我正在尝试使用TensorFlow创建一个变分自编码器。我按照Keras官网的步骤进行了操作(https://keras.io/guides/making_new_layers_and_models_via_subclassing/)，但我进行了一些小修改。
annealing_weight = tf.keras.backend.variable(0.01)
test = VariationalAutoEncoder(annealing_weight,
[8, 8, 128],
input_shape=(None, 256, 256, 1))
test.compile('adam', loss=None)
test.summary()
test.train_on_batch(np.random.randn(32, 256, 256, 1),None)
我可以编译网络并获得摘要，一切似乎正常。但是，当我尝试对批次进行训练以查看网络是否正常工作时，出现以下错误消息。问题似乎在于误差函数。
希望有人能帮助我。谢谢！
WARNING:tensorflow:AutoGraph could not transform <bound method ConvolutionalBlock.call of <__main__.ConvolutionalBlock object at 0x000000001D5DC408>> and will run it as-is.
Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.
Cause: Unable to locate the source code of <bound method ConvolutionalBlock.call of <__main__.ConvolutionalBlock object at 0x000000001D5DC408>>. Note that functions defined in certain environments, like the interactive Python shell do not expose their source code. If that is the case, you should to define them in a .py source file. If you are certain the code is graph-compatible, wrap the call using @tf.autograph.do_not_convert. Original error: could not get source code
WARNING:tensorflow:Output output_1 missing from loss dictionary. We assume this was done on purpose. The fit and evaluate APIs will not be expecting any data to be passed to output_1.
Traceback (most recent call last):
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\framework\ops.py", line 1619, in _create_c_op
c_op = c_api.TF_FinishOperation(op_desc)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Shapes must be equal rank, but are 1 and 0
From merging shape 1 with other shapes. for 'loss_1/AddN' (op: 'AddN') with input shapes: [?], [?], [], [], [], [], [], [], [], [], [], [], [], [].
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "<input>", line 10, in <module>
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 1078, in train_on_batch
standalone=True)
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py", line 416, in train_on_batch
extract_tensors_from_dataset=True)
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 2360, in _standardize_user_data
self._compile_from_inputs(all_inputs, y_input, x, y)
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 2618, in _compile_from_inputs
experimental_run_tf_function=self._experimental_run_tf_function)
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\training\tracking\base.py", line 457, in _method_wrapper
result = method(self, *args, **kwargs)
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 446, in compile
self._compile_weights_loss_and_weighted_metrics()
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\training\tracking\base.py", line 457, in _method_wrapper
result = method(self, *args, **kwargs)
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 1592, in _compile_weights_loss_and_weighted_metrics
self.total_loss = self._prepare_total_loss(masks)
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 1701, in _prepare_total_loss
math_ops.add_n(custom_losses))
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\util\dispatch.py", line 180, in wrapper
return target(*args, **kwargs)
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\ops\math_ops.py", line 3053, in add_n
return gen_math_ops.add_n(inputs, name=name)
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\ops\gen_math_ops.py", line 420, in add_n
"AddN", inputs=inputs, name=name)
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\framework\op_def_library.py", line 742, in _apply_op_helper
attrs=attr_protos, op_def=op_def)
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\framework\func_graph.py", line 595, in _create_op_internal
compute_device)
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\framework\ops.py", line 3322, in _create_op_internal
op_def=op_def)
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\framework\ops.py", line 1786, in __init__
control_input_ops)
File "C:\Users\user\.conda\envs\Thesis\lib\site-packages\tensorflow_core\python\framework\ops.py", line 1622, in _create_c_op
raise ValueError(str(e))
ValueError: Shapes must be equal rank, but are 1 and 0
From merging shape 1 with other shapes. for 'loss_1/AddN' (op: 'AddN') with input shapes: [?], [?], [], [], [], [], [], [], [], [], [], [], [], [].
下面展示了代码。
import numpy as np
import tensorflow as tf
from tensorflow.keras import layers as tfl
class ConvolutionalBlock(tfl.Layer):
def __init__(self, filters, name, deconv=False, **kwargs):
self.conv_layer = tfl.Conv2DTranspose if deconv else tfl.Conv2D
self.conv_layer = self.conv_layer(filters,
kernel_size=3,
padding='same',
kernel_initializer='he_normal',
kernel_regularizer=tf.keras.regularizers.l2(0.0001),
strides=2,
name='conv')
self.batch_norm = tfl.BatchNormalization(name='de_ennorm')
self.relu = tfl.ReLU(name='en_relu')# + str(index))
super(ConvolutionalBlock, self).__init__(name=name, **kwargs)
def call(self, inputs, **kwargs):
outputs = self.conv_layer(inputs)
outputs = self.batch_norm(outputs)
outputs = self.relu(outputs)
return outputs
class Sampling(tfl.Layer):
def __init__(self, **kwargs):
super(Sampling, self).__init__(name='reparameterization_trick', **kwargs)
def call(self, inputs, training=None, mask=None, **kwargs):
x_mean, x_variance = inputs
return x_mean + tf.keras.backend.exp(0.5 * x_variance) * \
tf.keras.backend.random_normal(shape=(32, 128), mean=0., stddev=1.0)
class Encoder(tfl.Layer):
def __init__(self, **kwargs):
super(Encoder, self).__init__(name='Encoder', **kwargs)
self.convs = [
ConvolutionalBlock(8, 'conv1'),
ConvolutionalBlock(16, 'conv2'),
ConvolutionalBlock(32, 'conv3'),
ConvolutionalBlock(64, 'conv4'),
ConvolutionalBlock(128, 'conv5')
]
self.features = tfl.GlobalAveragePooling2D(name='globaverpool')
self.denserepresentation = tfl.Dense(128, activation='relu', name='Dense1')
self.x_mean = tfl.Dense(128, name='meanvector')
self.x_variance = tfl.Dense(128, name='variancevector')
self.sampling = Sampling()
def call(self, inputs, training=None, mask=None, **kwargs):
outputs = inputs
print(outputs)
for layer in self.convs:
outputs = layer(outputs)
print(outputs)
outputs = self.features(outputs)
print(outputs)
dense_output = self.denserepresentation(outputs)
print(dense_output)
x_mean = self.x_mean(dense_output)
x_variance = self.x_variance(dense_output)
output = self.sampling((x_mean,x_variance))
return output, x_mean, x_variance
class Decoder(tfl.Layer):
def __init__(self,
dense_reshape,
**kwargs):
super(Decoder, self).__init__(name='Decoder', **kwargs)
self.denserepresentation = tfl.Dense(np.prod(dense_reshape),
activation='relu',
kernel_regularizer=tf.keras.regularizers.l2(0.0001),
name='dense2')
self.reshaped = tfl.Reshape(dense_reshape,
name='reshape')
self.deconvs=[
ConvolutionalBlock(128, 'conv1', deconv=True),
ConvolutionalBlock(64, 'conv2', deconv=True),
ConvolutionalBlock(32, 'conv3', deconv=True),
ConvolutionalBlock(16, 'conv4', deconv=True),
ConvolutionalBlock(8, 'conv5', deconv=True)
]
self.output_layer = tfl.Conv2D(filters=1,
kernel_size=3,
activation='sigmoid', # check this
padding='same',
name='decodedconv',
kernel_regularizer=tf.keras.regularizers.l2(0.0001),
kernel_initializer='he_normal')
def call(self, inputs, training=None, mask=None):
outputs = inputs
outputs = self.denserepresentation(outputs)
outputs = self.reshaped(outputs)
for layer in self.deconvs:
outputs = layer(outputs)
outputs = self.output_layer(outputs)
return outputs
class VariationalAutoEncoder(tf.keras.Model):
def __init__(self,
annealing_weight,
dense_reshape,
input_shape,
**kwargs):
super(VariationalAutoEncoder, self).__init__(**kwargs)
self.annealing_weight = annealing_weight # for KL-loss
self.encoder = Encoder()
self.decoder = Decoder(dense_reshape)
self.build(input_shape)
def call(self, inputs, training=None, mask=None):
dense_output, x_mean, x_variance = self.encoder(inputs)
output = self.decoder(dense_output)
kl_loss = - self.annealing_weight * tf.reduce_mean(
x_variance - tf.keras.backend.square(x_mean)
- tf.keras.backend.exp(x_variance) + 1,
axis=-1)
self.add_loss(lambda: kl_loss)
return output