【发布时间】：2018-10-24 20:03:22
【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 到 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：输入 0 与层 conv2d_40 不兼容：预期 ndim=4，发现 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 (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')
这里有个问题，比如图片的形状不一样
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)
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 (48,48,3)
当我移除重塑
ValueError：检查输入时出错：预期 conv2d_41_input 到 有 4 个维度，但得到了形状为 (9030, 1) 的数组
当我改用这个时
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 到 有 4 个维度，但得到了形状为 (30, 29, 3) 的数组
那就是
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：输入 0 与层 conv2d_47 不兼容：预期 ndim=4，发现 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
如果有人能提供帮助，将不胜感激。
链接 GTSRB：http://benchmark.ini.rub.de/?section=gtsrb&subsection=news 我从 Keras 文档中获取模型：https://chsasank.github.io/keras-tutorial.html
github上完整项目的链接：https://github.com/PavlySz/TSR-Project
谢谢！
【问题讨论】：
标签： python arrays tensorflow keras training-data