Question

在CNN的预测方法中，我有一个关于解决维数的问题。在基于图像定义火车和测试数据之前，我提出了一个CNN模型。完成该过程后，我对模型进行了拟合。当我使用模型预测值时，会在此处引发错误。

我该如何解决？

这是我的代码块，如下所示。

我的Keras库

from keras.models import Sequential
from keras.layers import Convolution2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense
from keras.preprocessing.image import ImageDataGenerator

这是我的CNN模型

classifier = Sequential()
classifier.add(Convolution2D(filters = 32, 
                             kernel_size=(3,3), 
                             data_format= "channels_last", 
                             input_shape=(64, 64, 3), 
                             activation="relu")
              )

classifier.add(MaxPooling2D(pool_size = (2,2)))

classifier.add(Convolution2D(32, (3, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (2, 2)))

classifier.add(Convolution2D(32, (3, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (2, 2)))

classifier.add(Flatten())

classifier.add(Dense(units = 128, activation = 'relu'))
classifier.add(Dense(units = 1, activation = 'sigmoid'))

classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])

将CNN设置为图像

train_datagen = ImageDataGenerator(
        rescale=1./255,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1./255)

training_set = train_datagen.flow_from_directory(train_path, 
                                                 target_size=(64, 64), 
                                                 batch_size=32, 
                                                 class_mode='binary')

test_set = test_datagen.flow_from_directory(
        test_path,
        target_size=(64, 64),
        batch_size=32,
        class_mode='binary')

合适的型号

classifier.fit_generator(
        training_set,
        steps_per_epoch=50,
        epochs=30,
        validation_data=test_set,
        validation_steps=200)

预测

S = 64

directory = os.listdir(test_forged_path)
print(directory[3])

print("Path : ", test_forged_path + "/" + directory[3])

imgForged = cv2.imread(test_forged_path + "/" + directory[3])
plt.imshow(imgForged)

pred = classifier.predict(imgForged) # ERROR
print("Probability of Forged Signature : ", "%.2f".format(pred))

错误：

ValueError: Error when checking input: expected conv2d_19_input to have 4 dimensions, but got array with shape (270, 660, 3)

Answer 1

predict方法缺少输入中的批次尺寸。像这样修改您的预测：

import numpy as np <--- import numpy

S = 64

directory = os.listdir(test_forged_path)
print(directory[3])

print("Path : ", test_forged_path + "/" + directory[3])

imgForged = cv2.imread(test_forged_path + "/" + directory[3])
plt.imshow(imgForged)

pred = classifier.predict(np.expand_dims(imgForged,0)) # <-- add new axis to the front, shape will be (1, 270, 660, 3)
print("Probability of Forged Signature : ", "%.2f".format(pred))

预期conv2d_19_input具有4个维度通过Python在CNN中出错

1 个答案: