如何在keras tensorflow中将图像作为输入并获取另一个图像作为输出

Posted 2023-02-16

【中文标题】如何在keras tensorflow中将图像作为输入并获取另一个图像作为输出

【英文标题】：How to give an image as input and get another image as output in keras tensorflow

【发布时间】：2021-12-23 23:44:58

【问题描述】：

我有 zigsaw 拼图图像和对应的对。我想将图像作为模型的输入并找到对应的对。我制作了以下模型，在训练。但是当我通过测试图像数组时，它会预测一个具有所有 nan 值的数组。我应该改变我的损失函数吗？请查看图片下方的代码

in_shape=(32,256,256,3)
model1=models.Sequential(
[
    resize_and_rescale,
    layers.Conv2D(32,(3,3),activation="relu",input_shape=in_shape,padding='same'),
    layers.Dropout(0.1),
    layers.Conv2D(32,(3,3),activation="relu",input_shape=in_shape,padding='same'),
    layers.MaxPooling2D((2,2)),
    

    layers.Conv2D(64,  kernel_size = (3,3), activation='relu',padding='same'),
    layers.Dropout(0.1),
    layers.Conv2D(64,(3,3),activation="relu",input_shape=in_shape,padding='same'),
    layers.MaxPooling2D((2, 2)),
 

    layers.Conv2D(128,  kernel_size = (3,3), activation='relu',padding='same'),
    layers.Dropout(0.1),
    layers.Conv2D(128,(3,3),activation="relu",input_shape=in_shape,padding='same'),
    layers.MaxPooling2D((2, 2)),
    layers.Conv2D(256,  kernel_size = (3,3), activation='relu',padding='same'),
    layers.MaxPooling2D((2, 2)),
 
    layers.Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same'),
    layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'),
    layers.Dropout(0.2),
    layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'),

    layers.Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same'),
    layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'),
    layers.Dropout(0.2),
    layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'),
 
    layers.Conv2DTranspose(32, (2, 2), strides=(2, 2), padding='same'),
    layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'),
    layers.Dropout(0.2),
    layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'),

    layers.Conv2DTranspose(16, (2, 2), strides=(2, 2), padding='same'),
    layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'),
    layers.Dropout(0.2),
    layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'),


    layers.Conv2D(3, (1, 1), activation='sigmoid')
     
]
)
model1.build(input_shape=in_shape)

model1.compile(
    optimizer='adam',
    loss=tf.keras.losses.CategoricalCrossentropy(from_logits=False),
    metrics=['accuracy']
)

【问题讨论】：

回答有用吗？

【参考方案1】：

您可以在您的情况下使用tf.keras.losses.MeanSquaredError()，并且在提供您的input_shape 时，您不要指定batch_size。您应该只提供宽度、高度和通道：(height, width, channels --> (256, 256, 3)。

import tensorflow as tf

model1=tf.keras.Sequential(
[
    tf.keras.layers.Conv2D(32,(3,3),activation="relu",input_shape=(256, 256, 3),padding='same'),
    tf.keras.layers.Dropout(0.1),
    tf.keras.layers.Conv2D(32,(3,3),activation="relu",padding='same'),
    tf.keras.layers.MaxPooling2D((2,2)),
    

    tf.keras.layers.Conv2D(64,  kernel_size = (3,3), activation='relu',padding='same'),
    tf.keras.layers.Dropout(0.1),
    tf.keras.layers.Conv2D(64,(3,3),activation="relu",padding='same'),
    tf.keras.layers.MaxPooling2D((2, 2)),
 

    tf.keras.layers.Conv2D(128,  kernel_size = (3,3), activation='relu',padding='same'),
    tf.keras.layers.Dropout(0.1),
    tf.keras.layers.Conv2D(128,(3,3),activation="relu",padding='same'),
    tf.keras.layers.MaxPooling2D((2, 2)),
    tf.keras.layers.Conv2D(256,  kernel_size = (3,3), activation='relu',padding='same'),
    tf.keras.layers.MaxPooling2D((2, 2)),
 
    tf.keras.layers.Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same'),
    tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'),
    tf.keras.layers.Dropout(0.2),
    tf.keras.layers.Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'),

    tf.keras.layers.Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same'),
    tf.keras.layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'),
    tf.keras.layers.Dropout(0.2),
    tf.keras.layers.Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'),
 
    tf.keras.layers.Conv2DTranspose(32, (2, 2), strides=(2, 2), padding='same'),
    tf.keras.layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'),
    tf.keras.layers.Dropout(0.2),
    tf.keras.layers.Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'),

    tf.keras.layers.Conv2DTranspose(16, (2, 2), strides=(2, 2), padding='same'),
    tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'),
    tf.keras.layers.Dropout(0.2),
    tf.keras.layers.Conv2D(16, (3, 3), activation='relu', kernel_initializer='he_normal', padding='same'),

    tf.keras.layers.Conv2D(3, (1, 1), activation='sigmoid')])

model1.compile(
    optimizer='adam',
    loss=tf.keras.losses.MeanSquaredError()
)
model1.fit(tf.random.normal((32, 256, 256, 3)), tf.random.normal((32, 256, 256, 3)))