自动编码器中conv2d层的形状大小不匹配

Question

我正在构建(重用(卷积自动编码器，但我对最后一个conv2D层有问题，因为它期望(180116,1(的形状，但接收(184120,1([这是我的图像的形状]。

我做了一些研究，但我没能解决这个问题，有人能解决吗？

# process the images into data
import glob
import pandas as pd
import numpy as np
from encoder_utils import prep_data
import sys
from sklearn.model_selection import train_test_split
np.set_printoptions(threshold=np.nan)
# create a list of XML files within the raw data folder
image_list = glob.glob("Images/dpi60/*.jpeg")
# set size of tensor_scope
tensor_scope = 500
# Process the images into numpy arrays and return a tensor
T = prep_data(image_list, all_items = False, less_items = tensor_scope)
# split into training and testing sets
labels = image_list[0:tensor_scope]
data_train, data_test, labels_train, labels_test = train_test_split(T, labels, test_size=0.20, random_state=42)
# convert to 0-1 floats (reconversion by * 255)
data_train = data_train.astype('float32') / 255.
data_test = data_test.astype('float32') / 255.
# reshape from channels first to channels last
data_train = np.rollaxis(data_train, 0, 3)
data_test = np.rollaxis(data_test, 0, 3)
from keras.layers import Input, Dense, Conv2D, MaxPooling2D, UpSampling2D
from keras.models import Model
from keras import backend as K
input_img = Input(shape=(184, 120, 1))  
x = Conv2D(16, (3, 3), activation='relu', padding='same')(input_img)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
encoded = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(16, (3, 3), activation='relu')(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)

autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')
data_train_dimensions =  data_train.shape
data_test_dimensions =  data_test.shape
data_train = np.reshape(data_train, (data_train_dimensions[2], 184, 120, 1))  # adapt this if using `channels_first` image data format
data_test = np.reshape(data_test, (data_test_dimensions[2], 184, 120, 1))
from keras.callbacks import TensorBoard
autoencoder.fit(data_train, data_test,
epochs=50,
batch_size=128,
shuffle=True,
validation_data=(data_train, data_test),
callbacks=[TensorBoard(log_dir='/tmp/autoencoder')])

Answer 1

您忘记了在的下一行使用padding="same">

x = Conv2D(16, (3, 3), activation='relu')(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)

add padding="same">

x = Conv2D(16, (3, 3), activation='relu', padding="same")(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)