ord('q'):
break
# Clean up
video.release()
cv2.destroyAllWindows()
在这段代码中,
s_class = classes[scores > 0.6]
print(s_class)
添加只是为了可视化输出。输出是 numpy.ndarray 类型的输出,打印为,
>>[2.] #car is detected
[3. 2. 1.] #all three objects(van,car,bus) are detected
[1. 2. 3.] #all three objects(bus,car,van) are detected
[1. 2. 3.]
[1. 2. 3.]
[2. 1. 3.]
[2. 1. 3.]
[2. 1. 3.]
[2. 1. 3.]
[2. 3. 1.]
[2. 3. 1.]
[] #nothing is detected
[2.] #only second object(car) is detected
[]
[1.] #only first object(bus) is detected
并继续...对象在数组中未按有组织的顺序表示(例如:- [1. 2. 3.] 或 [2. 1. 3.]...等 - 它改变了位置)。如果检测到对象 2(汽车)和/或对象 3(货车),我需要打印“小”,当检测到对象 1(公共汽车)时,我需要打印“大”。对象 1(公共汽车)也被对象 2(汽车)和/或对象 3(货车)检测到,它应该打印“小”。我试过了,
if (s_class==1):
print("large")
elif (s_class==2 or s_class==3):
print("small")
elif (s_class==1 and (s_class==2 or s_class==3)):
print("small")
elif (s_class==1 and s_class==2 and s_class==3 ):
print("small")
这不起作用,因为我比较 numpy.ndarray 的方式可能是错误的。如何将此 numpy.ndarray 与上述条件进行比较以打印所需的输出?
解决方案
假设它s_class
是一个或多个数组,以下代码会消除空子数组并根据子数组是否仅包含 1 来报告“大”或“小”:
[("large" if s.max() < 1.5 else "small") for s in s_class if s.any()]
如果您想报告空子数组的某些内容而不是简单地丢弃它们,请添加另一个子句:
[(("large" if s.max() < 1.5 else "small")
if s.any() else "empty") for s in s_class]
推荐阅读
- swiftui - 使用 ForEach 分层视图并使用 ZStack 偏移以创建一堆扑克筹码 (SwiftUI)
- html - Bootstrap - 在jumbotron上拥有一张卡片的最佳方式是什么?
- r - 使 igraph 图形在 Shiny App 中具有可移动节点的简单方法?
- laravel - search between 2 different dates with laravel
- android - 在 Android 上使用 DocuSign SDK 缓存模板需要多少可用空间?
- macos - terraform 手动安装插件失败
- regex - Combine two references into one or some serious regex work
- go - go get fails for hashicorp/levant
- python - Get the first layer of html sections only using Beautiful Soup using recursive strategy
- python - Sorting List of Dataframes