Keras-GAN
Keras-GAN copied to clipboard
Published
20 hours ago •
eriklindernoren
eriklindernoren
Cannot run the examples
I download the repo and I am trying some examples,like AAE or cgan. However, I get these errors and I do not know the reason:
In the case of the AAE:
Model: "sequential_5"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense_21 (Dense) (None, 512) 5632
_________________________________________________________________
leaky_re_lu_15 (LeakyReLU) (None, 512) 0
_________________________________________________________________
dense_22 (Dense) (None, 256) 131328
_________________________________________________________________
leaky_re_lu_16 (LeakyReLU) (None, 256) 0
_________________________________________________________________
dense_23 (Dense) (None, 1) 257
=================================================================
Total params: 137,217
Trainable params: 137,217
Non-trainable params: 0
_________________________________________________________________
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-3-9a0cd9a40d47> in <module>()
187
188 if __name__ == '__main__':
--> 189 aae = AdversarialAutoencoder()
190 aae.train(epochs=20000, batch_size=32, sample_interval=200)
1 frames
<ipython-input-3-9a0cd9a40d47> in __init__(self)
34
35 # Build the encoder / decoder
---> 36 self.encoder = self.build_encoder()
37 self.decoder = self.build_decoder()
38
<ipython-input-3-9a0cd9a40d47> in build_encoder(self)
70 latent_repr = merge([mu, log_var],
71 mode=lambda p: p[0] + K.random_normal(K.shape(p[0])) * K.exp(p[1] / 2),
---> 72 output_shape=lambda p: p[0])
73
74 return Model(img, latent_repr)
TypeError: 'module' object is not callable
In the case of the cgan:
Model: "sequential_8"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense_36 (Dense) (None, 512) 401920
_________________________________________________________________
leaky_re_lu_25 (LeakyReLU) (None, 512) 0
_________________________________________________________________
dense_37 (Dense) (None, 512) 262656
_________________________________________________________________
leaky_re_lu_26 (LeakyReLU) (None, 512) 0
_________________________________________________________________
dropout_9 (Dropout) (None, 512) 0
_________________________________________________________________
dense_38 (Dense) (None, 512) 262656
_________________________________________________________________
leaky_re_lu_27 (LeakyReLU) (None, 512) 0
_________________________________________________________________
dropout_10 (Dropout) (None, 512) 0
_________________________________________________________________
dense_39 (Dense) (None, 1) 513
=================================================================
Total params: 927,745
Trainable params: 927,745
Non-trainable params: 0
_________________________________________________________________
Model: "sequential_9"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense_40 (Dense) (None, 256) 25856
_________________________________________________________________
leaky_re_lu_28 (LeakyReLU) (None, 256) 0
_________________________________________________________________
batch_normalization_12 (Batc (None, 256) 1024
_________________________________________________________________
dense_41 (Dense) (None, 512) 131584
_________________________________________________________________
leaky_re_lu_29 (LeakyReLU) (None, 512) 0
_________________________________________________________________
batch_normalization_13 (Batc (None, 512) 2048
_________________________________________________________________
dense_42 (Dense) (None, 1024) 525312
_________________________________________________________________
leaky_re_lu_30 (LeakyReLU) (None, 1024) 0
_________________________________________________________________
batch_normalization_14 (Batc (None, 1024) 4096
_________________________________________________________________
dense_43 (Dense) (None, 784) 803600
_________________________________________________________________
reshape_4 (Reshape) (None, 28, 28, 1) 0
=================================================================
Total params: 1,493,520
Trainable params: 1,489,936
Non-trainable params: 3,584
_________________________________________________________________
/usr/local/lib/python3.6/dist-packages/keras/engine/training.py:297: UserWarning: Discrepancy between trainable weights and collected trainable weights, did you set `model.trainable` without calling `model.compile` after ?
'Discrepancy between trainable weights and collected trainable'
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/indexed_slices.py:434: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory.
"Converting sparse IndexedSlices to a dense Tensor of unknown shape. "
0 [D loss: 0.693212, acc.: 29.69%] [G loss: 0.681004]
---------------------------------------------------------------------------
FailedPreconditionError Traceback (most recent call last)
<ipython-input-5-d80d5608757d> in <module>()
183 if __name__ == '__main__':
184 cgan = CGAN()
--> 185 cgan.train(epochs=100, batch_size=32, sample_interval=200)
7 frames
<ipython-input-5-d80d5608757d> in train(self, epochs, batch_size, sample_interval)
138
139 # Train the discriminator
--> 140 d_loss_real = self.discriminator.train_on_batch([imgs, labels], valid)
141 d_loss_fake = self.discriminator.train_on_batch([gen_imgs, labels], fake)
142 d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)
/usr/local/lib/python3.6/dist-packages/keras/engine/training.py in train_on_batch(self, x, y, sample_weight, class_weight, reset_metrics)
1512 ins = x + y + sample_weights
1513 self._make_train_function()
-> 1514 outputs = self.train_function(ins)
1515
1516 if reset_metrics:
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py in __call__(self, inputs)
3790 value = math_ops.cast(value, tensor.dtype)
3791 converted_inputs.append(value)
-> 3792 outputs = self._graph_fn(*converted_inputs)
3793
3794 # EagerTensor.numpy() will often make a copy to ensure memory safety.
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in __call__(self, *args, **kwargs)
1603 TypeError: For invalid positional/keyword argument combinations.
1604 """
-> 1605 return self._call_impl(args, kwargs)
1606
1607 def _call_impl(self, args, kwargs, cancellation_manager=None):
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in _call_impl(self, args, kwargs, cancellation_manager)
1643 raise TypeError("Keyword arguments {} unknown. Expected {}.".format(
1644 list(kwargs.keys()), list(self._arg_keywords)))
-> 1645 return self._call_flat(args, self.captured_inputs, cancellation_manager)
1646
1647 def _filtered_call(self, args, kwargs):
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
1744 # No tape is watching; skip to running the function.
1745 return self._build_call_outputs(self._inference_function.call(
-> 1746 ctx, args, cancellation_manager=cancellation_manager))
1747 forward_backward = self._select_forward_and_backward_functions(
1748 args,
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in call(self, ctx, args, cancellation_manager)
596 inputs=args,
597 attrs=attrs,
--> 598 ctx=ctx)
599 else:
600 outputs = execute.execute_with_cancellation(
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
58 ctx.ensure_initialized()
59 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 60 inputs, attrs, num_outputs)
61 except core._NotOkStatusException as e:
62 if name is not None:
FailedPreconditionError: Error while reading resource variable _AnonymousVar440 from Container: localhost. This could mean that the variable was uninitialized. Not found: Resource localhost/_AnonymousVar440/N10tensorflow3VarE does not exist.
[[node mul_419/ReadVariableOp (defined at /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:3009) ]] [Op:__inference_keras_scratch_graph_23010]
Function call stack:
keras_scratch_graph
You need to install these specific packages:
TensorFlow GPU 1.13.1 Keras 2.3.1
Works for me. Running experiments on Ubuntu 18.04 with Python 3.6 inside a conda environment.
