自动编码器输入形状：预期 input_1 的形状为 (256, 256, 3) 但得到的数组形状为 (256, 256, 4)

Question

我正在尝试构建一个自动编码器，但我收到以下错误，我不知道为什么。

ValueError：检查输入时出错：预期 input_1 的形状为 (256, 256, 3) 但得到的数组的形状为 (256, 256, 4)

如果我打印图像形状，我会得到 (256, 256, 3) 但我仍然会收到关于形状的错误。

任何帮助都会很棒。

Ubuntu 18.04 | Python 3.7.6 | Tensorflow 2.1

---

from tensorflow.keras.layers import Input, Dense, Conv2D, MaxPooling2D, Dropout, Conv2DTranspose, UpSampling2D, add
from tensorflow.keras.models import Model
from tensorflow.keras import regularizers

import os
import re
from scipy import ndimage, misc
from skimage.transform import resize, rescale
from matplotlib import pyplot
import numpy as np

#Functions

def train_batches(just_load_dataset=False):

    batches = 256 # Number of images to have at the same time in a batch

    batch = 0 # Number if images in the current batch (grows over time and then resets for each batch)
    batch_nb = 0 # Batch current index

    max_batches = -1 # If you want to train only on a limited number of images to finish the training even faster.

    ep = 4 # Number of epochs

    images = []
    x_train_n = []
    x_train_down = []

    x_train_n2 = [] # Resulting high res dataset
    x_train_down2 = [] # Resulting low res dataset

    for root, dirnames, filenames in os.walk(input_dir):
        for filename in filenames:
            if re.search("\.(jpg|jpeg|JPEG|png|bmp|tiff)$", filename):
                if batch_nb == max_batches: # If we limit the number of batches, just return earlier
                    return x_train_n2, x_train_down2
                filepath = os.path.join(root, filename)
                image = pyplot.imread(filepath)

                if len(image.shape) > 2:

                    image_resized = resize(image, (256, 256))
                    x_train_n.append(image_resized)
                    x_train_down.append(rescale(rescale(image_resized, 0.5), 2.0))
                    batch += 1
                    if batch == batches:
                        batch_nb += 1

                        x_train_n2 = np.array(x_train_n)
                        x_train_down2 = np.array(x_train_down)

                        if just_load_dataset:
                            return x_train_n2, x_train_down2

                        print('Training batch', batch_nb, '(', batches, ')')

                        autoencoder.fit(x_train_down2, x_train_n2, epochs=ep, batch_size=10, shuffle=True, validation_split=0.15)

                        x_train_n = []
                        x_train_down = []

                        batch = 0

    return x_train_n2, x_train_down2

#Script

input_dir="/mnt/vanguard/datasets/ffhq-dataset/thumbnails256x256"

n = 256
chan = 3
input_img = Input(shape=(n, n, chan))


# Encoder
l1 = Conv2D(64, (3, 3), padding='same', activation='relu', activity_regularizer=regularizers.l1(10e-10))(input_img)
l2 = Conv2D(64, (3, 3), padding='same', activation='relu', activity_regularizer=regularizers.l1(10e-10))(l1)
l3 = MaxPooling2D(padding='same')(l2)
l3 = Dropout(0.3)(l3)
l4 = Conv2D(128, (3, 3),  padding='same', activation='relu', activity_regularizer=regularizers.l1(10e-10))(l3)
l5 = Conv2D(128, (3, 3), padding='same', activation='relu', activity_regularizer=regularizers.l1(10e-10))(l4)
l6 = MaxPooling2D(padding='same')(l5)
l7 = Conv2D(256, (3, 3), padding='same', activation='relu', activity_regularizer=regularizers.l1(10e-10))(l6)

# Decoder
l8 = UpSampling2D()(l7)
l9 = Conv2D(128, (3, 3), padding='same', activation='relu', activity_regularizer=regularizers.l1(10e-10))(l8)
l10 = Conv2D(128, (3, 3), padding='same', activation='relu', activity_regularizer=regularizers.l1(10e-10))(l9)
l11 = add([l5, l10])
l12 = UpSampling2D()(l11)
l13 = Conv2D(64, (3, 3), padding='same', activation='relu', activity_regularizer=regularizers.l1(10e-10))(l12)
l14 = Conv2D(64, (3, 3), padding='same', activation='relu', activity_regularizer=regularizers.l1(10e-10))(l13)
l15 = add([l14, l2])

#chan = 3, for RGB
decoded = Conv2D(chan, (3, 3), padding='same', activation='relu', activity_regularizer=regularizers.l1(10e-10))(l15)

# Create neural network
autoencoder = Model(input_img, decoded)
autoencoder_hfenn = Model(input_img, decoded)
autoencoder.summary()

autoencoder.compile(optimizer='adadelta', loss='mean_squared_error')

x_train_n = []
x_train_down = []
x_train_n, x_train_down = train_batches()

Answer 1

重新缩放x_train_down.append(rescale(rescale(image_resized, 0.5), 2.0))导致问题。 OpenCV 可用于降低图像质量：

small = cv2.resize(image_resized, (0,0), fx=0.5, fy=0.5)
large = cv2.resize(small, (0,0), fx=2.0, fy=2.0)

另请注意，这是 GPU 密集型计算。 要么减小图像尺寸，要么尝试使用更多 memory (K80) 的 GPU。