卷積和降噪自編碼器

1.導入各種包

from pathlib import Path import pandas as pd import numpy as np from numpy.random import choiceimport tensorflow as tf from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, UpSampling2D from tensorflow.keras.models import Model from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint from tensorflow.keras.datasets import fashion_mnistimport matplotlib.pyplot as plt import seaborn as sns

2.數(shù)據(jù)準備

(X_train, y_train), (X_test, y_test) = fashion_mnist.load_data() X_train.shape, X_test.shape class_dict = {0: 'T-shirt/top',1: 'Trouser',2: 'Pullover',3: 'Dress',4: 'Coat',5: 'Sandal',6: 'Shirt',7: 'Sneaker',8: 'Bag',9: 'Ankle boot'} classes = list(class_dict.keys())#規(guī)范數(shù)據(jù) image_size = 28 def data_prep_conv(x, size=image_size):return x.reshape(-1, size, size, 1).astype('float32')/255 X_train_scaled = data_prep_conv(X_train) X_test_scaled = data_prep_conv(X_test) X_train_scaled.shape, X_test_scaled.shape

out：

#訓練與函數(shù)結(jié)合 def train_autoencoder(path, model, x_train=X_train_scaled, x_test=X_test_scaled):callbacks = [EarlyStopping(patience=5, restore_best_weights=True),ModelCheckpoint(filepath=path, save_best_only=True, save_weights_only=True)]model.fit(x=x_train, y=x_train, epochs=100, validation_split=.1, callbacks=callbacks)model.load_weights(path)mse = model.evaluate(x=x_test, y=x_test)return model, mse

3.卷積Autoencoder

定義一個三層的編碼器，它分別使用32、16和8個過濾器的2D卷積。第三層的編碼大小是4 x 4 x 8 = 128，比之前的例子要大。

input_ = Input(shape=(28, 28, 1), name='Input_3D')x = Conv2D(filters=32,kernel_size=(3, 3),activation='relu',padding='same',name='Encoding_Conv_1')(input_) x = MaxPooling2D(pool_size=(2, 2), padding='same', name='Encoding_Max_1')(x) x = Conv2D(filters=16,kernel_size=(3, 3),activation='relu',padding='same',name='Encoding_Conv_2')(x) x = MaxPooling2D(pool_size=(2, 2), padding='same', name='Encoding_Max_2')(x) x = Conv2D(filters=8,kernel_size=(3, 3),activation='relu',padding='same',name='Encoding_Conv_3')(x) encoded_conv = MaxPooling2D(pool_size=(2, 2),padding='same',name='Encoding_Max_3')(x)x = Conv2D(filters=8,kernel_size=(3, 3),activation='relu',padding='same',name='Decoding_Conv_1')(encoded_conv) x = UpSampling2D(size=(2, 2), name='Decoding_Upsample_1')(x) x = Conv2D(filters=16,kernel_size=(3, 3),activation='relu',padding='same',name='Decoding_Conv_2')(x) x = UpSampling2D(size=(2, 2), name='Decoding_Upsample_2')(x) x = Conv2D(filters=32,kernel_size=(3, 3),activation='relu',name='Decoding_Conv_3')(x) x = UpSampling2D(size=(2, 2), name='Decoding_Upsample_3')(x) decoded_conv = Conv2D(filters=1,kernel_size=(3, 3),activation='sigmoid',padding='same',name='Decoding_Conv_4')(x)autoencoder_conv = Model(input_, decoded_conv) autoencoder_conv.compile(optimizer='adam', loss='mse') autoencoder_conv.summary()

這里是定義了一個解碼器，它限制了濾波器的數(shù)量，并使用2D采樣代替最大池化來解決濾波器數(shù)量的減少的問題。out可見三層自動編碼器有12785個參數(shù)，略高于前一種深度自動編碼器容量的5%。
out：

path = (results_path / 'autencoder_conv.32.weights.hdf5').as_posix() autoencoder_deep, mse = train_autoencoder(path, autoencoder_conv, x_train=X_train_scaled, x_test=X_test_scaled)

out結(jié)果略

f'MSE: {mse:.4f} | RMSE {mse**.5:.4f}'

out：

訓練在75個周期后停止，結(jié)果測試RMSE進一步減少9%，這是由于卷積濾波器從圖像數(shù)據(jù)學習的能力更有效并且編碼尺寸更大。

autoencoder_conv.load_weights(path) reconstructed_images = autoencoder_deep.predict(X_test_scaled) reconstructed_images.shapefig, axes = plt.subplots(ncols=n_classes, nrows=2, figsize=(20, 4)) for i in range(n_classes):axes[0, i].imshow(X_test_scaled[i].reshape(image_size, image_size), cmap='gray')axes[0, i].axis('off')axes[1, i].imshow(reconstructed_images[i].reshape(image_size, image_size) , cmap='gray')axes[1, i].axis('off')

out：

4.去噪自編碼器

自編碼器在去噪任務中的應用只影響訓練階段。下面會在標準正態(tài)分布的Fashion MNIST數(shù)據(jù)中添加噪聲，同時保持像素值在[0,1]范圍內(nèi)。

def add_noise(x, noise_factor=.3):return np.clip(x + noise_factor * np.random.normal(size=x.shape), 0, 1)X_train_noisy = add_noise(X_train_scaled) X_test_noisy = add_noise(X_test_scaled) fig, axes = plt.subplots(nrows=2, ncols=5, figsize=(20, 4))axes = axes.flatten() for i, ax in enumerate(axes):ax.imshow(X_test_noisy[i].reshape(28, 28), cmap='gray')ax.axis('off')

out：

x = Conv2D(filters=32, kernel_size=(3, 3), activation='relu', padding='same', name='Encoding_Conv_1')(input_) x = MaxPooling2D(pool_size=(2, 2), padding='same', name='Encoding_Max_1')(x) x = Conv2D(filters=32, kernel_size=(3, 3), activation='relu', padding='same', name='Encoding_Conv_2')(x) encoded_conv = MaxPooling2D(pool_size=(2, 2), padding='same', name='Encoding_Max_3')(x)x = Conv2D(filters=32, kernel_size=(3, 3), activation='relu', padding='same', name='Decoding_Conv_1')(encoded_conv) x = UpSampling2D(size=(2, 2), name='Decoding_Upsample_1')(x) x = Conv2D(filters=32, kernel_size=(3, 3), activation='relu', padding='same', name='Decoding_Conv_2')(x) x = UpSampling2D(size=(2, 2), name='Decoding_Upsample_2')(x) decoded_conv = Conv2D(filters=1, kernel_size=(3, 3), activation='sigmoid', padding='same', name='Decoding_Conv_4')(x)autoencoder_denoise = Model(input_, decoded_conv) autoencoder_denoise.compile(optimizer='adam', loss='mse')path = (results_path / 'autencoder_denoise.32.weights.hdf5').as_posix()callbacks = [EarlyStopping(patience=5,restore_best_weights=True),ModelCheckpoint(filepath=path,save_best_only=True,save_weights_only=True)]#繼續(xù)在有噪聲的輸入上訓練卷積自編碼器，目的是學習如何生成未損壞的原始數(shù)據(jù): autoencoder_denoise.fit(x=X_train_noisy,y=X_train_scaled,epochs=100,batch_size=128,shuffle=True,validation_split=.1,callbacks=callbacks)

out略

autoencoder_denoise.load_weights(path) mse = autoencoder_denoise.evaluate(x=X_test_noisy, y=X_test_scaled) f'MSE: {mse:.4f} | RMSE {mse**.5:.4f}'

out：

5.可視化

下圖從上到下分別是原始圖像和去噪后的圖像。它說明了自編碼器成功地從噪聲圖像中產(chǎn)生壓縮編碼，這些壓縮編碼與從原始圖像中產(chǎn)生的非常相似。

總結(jié)

以上是生活随笔為你收集整理的MLAT-Autoencoders---下篇-关键代码及结果展示（2）的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。