使用自定义数据集进行人脸识别而不是 MNIST

Question

我想使用包含不同人脸图像的自定义数据集。我计划使用 CNN 和堆叠自动编码器对我的图像进行分类。

我应该改变 (x_train, _), (x_test, _) = mnist.load_data() 吗？

或更改 input_img ，我认为问题出在输入数据上，但我不知道应该在哪里修改。

我迷路了，我需要帮助。

from keras.layers import Input, Dense, Conv2D, MaxPooling2D, UpSampling2D

from keras.models import Model

from keras import backend as K

input_img = Input(shape=(28, 28, 1))  # adapt this if using`channels_first` image data format

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)

# at this point the representation is (4, 4, 8) i.e. 128-dimensional

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')

from keras.datasets import mnist

import numpy as np

(x_train, _), (x_test, _) = mnist.load_data()

x_train = x_train.astype('float32') / 255.

x_test = x_test.astype('float32') / 255.

x_train = np.reshape(x_train, (len(x_train), 28, 28, 1))  # adapt this if 

using `channels_first` image data format

x_test = np.reshape(x_test, (len(x_test), 28, 28, 1))  # adapt this if 

using `channels_first` image data format

from keras.callbacks import TensorBoard

autoencoder.fit(x_train, x_train,

               epochs=50,

               batch_size=128,

               shuffle=True,

               validation_data=(x_test, x_test),

               callbacks=[TensorBoard(log_dir='/tmp/autoencoder')])

decoded_imgs = autoencoder.predict(x_test)

Answer 1

您需要使用数据加载器更改 (x_train, _), (x_test, _) = mnist.load_data() 。您可以使用 kerasImageDataGenerator类来完成此操作或构建您自己的. 如果您的图像尺寸远大于28 x 28您可能需要更改模型架构，因为直接28 x 28将它们重塑为不会产生好的结果。

Answer 2

您需要加载数据集并将其拆分为两个子集：x_train和x_test.您的数据以哪种格式存储？