VAE(変分オートエンコーダ) MNIST

Question

前提・実現したいこと

VAE、変分オートエンコーダのプログラムについて勉強しています。
https://nbviewer.jupyter.org/github/fchollet/deep-learning-with-python-notebooks/blob/master/8.4-generating-images-with-vaes.ipynb
上記のプログラムを実行している時に下記のようなエラーが発生しました。

発生している問題・エラーメッセージ

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-5-b05f280ca0dc> in <module>
     13 x_test = x_test.reshape(x_test.shape + (1,))
     14 
---> 15 vae.fit(x=x_train, y=None,
     16         shuffle=True,
     17         epochs=10,

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
   1098                 _r=1):
   1099               callbacks.on_train_batch_begin(step)
-> 1100               tmp_logs = self.train_function(iterator)
   1101               if data_handler.should_sync:
   1102                 context.async_wait()

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
    826     tracing_count = self.experimental_get_tracing_count()
    827     with trace.Trace(self._name) as tm:
--> 828       result = self._call(*args, **kwds)
    829       compiler = "xla" if self._experimental_compile else "nonXla"
    830       new_tracing_count = self.experimental_get_tracing_count()

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
    869       # This is the first call of __call__, so we have to initialize.
    870       initializers = []
--> 871       self._initialize(args, kwds, add_initializers_to=initializers)
    872     finally:
    873       # At this point we know that the initialization is complete (or less

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
    723     self._graph_deleter = FunctionDeleter(self._lifted_initializer_graph)
    724     self._concrete_stateful_fn = (
--> 725         self._stateful_fn._get_concrete_function_internal_garbage_collected(  # pylint: disable=protected-access
    726             *args, **kwds))
    727 

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
   2967       args, kwargs = None, None
   2968     with self._lock:
-> 2969       graph_function, _ = self._maybe_define_function(args, kwargs)
   2970     return graph_function
   2971 

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
   3359 
   3360           self._function_cache.missed.add(call_context_key)
-> 3361           graph_function = self._create_graph_function(args, kwargs)
   3362           self._function_cache.primary[cache_key] = graph_function
   3363 

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   3194     arg_names = base_arg_names + missing_arg_names
   3195     graph_function = ConcreteFunction(
-> 3196         func_graph_module.func_graph_from_py_func(
   3197             self._name,
   3198             self._python_function,

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
    988         _, original_func = tf_decorator.unwrap(python_func)
    989 
--> 990       func_outputs = python_func(*func_args, **func_kwargs)
    991 
    992       # invariant: `func_outputs` contains only Tensors, CompositeTensors,

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/eager/def_function.py in wrapped_fn(*args, **kwds)
    632             xla_context.Exit()
    633         else:
--> 634           out = weak_wrapped_fn().__wrapped__(*args, **kwds)
    635         return out
    636 

~/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
    975           except Exception as e:  # pylint:disable=broad-except
    976             if hasattr(e, "ag_error_metadata"):
--> 977               raise e.ag_error_metadata.to_exception(e)
    978             else:
    979               raise

該当のソースコード

import keras
from keras import layers
from keras import backend as K
from keras.models import Model
import numpy as np

img_shape = (28, 28, 1)
batch_size = 16
latent_dim = 2  # Dimensionality of the latent space: a plane

input_img = keras.Input(shape=img_shape)

x = layers.Conv2D(32, 3,
                  padding='same', activation='relu')(input_img)
x = layers.Conv2D(64, 3,
                  padding='same', activation='relu',
                  strides=(2, 2))(x)
x = layers.Conv2D(64, 3,
                  padding='same', activation='relu')(x)
x = layers.Conv2D(64, 3,
                  padding='same', activation='relu')(x)
shape_before_flattening = K.int_shape(x)

x = layers.Flatten()(x)
x = layers.Dense(32, activation='relu')(x)

z_mean = layers.Dense(latent_dim)(x)
z_log_var = layers.Dense(latent_dim)(x)

def sampling(args):
    z_mean, z_log_var = args
    epsilon = K.random_normal(shape=(K.shape(z_mean)[0], latent_dim),
                              mean=0., stddev=1.)
    return z_mean + K.exp(z_log_var) * epsilon

z = layers.Lambda(sampling)([z_mean, z_log_var])

# This is the input where we will feed `z`.
decoder_input = layers.Input(K.int_shape(z)[1:])

# Upsample to the correct number of units
x = layers.Dense(np.prod(shape_before_flattening[1:]),
                 activation='relu')(decoder_input)

# Reshape into an image of the same shape as before our last `Flatten` layer
x = layers.Reshape(shape_before_flattening[1:])(x)

# We then apply then reverse operation to the initial
# stack of convolution layers: a `Conv2DTranspose` layers
# with corresponding parameters.
x = layers.Conv2DTranspose(32, 3,
                           padding='same', activation='relu',
                           strides=(2, 2))(x)
x = layers.Conv2D(1, 3,
                  padding='same', activation='sigmoid')(x)
# We end up with a feature map of the same size as the original input.

# This is our decoder model.
decoder = Model(decoder_input, x)

# We then apply it to `z` to recover the decoded `z`.
z_decoded = decoder(z)

class CustomVariationalLayer(keras.layers.Layer):

    def vae_loss(self, x, z_decoded):
        x = K.flatten(x)
        z_decoded = K.flatten(z_decoded)
        xent_loss = keras.metrics.binary_crossentropy(x, z_decoded)
        kl_loss = -5e-4 * K.mean(
            1 + z_log_var - K.square(z_mean) - K.exp(z_log_var), axis=-1)
        return K.mean(xent_loss + kl_loss)

    def call(self, inputs):
        x = inputs[0]
        z_decoded = inputs[1]
        loss = self.vae_loss(x, z_decoded)
        self.add_loss(loss, inputs=inputs)
        # We don't use this output.
        return x

# We call our custom layer on the input and the decoded output,
# to obtain the final model output.
y = CustomVariationalLayer()([input_img, z_decoded])

from keras.datasets import mnist

vae = Model(input_img, y)
vae.compile(optimizer='rmsprop', loss=None)
vae.summary()

# Train the VAE on MNIST digits
(x_train, _), (x_test, y_test) = mnist.load_data()

x_train = x_train.astype('float32') / 255.
x_train = x_train.reshape(x_train.shape + (1,))
x_test = x_test.astype('float32') / 255.
x_test = x_test.reshape(x_test.shape + (1,))

vae.fit(x=x_train, y=None,
        shuffle=True,
        epochs=10,
        batch_size=batch_size,
        validation_data=(x_test, None))

https://nbviewer.jupyter.org/github/fchollet/deep-learning-with-python-notebooks/blob/master/8.4-generating-images-with-vaes.ipynb
からコピペで入力しました。

解決方法を教えて頂きたいです。よろしくお願い致します。

Comments

[jbpb0]

エラーメッセージは、もっと続いてませんか？

[Maru_Ma]

コメントありがとうございます。
下記のエラーが続いています。

TypeError: in user code:

/Users/username/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:805 train_function *
return step_function(self, iterator)
/Users/username/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:795 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
/Users/username/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:1259 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/Users/username/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:2730 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/Users/username/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/distribute/distribute_lib.py:3417 _call_for_each_replica
return fn(*args, **kwargs)
/Users/username/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:788 run_step **
outputs = model.train_step(data)
/Users/username/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/training.py:755 train_step
loss = self.compiled_loss(
/Users/username/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/compile_utils.py:237 __call__
self._loss_metric.update_state(
/Users/username/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/utils/metrics_utils.py:90 decorated
update_op = update_state_fn(*args, **kwargs)
/Users/username/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/metrics.py:177 update_state_fn
return ag_update_state(*args, **kwargs)
/Users/username/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/metrics.py:378 update_state **
with ops.control_dependencies([value_sum]):
/Users/username/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/framework/ops.py:5359 control_dependencies
return get_default_graph().control_dependencies(control_inputs)
/Users/username/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/framework/func_graph.py:359 control_dependencies
self.control_captures.add(graph_element)
/Users/username/opt/anaconda3/lib/python3.8/site-packages/tensorflow/python/keras/engine/keras_tensor.py:260 __hash__
raise TypeError('Tensors are unhashable. (%s)'

TypeError: Tensors are unhashable. (KerasTensor(type_spec=TensorSpec(shape=(), dtype=tf.float32, name=None), name='tf.math.reduce_sum_9/Sum:0', description="created by layer 'tf.math.reduce_sum_9'"))Instead, use tensor.ref() as the key.

Answer 1

Generating images
をgoogleコラボに入れて動かしたら、同様なエラーが出ました

上記の先頭を見たら、

keras.__version__

が「'2.0.8'」と古いので、TF 1.x時代のコードだろうと思い、googleコラボで先頭に

!pip install tensorflow-gpu==1.15.3
!pip install keras==2.3.1

を追加して実行したら、エラー出ませんでした

TF 1.x環境を作って、そこで動かしてみてください