设计简单的自动编码器时尺寸值误差

Question

嗨，我正在使用 Keras 库在 Python 3.5 中尝试一个简单的自动编码器。我面临的问题是 - ValueError：检查输入时出错：预期input_40有 2 个维度，但得到形状为 (32、256、256、3( 的数组。我的数据集非常小(60 张尺寸为 - 256*256 的 RGB 图像和一个相同类型的图像进行验证(。我对Python有点陌生。请帮忙。

import matplotlib.pyplot as plt
from keras.layers import Input, Dense
from keras.models import Model
#Declaring the model
encoding_dim = 32
input_img = Input(shape=(65536,))
encoded = Dense(encoding_dim, activation='relu')(input_img)
decoded = Dense(65536, activation='sigmoid')(encoded)
autoencoder = Model(input_img, decoded)
encoder = Model(input_img, encoded)
encoded_input = Input(shape=(encoding_dim,))
decoder_layer = autoencoder.layers[-1]
decoder = Model(encoded_input, decoder_layer(encoded_input))
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')

#Constructing a data generator iterator
from keras.preprocessing.image import ImageDataGenerator
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('C:\Users\vlsi\Desktop\train',
batch_size = 32,
class_mode = 'binary')
test_set =     
test_datagen.flow_from_directory('C:\Users\vlsi\Desktop\validation',
batch_size = 32,
class_mode = 'binary')

#fitting data
autoencoder.fit_generator(training_set,
steps_per_epoch = 80,
epochs = 25,
validation_data = test_set,
validation_steps = 20)
import numpy as np from keras.preprocessing import image
test_image =            
image.load_img('C:\Users\vlsi\Desktop\validation\validate\apple1.jpg')
test_image = image.img_to_array(test_image)
test_image = np.expand_dims(test_image, axis = 0)
#Displaying output
encoded_imgs = encoder.predict(test_image)
decoded_imgs = decoder.predict(encoded_imgs)
plt.imshow(decoded_imgs)

Answer 1

问题就在这里：

input_img = Input(shape=(65536,))

您告诉 Keras 网络的输入将具有 65K 维，这意味着形状向量(样本，65536(，但您的实际输入具有形状(样本，256,256,3(。任何简单的解决方案都是使用真实的输入形状，并让网络执行必要的重塑：

input_img = Input(shape=((256, 256, 3))
flattened = Flatten()(input_img)
encoded = Dense(encoding_dim, activation='relu')(flattened)
decoded = Dense(256 * 256 * 3, activation='sigmoid')(encoded)
decoded = Reshape((256, 256, 3))(decoded)
autoencoder = Model(input_img, decoded)
encoder = Model(input_img, encoded)
encoded_input = Input(shape=(encoding_dim,))
decoder_layer = autoencoder.layers[-1]
decoder = Model(encoded_input, decoder_layer(encoded_input))

请注意，我首先添加了一个拼合和重新塑造图层来拼合图像，然后将拼合后的图像恢复为形状 (256， 256， 3(。