vae.py about keras-io HOT 7 CLOSED

ValueError Traceback (most recent call last)
in
5 vae = VAE(encoder, decoder)
6 vae.compile(optimizer=keras.optimizers.Adam())
----> 7 vae.fit(mnist_digits, epochs=30, batch_size=128)

/opt/conda/lib/python3.6/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_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
641 max_queue_size=max_queue_size,
642 workers=workers,
--> 643 use_multiprocessing=use_multiprocessing)
644
645 def evaluate(self,

/opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/training_arrays.py in fit(self, model, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_freq, **kwargs)
630 steps=steps_per_epoch,
631 validation_split=validation_split,
--> 632 shuffle=shuffle)
633
634 if validation_data:

/opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, batch_size, check_steps, steps_name, steps, validation_split, shuffle, extract_tensors_from_dataset)
2388 target_tensors=target_tensors,
2389 run_eagerly=self.run_eagerly,
-> 2390 cloning=self._cloning)
2391
2392 # In graph mode, if we had just set inputs and targets as symbolic tensors

/opt/conda/lib/python3.6/site-packages/tensorflow/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs)
456 self._self_setattr_tracking = False # pylint: disable=protected-access
457 try:
--> 458 result = method(self, *args, **kwargs)
459 finally:
460 self._self_setattr_tracking = previous_value # pylint: disable=protected-access

/opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py in compile(self, optimizer, loss, metrics, loss_weights, sample_weight_mode, weighted_metrics, target_tensors, distribute, **kwargs)
335
336 # Creates the model loss and weighted metrics sub-graphs.
--> 337 self._compile_weights_loss_and_weighted_metrics()
338
339 # Functions for train, test and predict will

/opt/conda/lib/python3.6/site-packages/tensorflow/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs)
456 self._self_setattr_tracking = False # pylint: disable=protected-access
457 try:
--> 458 result = method(self, *args, **kwargs)
459 finally:
460 self._self_setattr_tracking = previous_value # pylint: disable=protected-access

/opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py in _compile_weights_loss_and_weighted_metrics(self, sample_weights)
1492 # loss_weight_2 * output_2_loss_fn(...) +
1493 # layer losses.
-> 1494 self.total_loss = self._prepare_total_loss(masks)
1495
1496 def _prepare_skip_target_masks(self):

/opt/conda/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py in _prepare_total_loss(self, masks)
1593 if total_loss is None:
1594 if not self.losses:
-> 1595 raise ValueError('The model cannot be compiled '
1596 'because it has no loss to optimize.')
1597 else:

ValueError: The model cannot be compiled because it has no loss to optimize.

from keras-io.

I wasn't able to reproduce this issue while running tensorflow 2.2. What version are you using?

from keras-io.

I also met this issue with tensorflow 2.1, but fixed it by updating to 2.2

However, there is a warning:

WARNING:tensorflow:AutoGraph could not transform <bound method VAE.train_step of <main.VAE object at 0x7f8319e7da90>> 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.

from keras-io.

I encountered this issue using TF 2.1.0. Please update the example - some environments are still using TF 2.1.0 and older versions. For instance see conda's offering TD 2.1.0 for Windows here:

from keras-io.

Hi,

Please upgrade to the latest Keras/ Tensorflow version

You can use Keras using Tensorflow import as below.

import tensorflow as tf
input_layer = tf.keras.Input(shape=[100])

Let us know if you still face any error in latest version. Thanks!

from keras-io.

This issue is stale because it has been open for 14 days with no activity. It will be closed if no further activity occurs. Thank you.

from keras-io.

This issue was closed because it has been inactive for 28 days. Please reopen if you'd like to work on this further.

from keras-io.