我试图通过创建三个类来构建TensorFlow 2.0中的自动编码器：编码器，解码器和自动编码器。 由于我不想手动设置输入形状，因此我尝试从编码器的input_shape推断解码器的输出形状。
import os
import shutil
import numpy as np
import tensorflow as tf
from tensorflow.keras import Model
from tensorflow.keras.layers import Dense, Layer
def mse(model, original):
return tf.reduce_mean(tf.square(tf.subtract(model(original), original)))
def train_autoencoder(loss, model, opt, original):
with tf.GradientTape() as tape:
gradients = tape.gradient(
loss(model, original), model.trainable_variables)
gradient_variables = zip(gradients, model.trainable_variables)
opt.apply_gradients(gradient_variables)
def log_results(model, X, max_outputs, epoch, prefix):
loss_values = mse(model, X)
sample_img = X[sample(range(X.shape[0]), max_outputs), :]
original = tf.reshape(sample_img, (max_outputs, 28, 28, 1))
encoded = tf.reshape(
model.encode(sample_img), (sample_img.shape[0], 8, 8, 1))
decoded = tf.reshape(
model(tf.constant(sample_img)), (sample_img.shape[0], 28, 28, 1))
tf.summary.scalar("{}_loss".format(prefix), loss_values, step=epoch + 1)
tf.summary.image(
"{}_original".format(prefix),
original,
max_outputs=max_outputs,
step=epoch + 1)
tf.summary.image(
"{}_encoded".format(prefix),
encoded,
max_outputs=max_outputs,
step=epoch + 1)
tf.summary.image(
"{}_decoded".format(prefix),
decoded,
max_outputs=max_outputs,
step=epoch + 1)
return loss_values
def preprocess_mnist(batch_size):
(X_train, y_train), (X_test, y_test) = tf.keras.datasets.mnist.load_data()
X_train = X_train / np.max(X_train)
X_train = X_train.reshape(X_train.shape[0],
X_train.shape[1] * X_train.shape[2]).astype(
np.float32)
train_dataset = tf.data.Dataset.from_tensor_slices(X_train).batch(
batch_size)
y_train = y_train.astype(np.int32)
train_labels = tf.data.Dataset.from_tensor_slices(y_train).batch(
batch_size)
X_test = X_test / np.max(X_test)
X_test = X_test.reshape(
X_test.shape[0], X_test.shape[1] * X_test.shape[2]).astype(np.float32)
y_test = y_test.astype(np.int32)
return X_train, X_test, train_dataset, y_train, y_test, train_labels
class Encoder(Layer):
def __init__(self, units):
super(Encoder, self).__init__()
self.units = units
def build(self, input_shape):
self.output_layer = Dense(units=self.units, activation=tf.nn.relu)
@tf.function
def call(self, X):
return self.output_layer(X)
class Decoder(Layer):
def __init__(self, encoder):
super(Decoder, self).__init__()
self.encoder = encoder
def build(self, input_shape):
self.output_layer = Dense(units=self.encoder.input_shape)
@tf.function
def call(self, X):
return self.output_layer(X)
class AutoEncoder(Model):
def __init__(self, units):
super(AutoEncoder, self).__init__()
self.units = units
def build(self, input_shape):
self.encoder = Encoder(units=self.units)
self.encoder.build(input_shape)
self.decoder = Decoder(encoder=self.encoder)
@tf.function
def call(self, X):
Z = self.encoder(X)
return self.decoder(Z)
@tf.function
def encode(self, X):
return self.encoder(X)
@tf.function
def decode(self, Z):
return self.decode(Z)
def test_autoencoder(batch_size,
learning_rate,
epochs,
max_outputs=4,
seed=None):
tf.random.set_seed(seed)
X_train, X_test, train_dataset, _, _, _ = preprocess_mnist(
batch_size=batch_size)
autoencoder = AutoEncoder(units=64)
opt = tf.optimizers.Adam(learning_rate=learning_rate)
log_path = 'logs/autoencoder'
if os.path.exists(log_path):
shutil.rmtree(log_path)
writer = tf.summary.create_file_writer(log_path)
with writer.as_default():
with tf.summary.record_if(True):
for epoch in range(epochs):
for step, batch in enumerate(train_dataset):
train_autoencoder(mse, autoencoder, opt, batch)
# logs (train)
train_loss = log_results(
model=autoencoder,
X=X_train,
max_outputs=max_outputs,
epoch=epoch,
prefix='train')
# logs (test)
test_loss = log_results(
model=autoencoder,
X=X_test,
max_outputs=max_outputs,
epoch=epoch,
prefix='test')
writer.flush()
template = 'Epoch {}, Train loss: {:.5f}, Test loss: {:.5f}'
print(
template.format(epoch + 1, train_loss.numpy(),
test_loss.numpy()))
if not os.path.exists('saved_models'):
os.makedirs('saved_models')
np.savez_compressed('saved_models/encoder.npz',
*autoencoder.encoder.get_weights())
if __name__ == '__main__':
test_autoencoder(batch_size=128, learning_rate=1e-3, epochs=20, seed=42)
由于编码器的输入形状用于解码器的构建函数，因此我希望在训练自动编码器时首先构建编码器，然后构建解码器，但事实似乎并非如此。我还尝试通过在解码器的构建函数开始时调用self.encoder.build()来在解码器的构建函数中构建编码器，但这没有任何区别。我做错了什么？
我收到的错误：
AttributeError: The layer has never been called and thus has no defined input shape.
你快到了，只是事情有点过于复杂。您收到此错误Decoder因为图层依赖于尚未构建的Encoder图层(因为对build的调用不成功)，并且未设置input_shape属性。
解决方案是从对象传递正确的输出形状AutoEncoder如下所示：
class Decoder(Layer):
def __init__(self, units):
super(Decoder, self).__init__()
self.units = units
def build(self, _):
self.output_layer = Dense(units=self.units)
def call(self, X):
return self.output_layer(X)
class AutoEncoder(Model):
def __init__(self, units):
super(AutoEncoder, self).__init__()
self.units = units
def build(self, input_shape):
self.encoder = Encoder(units=self.units)
self.decoder = Decoder(units=input_shape[-1])
请注意，我已经删除了@tf,function装饰器，因为您不太可能获得任何效率提升(keras已经为您创建了幕后的静态图形)。
此外，正如人们所看到的，您的构建不依赖于input_shape信息，因此所有创建都可以安全地移动到构造函数中，如下所示：
class Encoder(Layer):
def __init__(self, units):
super(Encoder, self).__init__()
self.output_layer = Dense(units=units, activation=tf.nn.relu)
def call(self, X):
return self.output_layer(X)
class Decoder(Layer):
def __init__(self, units):
super(Decoder, self).__init__()
self.output_layer = Dense(units=units)
def call(self, X):
return self.output_layer(X)
class AutoEncoder(Model):
def __init__(self, units):
super(AutoEncoder, self).__init__()
self.units = units
def build(self, input_shape):
self.encoder = Encoder(units=self.units)
self.decoder = Decoder(units=input_shape[-1])
def call(self, X):
Z = self.encoder(X)
return self.decoder(Z)
def encode(self, X):
return self.encoder(X)
def decode(self, Z):
return self.decode(Z)
上面引出了一个问题，是否真的需要单独的Decoder层和Encoder层。IMO 这些应该被排除在外，这给我们留下的只有这个简短且可读的片段：
class AutoEncoder(Model):
def __init__(self, units):
super(AutoEncoder, self).__init__()
self.units = units
def build(self, input_shape):
self.encoder = Dense(units=self.units, activation=tf.nn.relu)
self.decoder = Dense(units=input_shape[-1])
def call(self, X):
Z = self.encoder(X)
return self.decoder(Z)
def encode(self, X):
return self.encoder(X)
def decode(self, Z):
return self.decode(Z)
顺便说一句。你在sample上有一个错误，但毫无疑问，这是一个你可以自己处理的未成年人。