基于Keras的卷积自编码器

最新推荐文章于 2023-04-01 11:51:23 发布

cpzxm

最新推荐文章于 2023-04-01 11:51:23 发布

阅读量1.1k

点赞数

分类专栏：人工智能机器学习文章标签：深度学习神经网络机器学习自编码器卷积神经网络

本文链接：https://blog.csdn.net/cpzzy123/article/details/107550288

版权

代码：

import keras
import numpy as np
import matplotlib.pyplot as plt
from keras.datasets import mnist
from keras.models import Sequential, Model
from keras.layers import Input, add
from keras.layers import Layer, Dense, Dropout, Activation, Flatten, Reshape
from keras import regularizers
from keras.optimizers import Adam
from keras.regularizers import l2
from keras.layers.convolutional import Conv2D, MaxPooling2D, UpSampling2D, ZeroPadding2D
from keras.utils import np_utils
import warnings
import tensorflow as tf
from keras import backend as K

config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.compat.v1.Session(config=config)
K.set_session(sess)
warnings.filterwarnings("ignore")


class CNN_VAE():
    def __init__(self):
        self.img_rows = 28
        self.img_cols = 28
        self.channels = 1
        self.img_shape = (self.img_rows, self.img_cols, self.channels)