python - 预期 ndim = 4 发现 ndim = 5 和其他错误 - Keras - GTSRB 数据集
问题描述
我正在尝试基于 GTSRB 数据集(下面给出的链接)制作一个 CNN 模型,但我遇到了以下错误:
当我设置 input_shape = input_shape=(3, IMG_SIZE, IMG_SIZE) 时,我收到此错误:
ValueError:检查输入时出错:预期 conv2d_34_input 有 4 个维度,但得到了形状为 (9030, 1) 的数组
当我研究这个问题时,我发现一种解决方案可能是将 batch_size 作为参数传递,当我尝试这样做时,我得到了这个错误:
ValueError: Input 0 is in compatible with layer conv2d_40: expected ndim=4, found ndim=5
当我尝试重塑 training_images 时,出现此错误:
ValueError:无法将大小为 9030 的数组重新整形为形状 (48,48,3)
代码片段:加载训练数据集:
import csv
# Training dataset
def readTrafficSignsTrain(rootpath):
'''Reads traffic sign data for German Traffic Sign Recognition Benchmark.
Arguments: path to the traffic sign data, for example './GTSRB/Training'
Returns: list of images, list of corresponding labels'''
images = [] # images
labels = [] # corresponding labels
# loop over all 42 classes
for c in range(0,43):
# prefix = rootpath + '/' + format(c, '05d') + '/' # subdirectory for class
# annFile = open(prefix + 'GT-'+ format(c, '05d') + '.csv') # annotations file
prefix = rootpath + '/00000' + '/'
annFile = open(prefix + 'GT-00000' + '.csv')
annReader = csv.reader(annFile, delimiter=';') # csv parser for annotations file
next(annReader, None) # skip header
# loop over all images in current annotations file
for row in annReader:
images.append(plt.imread(prefix + row[0])) # the 1st column is the filename
labels.append(row[7]) # the 8th column is the label
annFile.close()
return images, labels
training_images, training_labels = readTrafficSignsTrain('./GTSRB/Training')
这是一个问题,图像形状不一样,例如
print(len(training_images))
print(len(training_labels))
print()
print(training_images[0].shape)
print(training_images[20].shape)
print(training_images[200].shape)
print(training_images[2000].shape)
输出
9030 9030
(30, 29, 3) (54, 57, 3) (69, 63, 3) (52, 51, 3)
图层设置(从下面链接的 Keras 文档复制和粘贴):
IMG_SIZE = 48
NUM_CLASSES = 43
K.set_image_data_format('channels_first')
batch_size = 32
def cnn_model():
model = Sequential()
model.add(Conv2D(32, (3, 3), padding='same',
input_shape=(3, IMG_SIZE, IMG_SIZE),
activation='relu',
data_format="channels_first"))
model.add(Conv2D(32, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2), data_format="channels_first"))
model.add(Dropout(0.2))
model.add(Conv2D(64, (3, 3), padding='same',
activation='relu'))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.2))
model.add(Conv2D(128, (3, 3), padding='same',
activation='relu'))
model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(NUM_CLASSES, activation='softmax'))
return model
model = cnn_model()
训练模型(暂时只是model.fit
import numpy
trim = numpy.array(training_images)
trlb = numpy.array(training_labels)
print(training_images[0].shape)
print(trim.shape)
trim - trim.reshape(48, 48, 3)
model.fit(trim, trlb, epochs = 30, batch_size = 32)
输出
ValueError:无法将大小为 9030 的数组重新整形为形状 (48,48,3)
当我删除重塑
ValueError:检查输入时出错:预期 conv2d_41_input 有 4 个维度,但得到了形状为 (9030, 1) 的数组
当我改用它时
model.fit(training_images, training_labels, epochs = 30, batch_size = 32)
输出
> ValueError: Error when checking model input: the list of Numpy arrays
> that you are passing to your model is not the size the model expected.
> Expected to see 1 array(s), but instead got the following list of 9030
> arrays: [array([[[ 75, 78, 80],
> [ 74, 76, 78],
> [ 86, 87, 84],
> ...,
> [ 68, 75, 75],
> [ 65, 69, 68],
> [ 66, 67, 66]],
>
> [[ 83, 84, 86],
> [...
所以,如果我这样做(不太确定为什么)
for i in range(len(training_images)):
model.fit(training_images[i], training_labels[i], epochs = 30, batch_size = 32)
我明白了
ValueError:检查输入时出错:预期 conv2d_41_input 有 4 个维度,但得到了形状为 (30, 29, 3) 的数组
那是与
input_shape=(3, IMG_SIZE, IMG_SIZE)
如果我做
input_shape=(batch_size, 3, IMG_SIZE, IMG_SIZE)
我明白了
ValueError: Input 0 is in compatible with layer conv2d_47: expected ndim=4, found ndim=5
model.summary() 的输出
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_34 (Conv2D) (None, 32, 48, 48) 896
_________________________________________________________________
conv2d_35 (Conv2D) (None, 32, 46, 46) 9248
_________________________________________________________________
max_pooling2d_14 (MaxPooling (None, 32, 23, 23) 0
_________________________________________________________________
dropout_14 (Dropout) (None, 32, 23, 23) 0
_________________________________________________________________
conv2d_36 (Conv2D) (None, 64, 23, 23) 18496
_________________________________________________________________
conv2d_37 (Conv2D) (None, 64, 21, 21) 36928
_________________________________________________________________
max_pooling2d_15 (MaxPooling (None, 64, 10, 10) 0
_________________________________________________________________
dropout_15 (Dropout) (None, 64, 10, 10) 0
_________________________________________________________________
conv2d_38 (Conv2D) (None, 128, 10, 10) 73856
_________________________________________________________________
conv2d_39 (Conv2D) (None, 128, 8, 8) 147584
_________________________________________________________________
max_pooling2d_16 (MaxPooling (None, 128, 4, 4) 0
_________________________________________________________________
dropout_16 (Dropout) (None, 128, 4, 4) 0
_________________________________________________________________
flatten_4 (Flatten) (None, 2048) 0
_________________________________________________________________
dense_10 (Dense) (None, 512) 1049088
_________________________________________________________________
dropout_17 (Dropout) (None, 512) 0
_________________________________________________________________
dense_11 (Dense) (None, 43) 22059
=================================================================
Total params: 1,358,155
Trainable params: 1,358,155
Non-trainable params: 0
_________________________________________________________________
None
如果有人可以提供帮助,那将不胜感激。
链接 GTSRB:http ://benchmark.ini.rub.de/?section=gtsrb&subsection=news Keras 文档我的模型来自:https ://chsasank.github.io/keras-tutorial.html
github上完整项目的链接:https ://github.com/PavlySz/TSR-Project
谢谢!
解决方案
您不能将 np.array 重塑为尺寸不允许的东西。这是你可以做的
import numpy as np
img_arr = np.array([np.ones((30, 29, 3)),
np.ones((54, 57, 3)),
np.ones((69, 63, 3)),
np.ones((52, 51, 3))])
print(img_arr.shape)
import cv2
img_arr_conv = np.array([cv2.resize(img, dsize=(48, 48)) for img in img_arr])
print(img_arr_conv.shape)
>>>(4,)
>>>(4, 48, 48, 3)
您得到的ValueError: cannot reshape array of size 9030 into shape (48,48,3)
原因是,如果元素的大小都不同,numpy 无法推断数组的维度,并且它无法重塑维度不允许的数组。对于ValueError: Error when checking input: expected conv2d_41_input to have 4 dimensions, but got array with shape (9030, 1)
. Numpy 只知道数组中有 9030 个元素。它不能做更多的事情,因为元素的所有维度都是不同的。
例子
img_arr_bad = np.array([np.ones((30, 29, 3)),
np.ones((54, 57, 3)),
np.ones((69, 63, 3)),
np.ones((52, 51, 3))])
img_arr_good = np.array([np.ones((48, 48, 3)),
np.ones((48, 48, 3)),
np.ones((48, 48, 3)),
np.ones((48, 48, 3))])
print(img_arr_bad.shape)
print(img_arr_good.shape)
>>>(4,)
>>>(4, 48, 48, 3)
希望这可以帮助
推荐阅读
- angular - Auth0 with Angular and Oidc-client
- javascript - 通过 Ajax 发送 acf_form()
- python - Notepad ++的Python缩进插件不自动缩进
- css - 为什么我的 CSS 网格不会填满整个屏幕?
- ios - How to display the song selected album artwork to an ImageView in Swift
- reactjs - React Bootstrap - [HMR] 等待来自 WDS 错误的更新信号
- javascript - 如何在 react-native (web/android/ios) 中的图像上创建链接?
- laravel - [Route: patients.destroy] [URI: {language}/patients/{patient}] 缺少必需的参数。(资源/视图/患者/index.blade.php)
- python - IMAP 消息获取 UnicodeDecodeError 'utf-8' codec can't decode
- python - Python pd.read_csv:如何通过循环读取文件?