我即将结束一个教程，创建一个自定义对象检测模型来识别徽标，但我已经被卡住了一段时间。因此，我已经尝试了我在堆栈溢出问题上看到的所有解决方案，但不幸的是，它没有起作用。我目前遇到的问题是，我的np数组是一个形状为(145，(的1D数组。我试过用来修复它的结构，但对我来说没有效果。我试过了：
train_images=np.array(train_images，dtype=对象(
train_images=np.aarray(train_images(
以及其他几种变体
库：
import matplotlib.pyplot as plt
import numpy as np
import os
import PIL
import tensorflow as tf
import pathlib
import pandas as pd
from PIL import IcnsImagePlugin
from PIL.ImageDraw import Draw
import glob
import pandas as pd
import xml.etree.ElementTree as ET
from tensorflow.keras.utils import to_categorical
from keras.preprocessing import image
from sklearn.model_selection import train_test_split
from skimage.segmentation import mark_boundaries
将我的xml文件[边界框图像]转换为2个csv文件。一个用于训练图像，一个用于验证图像。使用Labeimg创建边界框：
SKIP_NEGATIVES = True
NEGATIVE_CLASS = "no_logo"
def xml_to_csv(path, skipNegatives):
xml_list = []
for xml_file in glob.glob(path + '/*.xml'):
#print("XML_FILE is: "+xml_file)
tree = ET.parse(xml_file)
root = tree.getroot()
if root.find('object'):
for member in root.findall('object'):
bbx = member.find('bndbox')
xmin = round(float(bbx.find('xmin').text))
ymin = round(float(bbx.find('ymin').text))
xmax = round(float(bbx.find('xmax').text))
ymax = round(float(bbx.find('ymax').text))
label = member.find('name').text
value = (root.find('filename').text,
int(root.find('size')[0].text),
int(root.find('size')[1].text),
label,
xmin,
ymin,
xmax,
ymax
)
print(value)
if(value[1]>0 and value[2]>0):
xml_list.append(value)
print("Value appended",end=" ")
print(value)
elif not skipNegatives:
value = (root.find('filename').text,
int(root.find('size')[0].text),
int(root.find('size')[1].text),
NEGATIVE_CLASS,
0,
0,
0,
0
)
print("Printing Value")
print(value)
if(value[1]>0 and value[2]>0):
xml_list.append(value)
print("Value appended",end=" ")
print(value)
else:
print("VALUE NOT APPENDED")
column_name = ['filename', 'width', 'height',
'class', 'xmin', 'ymin', 'xmax', 'ymax']
print("Printing XML_LIST: ")
print(xml_list)
xml_df = pd.DataFrame(xml_list, columns=column_name)
print("Printing xml_df")
print(xml_df)
return xml_df
def main():
datasets = ['/content/drive/MyDrive/Logo_Model/train','/content/drive/MyDrive/Logo_Model/validation']
for ds in datasets:
image_path = os.path.join(os.getcwd(), 'Images', ds)
xml_df = xml_to_csv(image_path, SKIP_NEGATIVES)
print(xml_df)
xml_df.to_csv('/{}_data.csv'.format(ds), index=None)
print('Successfully converted xml to csv.')
main()
现在问题就从这里开始了。当train_img_arr被附加到train_images时，我得到的train_image的形状为(145，(。验证数据也是如此。
num_classes = 2
classes = ["logo","no_logo"]
TRAINING_CSV_FILE = '/content/drive/MyDrive/Logo_Model/train/logo_data.csv'
TRAINING_IMAGE_DIR = '/content/drive/MyDrive/Logo_Model/train/'
training_image_records = pd.read_csv(TRAINING_CSV_FILE)
train_image_path = os.path.join(os.getcwd(), TRAINING_IMAGE_DIR)
train_images = []
train_targets = []
train_labels = []
for index, row in training_image_records.iterrows():
(filename, width, height, class_name, xmin, ymin, xmax, ymax) = row
train_image_fullpath = os.path.join(train_image_path, filename)
train_img = tf.keras.preprocessing.image.load_img(train_image_fullpath, target_size=(height, width))
train_img_arr = tf.keras.preprocessing.image.img_to_array(train_img)
xmin = round(xmin/ width, 2)
ymin = round(ymin/ height, 2)
xmax = round(xmax/ width, 2)
ymax = round(ymax/ height, 2)
train_images.append(train_img_arr)
train_targets.append((xmin, ymin, xmax, ymax))
train_labels.append(classes.index(class_name))
train_img_arr:的样本输出
(78, 323, 3)
(180, 235, 3)
(180, 166, 3)
(156, 311, 3)
(180, 342, 3)
(180, 197, 3)
(180, 315, 3)
(180, 297, 3)
(180, 156, 3)
(180, 190, 3)
(180, 325, 3)
(180, 227, 3)
(176, 192, 3)
(180, 235, 3)
(180, 138, 3)
(180, 222, 3)
(180, 213, 3)
转换为np数组：
train_images = np.array(train_images)
train_targets = np.array(train_targets)
train_labels = np.array(train_labels)
print(train_images.shape)
print(train_targets.shape)
print(train_labels.shape)
输出：
(145,)
(145, 4)
(145,)
/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:2: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray.
这是我的代码的其余部分
VALIDATION_CSV_FILE = '/content/drive/MyDrive/Logo_Model/validation/logo_data.csv'
VALIDATION_IMAGE_DIR = '/content/drive/MyDrive/Logo_Model/validation/'
validation_image_records = pd.read_csv(VALIDATION_CSV_FILE)
validation_image_path = os.path.join(os.getcwd(), VALIDATION_IMAGE_DIR)
validation_images = []
validation_targets = []
validation_labels = []
for index, row in validation_image_records.iterrows():
(filename, width, height, class_name, xmin, ymin, xmax, ymax) = row
validation_image_fullpath = os.path.join(validation_image_path, filename)
validation_img = tf.keras.preprocessing.image.load_img(validation_image_fullpath, target_size=(height, width))
validation_img_arr =tf.keras.preprocessing.image.img_to_array(validation_img)
xmin = round(xmin/ width, 2)
ymin = round(ymin/ height, 2)
xmax = round(xmax/ width, 2)
ymax = round(ymax/ height, 2)
validation_images.append(validation_img_arr)
validation_targets.append((xmin, ymin, xmax, ymax))
validation_labels.append(classes.index(class_name))
validation_images = np.array(validation_images)
validation_targets = np.array(validation_targets)
validation_labels = np.array(validation_labels)
print(validation_images.shape)
print(validation_targets.shape)
print(validation_labels.shape)
input_shape = (height,width,3)
input_layer = tf.keras.layers.Input(input_shape)
#create the base layers
base_layers = tf.keras.layers.experimental.preprocessing.Rescaling(1./255, name='bl_1')(input_layer)
base_layers = tf.keras.layers.Conv2D(16, 3, padding='same', activation='relu', name='bl_2')(base_layers)
base_layers = tf.keras.layers.MaxPooling2D(name='bl_3')(base_layers)
base_layers = tf.keras.layers.Conv2D(32, 3, padding='same', activation='relu', name='bl_4')(base_layers)
base_layers = tf.keras.layers.MaxPooling2D(name='bl_5')(base_layers)
base_layers = tf.keras.layers.Conv2D(64, 3, padding='same', activation='relu', name='bl_6')(base_layers)
base_layers = tf.keras.layers.MaxPooling2D(name='bl_7')(base_layers)
base_layers = tf.keras.layers.Flatten(name='bl_8')(base_layers)
#create the classifier branch
classifier_branch = tf.keras.layers.Dense(128, activation='relu', name='cl_1')(base_layers)
classifier_branch = tf.keras.layers.Dense(num_classes, name='cl_head')(classifier_branch)
#create the localiser branch
locator_branch = tf.keras.layers.Dense(128, activation='relu', name='bb_1')(base_layers)
locator_branch = tf.keras.layers.Dense(64, activation='relu', name='bb_2')(locator_branch)
locator_branch = tf.keras.layers.Dense(32, activation='relu', name='bb_3')(locator_branch)
locator_branch = tf.keras.layers.Dense(4, activation='sigmoid', name='bb_head')(locator_branch)
model = tf.keras.Model(input_layer,outputs=[classifier_branch,locator_branch])
model.summary()
losses ={"cl_head":tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), "bb_head":tf.keras.losses.MSE}
model.compile(loss=losses, optimizer='Adam', metrics=['accuracy'])
trainTargets = {
"cl_head": train_labels,
"bb_head": train_targets
}
validationTargets = {
"cl_head": validation_labels,
"bb_head": validation_targets
}
history = model.fit(train_images, trainTargets,validation_data=(validation_images, validationTargets),batch_size=4,epochs=20,shuffle=True,verbose=1)
numpy数组的形状不会显示，因为每个图像的形状都不是固定的。
添加tf.image.resize，使图像的形状固定。
train_img_arr = tf.keras.preprocessing.image.img_to_array(train_img)
train_img_arr = tf.image.resize(train_img_arr, (size1, size2))
如果你希望你的输入数据有不同的形状，你可以检查这个链接。