python - ValueError : Error when checking input: expected conv2d_1_input to have 4 dimensions, 但得到形状为 (454, 512, 512) 的数组

Question

我使用此代码在 keras 中生成我的数据集。但是当我实现我的代码时，它会产生以下错误:

ValueError: Error when checking input: expected conv2d_1_input to have 4 dimensions, but got array with shape (454, 512, 512)

我无法解决它。你能告诉我有什么问题吗？我在网络中使用之前扩展了维度，但它不起作用!你能快速回答我吗，因为我搜索了好几天但找不到解决方案，而且我没有足够的时间:

import os,cv2
import numpy as np
import matplotlib.pyplot as plt

from sklearn.utils import shuffle
from sklearn.cross_validation import train_test_split

from keras import backend as K
#K.set_image_dim_ordering('th')

from keras.utils import np_utils
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.optimizers import SGD,RMSprop,adam

#%%

PATH = os.getcwd()
# Define data path
data_path = r"E:\PhD\thesis\deepwatermark\databasetest\train"
data_dir_list = os.listdir(data_path)

img_rows=512
img_cols=512
num_channel=1
num_epoch=20

# Define the number of classes
num_classes = 7

labels_name={'CRP':0,'GF':1,'GN':2,'JPG':3,'MED':4,'ROT':5,'SP':6}

img_data_list=[]
labels_list = []

for dataset in data_dir_list:
    img_list=os.listdir(data_path+'/'+ dataset)
    print ('Loading the images of dataset-'+'{}\n'.format(dataset))
    label = labels_name[dataset]
    for img in img_list:
        input_img=cv2.imread(data_path + '/'+ dataset + '/'+ img )
        input_img=cv2.cvtColor(input_img, cv2.COLOR_BGR2GRAY)
        input_img_resize=cv2.resize(input_img,(512,512))
        img_data_list.append(input_img_resize)
        labels_list.append(label)

img_data = np.array(img_data_list)
img_data = img_data.astype('float32')
img_data /= 255
print (img_data.shape)

labels = np.array(labels_list)
# print the count of number of samples for different classes
print(np.unique(labels,return_counts=True))
# convert class labels to on-hot encoding
Y = np_utils.to_categorical(labels, num_classes)

#Shuffle the dataset
x,y = shuffle(img_data,Y, random_state=2)
# Split the dataset
X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=2)
img_data= np.expand_dims(img_data, axis=4)** 
print (img_data.shape)


# Defining the model
input_shape=img_data[0].shape

model = Sequential()

model.add(Convolution2D(32, 3,3,border_mode='same',input_shape=input_shape))
model.add(Activation('relu'))
model.add(Convolution2D(32, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))

model.add(Convolution2D(64, 3, 3))
model.add(Activation('relu'))
#model.add(Convolution2D(64, 3, 3))
#model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))

model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes))
model.add(Activation('softmax'))

#sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
#model.compile(loss='categorical_crossentropy', optimizer=sgd,metrics=["accuracy"])
model.compile(loss='categorical_crossentropy', optimizer='rmsprop',metrics=["accuracy"])

# Viewing model_configuration

model.summary()
model.get_config()
model.layers[0].get_config()
model.layers[0].input_shape         
model.layers[0].output_shape            
model.layers[0].get_weights()
np.shape(model.layers[0].get_weights()[0])
model.layers[0].trainable

#%%
# Training
hist = model.fit(X_train, y_train, batch_size=16, nb_epoch=num_epoch, verbose=1, validation_data=(X_test, y_test))

我的带有生成器的新代码在这里，您发现任何问题吗？我的数据集与以前相同。

import numpy as np
import matplotlib.pyplot as plt
from keras.preprocessing.image import ImageDataGenerator
from sklearn.utils import shuffle
from sklearn.cross_validation import train_test_split
from keras import backend as K
#K.set_image_dim_ordering('th')

from keras.utils import np_utils
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.optimizers import SGD,RMSprop,adam


train_datagen = ImageDataGenerator(
        rescale=1./255,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True)
#
valid_datagen = ImageDataGenerator(
        rescale=1./255,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True)
#
test_datagen = ImageDataGenerator(rescale=1./255)
#
train_generator = train_datagen.flow_from_directory(
    directory=r"E:\databasetest\train",
    target_size=(512, 512),
    color_mode="grayscale",
    batch_size=32,
    class_mode="categorical",
    shuffle=True,
    seed=42
)
#
valid_generator = valid_datagen.flow_from_directory(
   directory=r"E:\databasetest\validation",
    target_size=(512, 512),
    color_mode="grayscale",
    batch_size=32,
    class_mode="categorical",
    shuffle=True,
    seed=42
)
#
test_generator = test_datagen.flow_from_directory(
    directory=r"E:\databasetest\test",
    target_size=(512, 512),
    color_mode="grayscale",
    batch_size=16,
    class_mode=None,
    shuffle=False,
    seed=42
)
#
## neural network model
model = Sequential()
model.add(Conv2D(32, (3,3),border_mode='same', input_shape = (512, 512, 1), activation = 'relu'))
model.add(Activation('relu'))
model.add(Conv2D(32, 3, 3))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))

model.add(Conv2D(64, 3, 3))
model.add(Activation('relu'))
#model.add(Convolution2D(64, 3, 3))
#model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))

model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(7))
model.add(Activation('softmax'))

model.summary()

model.compile(loss = 'categorical_crossentropy',
              optimizer = 'rmsprop',
              metrics = ['accuracy'])
STEP_SIZE_TRAIN=train_generator.n//train_generator.batch_size
STEP_SIZE_VALID=valid_generator.n//valid_generator.batch_size
model.fit_generator(generator=train_generator,
                    steps_per_epoch=STEP_SIZE_TRAIN,
                    validation_data=valid_generator,
                    validation_steps=STEP_SIZE_VALID,
                    epochs=10
)

但是当我实现它时，我再次收到此错误:

ResourceExhaustedError:通过分配器 GPU_0_bfc 在/job:localhost/replica:0/task:0/device:GPU:0 上分配形状为 [32,32,512,512] 的张量并键入 float 时出现 OOM [[节点: conv2d_1/卷积 = Conv2D[T=DT_FLOAT, data_format="NCHW", 膨胀=[1, 1, 1, 1], 填充="SAME", 步幅=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](conv2d_1/卷积-0-TransposeNHWCToNCHW-LayoutOptimizer, conv2d_1/kernel/read)]]

Answer 1

    for img in img_list:
        input_img=cv2.imread(data_path + '/'+ dataset + '/'+ img )
        input_img=cv2.cvtColor(input_img, cv2.COLOR_BGR2GRAY)
        input_img_resize=cv2.resize(input_img,(512,512))
    --->input_img_resize = np.expand_dims(input_img_resize, axis=-1)
        img_data_list.append(input_img_resize)
        labels_list.append(label)

这将使你的所有数组变成 512x512x1，这应该可以解决问题并最终得到一个形状为 (454, 512, 512, 1) 的数组。您确定要使用灰度图像吗？

另一件事是这段代码

X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, `random_state=2)`
img_data= np.expand_dims(img_data, axis=4)**
print (img_data.shape)

在声明了 x_train 等之后，您将另一个维度应用于您的 img_data。最后您提供了 x_train，它没有扩展，因此会出现错误。如果您从一开始就这样做，并在最后删除扩展，那么您的代码应该可以工作。

编辑 OOM

我建议为 OOM 问题创建一个单独的问题，以便更多人看到它。可能的问题是图像的大小和批量大小。将图像大小减小到 64 x 64，并将批量大小更改为 5。如果这仍然会引发错误，请尝试踢掉这个密集层。

model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))

如果这些减少仍然导致错误，那么我有以下问题:您是否在 GPU/CPU 上运行，以及哪一个？

重复一遍:代码很好，可能只需要一些更改。