我正在向VAE添加自定义损失，如下所示:https://www.linkedin.com/pulse/supervised-variational-autoencoder-code-included-ibrahim-sobh-phd/
它没有定义损失函数，而是使用dense网络并将其输出作为损失(如果我理解正确的话)。
# New: add a classifier
clf_latent_inputs = Input(shape=(latent_dim,), name='z_sampling_clf')
clf_outputs = Dense(10, activation='softmax', name='class_output')(clf_latent_inputs)
clf_supervised = Model(clf_latent_inputs, clf_outputs, name='clf')
clf_supervised.summary()
# instantiate VAE model
# New: Add another output
outputs = [decoder(encoder(inputs)[2]), clf_supervised(encoder(inputs)[2])]
vae = Model(inputs, outputs, name='vae_mlp')
vae.summary()
reconstruction_loss = binary_crossentropy(inputs, outputs[0])
reconstruction_loss *= original_dim
kl_loss = 1 + z_log_var - K.square(z_mean) - K.exp(z_log_var)
kl_loss = K.sum(kl_loss, axis=-1)
kl_loss *= -0.5
vae_loss = K.mean((reconstruction_loss + kl_loss) /100.0)
vae.add_loss(vae_loss)
# New: add the clf loss
vae.compile(optimizer='adam', loss={'clf': 'categorical_crossentropy'}) ===> this line <===
vae.summary()
# reconstruction_loss = binary_crossentropy(inputs, outputs)
svae_history = vae.fit(x_train, {'clf': y_train},
epochs=epochs,
batch_size=batch_size)
我被困在编译步骤(注释为===>这一行<===)，我遇到了一个类型错误:
TypeError: Expected float32, got <functionBaseProtVAE。>init．.Vae_loss at 0x7ff53051dd08;类型的"函数"代替。
如果你有什么建议，我需要你的帮助。
在Tensorflow中有几种实现VAE的方法。我提出了一个替代实现，可以在Tensorflow指南页面的custom_layers_and_models中找到:
让我们把所有这些东西放在一个端到端的例子中:我们将实现一个变分自动编码器(VAE)。我们将在MNIST数字上训练它。
它使用自定义模型类和梯度磁带。这样，就很容易将分类器加入到VAE模型中，并在优化过程中将分类交叉熵添加到总损失中。
你只需要修改:
class VariationalAutoEncoder(Model):
"""Combines the encoder and decoder into an end-to-end model for training."""
def __init__(
self,
original_dim,
intermediate_dim=64,
latent_dim=32,
name="autoencoder",
**kwargs
):
super(VariationalAutoEncoder, self).__init__(name=name, **kwargs)
self.original_dim = original_dim
self.encoder = Encoder(latent_dim=latent_dim, intermediate_dim=intermediate_dim)
self.decoder = Decoder(original_dim, intermediate_dim=intermediate_dim)
self.clf_supervised = Dense(10, activation='softmax', name='class_output')
def call(self, inputs):
z_mean, z_log_var, z = self.encoder(inputs)
reconstructed = self.decoder(z)
# Add KL divergence regularization loss.
kl_loss = -0.5 * tf.reduce_mean(
z_log_var - tf.square(z_mean) - tf.exp(z_log_var) + 1
)
self.add_loss(kl_loss)
# classifier
y_pred = self.clf_supervised(z)
return reconstructed, y_pred
通过添加self.clf_supervised = Dense(10, activation='softmax', name='class_output')和y_pred = self.clf_supervised(z)行
优化是这样完成的:
vae = VariationalAutoEncoder(original_dim, intermediate_dim, latent_dim)
optimizer = tf.keras.optimizers.Adam(learning_rate=1e-3)
mse_loss_fn = tf.keras.losses.MeanSquaredError()
loss_metric = tf.keras.metrics.Mean()
epochs = 2
train_dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))
train_dataset = train_dataset.shuffle(buffer_size=500).batch(4)
# Iterate over epochs.
for epoch in range(epochs):
print("Start of epoch %d" % (epoch,))
# Iterate over the batches of the dataset.
for step, (x_batch_train, y_batch_train) in enumerate(train_dataset):
with tf.GradientTape() as tape:
reconstructed, y_pred = vae(x_batch_train)
clf_loss = tf.keras.losses.SparseCategoricalCrossentropy()(y_batch_train, y_pred)
# Compute reconstruction loss
loss = mse_loss_fn(x_batch_train, reconstructed)
loss += sum(vae.losses) # Add KLD regularization loss
loss += clf_loss
grads = tape.gradient(loss, vae.trainable_weights)
optimizer.apply_gradients(zip(grads, vae.trainable_weights))
loss_metric(loss)
if step % 100 == 0:
print("step %d: mean loss = %.4f" % (step, loss_metric.result()))
其余的代码在上面的链接中。主要的变化是使用tf.GradientTape()完成的优化。它比fit方法稍微复杂一点，但它仍然非常简单和非常强大。