Keras多种输入，输出，损失模型 [英] Keras multiple input, output, loss model

问题描述

我正在研究超分辨率GAN，并且对我在Github上找到的代码有一些疑问.特别是，我在模型中有多个输入，多个输出.另外，我有两个不同的损失函数.

I am working on super-resolution GAN and having some doubts about the code I found on Github. In particular, I have multiple inputs, multiple outputs in the model. Also, I have two different loss functions.

在下面的代码中，是否将ms损失应用于img_hr和fake_features?

In the following code will the mse loss be applied to img_hr and fake_features?

# Build and compile the discriminator
        self.discriminator = self.build_discriminator()
        self.discriminator.compile(loss='mse',
            optimizer=optimizer,
            metrics=['accuracy'])

        # Build the generator
        self.generator = self.build_generator()

        # High res. and low res. images
        img_hr = Input(shape=self.hr_shape)
        img_lr = Input(shape=self.lr_shape)

        # Generate high res. version from low res.
        fake_hr = self.generator(img_lr)

        # Extract image features of the generated img
        fake_features = self.vgg(fake_hr)

        # For the combined model we will only train the generator
        self.discriminator.trainable = False

# Discriminator determines validity of generated high res. images
        validity = self.discriminator(fake_hr)

        self.combined = Model([img_lr, img_hr], [validity, fake_features])
        self.combined.compile(loss=['binary_crossentropy', 'mse'],
                              loss_weights=[1e-3, 1],
                              optimizer=optimizer)

推荐答案

在以下代码中，mse损失将应用于img_hr和fake_features?

In the following code will the mse loss be applied to img_hr and fake_features?

从文档中， https://keras.io/models/model/#compile

"如果模型具有多个输出，则可以通过传递字典或损失列表来对每个输出使用不同的损失."

在这种情况下，mse损失将应用于fake_features，并将相应的y_true作为 self.combined.fit()的一部分传递.

In this case, the mse loss will be applied to fake_features and the corresponding y_true passed as part of self.combined.fit().

这篇关于Keras多种输入，输出，损失模型的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！