def main(*args):
dataset_dir = "../data/mnist-tf"
mnist = input_data.read_data_sets(dataset_dir)
X_train = mnist.train.images.astype('float32') / 255.
X_eval = mnist.validation.images.astype('float32') / 255.
X_test = mnist.test.images.astype('float32') / 255.
X_train = X_train.reshape((len(X_train), total_tensor_depth(X_train)))
X_eval = X_eval.reshape((len(X_eval), total_tensor_depth(X_eval)))
X_test = X_test.reshape((len(X_test), total_tensor_depth(X_test)))
xp = experiment_fn("/tmp/polyaxon_logs/vae", {'images': X_train},
mnist.train.labels, {'images': X_eval},
mnist.validation.labels)
xp.continuous_train_and_evaluate()
encode(xp.estimator, X_test, mnist.test.labels)
generate(xp.estimator)
def main(*args):
dataset_dir = "../data/mnist-tf"
mnist = input_data.read_data_sets(dataset_dir)
X_train = mnist.train.images.astype('float32') / 255.
X_eval = mnist.validation.images.astype('float32') / 255.
X_test = mnist.test.images.astype('float32') / 255.
X_train = X_train.reshape((len(X_train), total_tensor_depth(X_train)))
X_eval = X_eval.reshape((len(X_eval), total_tensor_depth(X_eval)))
X_test = X_test.reshape((len(X_test), total_tensor_depth(X_test)))
xp = experiment_fn("/tmp/polyaxon_logs/vae",
{'images': X_train}, mnist.train.labels,
{'images': X_eval}, mnist.validation.labels)
xp.continuous_train_and_evaluate()
encode(xp.estimator, X_test, mnist.test.labels)
generate(xp.estimator)
def _build(self, incoming, *args, **kwargs):
"""
Args:
incoming: (2+)-D Tensor [samples, input dim]. If not 2D, input will be flatten.
Returns:
2D Tensor [samples, num_units].
"""
self._declare_dependencies()
input_shape = get_shape(incoming)
incoming = validate_dtype(incoming)
assert len(
input_shape) > 1, 'Incoming Tensor shape must be at least 2-D'
n_inputs = total_tensor_depth(tensor_shape=input_shape)
regularizer = getters.get_regularizer(self.regularizer,
scale=self.scale,
collect=True)
self._w = variable(name='w',
shape=[n_inputs, self.num_units],
dtype=incoming.dtype,
regularizer=regularizer,
initializer=getters.get_initializer(
self.weights_init),
trainable=self.trainable,
restore=self.restore)
track(self._w, tf.GraphKeys.LAYER_VARIABLES, self.module_name)
inference = incoming
# If input is not 2d, flatten it.
if len(input_shape) > 2:
inference = tf.reshape(tensor=inference, shape=[-1, n_inputs])
inference = tf.matmul(a=inference, b=self._w)
self._b = None
if self.bias:
self._b = variable(name='b',
shape=[self.num_units],
dtype=incoming.dtype,
initializer=getters.get_initializer(
self.bias_init),
trainable=self.trainable,
restore=self.restore)
track(self._b, tf.GraphKeys.LAYER_VARIABLES, self.module_name)
inference = tf.nn.bias_add(value=inference, bias=self._b)
if self.activation:
inference = getters.get_activation(self.activation,
collect=True)(inference)
if self._dropout:
inference = self._dropout(inference)
track(inference, tf.GraphKeys.LAYER_TENSOR, self.module_name)
return inference
def _build(self, incoming, *args, **kwargs):
"""
Args:
incoming: (2+)-D Tensor [samples, input dim]. If not 2D, input will be flatten.
Returns:
2D Tensor [samples, num_units].
"""
self._declare_dependencies()
input_shape = get_shape(incoming)
assert len(input_shape) > 1, 'Incoming Tensor shape must be at least 2-D'
n_inputs = total_tensor_depth(tensor_shape=input_shape)
regularizer = getters.get_regularizer(self.regularizer, scale=self.scale, collect=True)
initializer = getters.get_initializer(self.weights_init)
self._w = variable(name='w', shape=[n_inputs, self.num_units], regularizer=regularizer,
initializer=initializer, trainable=self.trainable,
restore=self.restore)
track(self._w, tf.GraphKeys.LAYER_VARIABLES, self.module_name)
self._b = variable(name='b', shape=[self.num_units],
initializer=getters.get_initializer(self.bias_init),
trainable=self.trainable, restore=self.restore)
track(self._b, tf.GraphKeys.LAYER_VARIABLES, self.module_name)
# Weight and bias for the transform gate
self._w_t = variable(name='w_t', shape=[n_inputs, self.num_units],
regularizer=None, initializer=initializer,
trainable=self.trainable, restore=self.restore)
track(self._w_t, tf.GraphKeys.LAYER_VARIABLES, self.module_name)
self._b_t = variable(name='b_t', shape=[self.num_units],
initializer=tf.constant_initializer(-1),
trainable=self.trainable, restore=self.restore)
track(self._b_t, tf.GraphKeys.LAYER_VARIABLES, self.module_name)
# If input is not 2d, flatten it.
if len(input_shape) > 2:
incoming = tf.reshape(tensor=incoming, shape=[-1, n_inputs])
H = getters.get_activation(self.activation)(tf.matmul(a=incoming, b=self._w) + self._b)
T = tf.sigmoid(tf.matmul(a=incoming, b=self._w_t) + self._b_t)
if self._transform_dropout:
T = self._transform_dropout(T)
C = tf.subtract(x=1.0, y=T)
inference = tf.add(x=tf.multiply(x=H, y=T), y=tf.multiply(x=incoming, y=C))
track(inference, tf.GraphKeys.ACTIVATIONS)
track(inference, tf.GraphKeys.LAYER_TENSOR, self.module_name)
return inference
def _build(self, incoming, *args, **kwargs):
"""
Args:
incoming: (2+)-D `Tensor`.
Returns:
2-D `Tensor` [batch, flatten_dims].
"""
input_shape = get_shape(incoming)
assert len(input_shape) > 1, 'Incoming Tensor shape must be at least 2-D'
dims = total_tensor_depth(tensor_shape=input_shape)
x = tf.reshape(tensor=incoming, shape=[-1, dims])
track(x, tf.GraphKeys.LAYER_TENSOR, self.name)
return x
def _build(self, incoming, *args, **kwargs):
"""
Args:
incoming: (2+)-D Tensor [samples, input dim]. If not 2D, input will be flatten.
Returns:
2D Tensor [samples, num_units].
"""
self._declare_dependencies()
input_shape = get_shape(incoming)
incoming = validate_dtype(incoming)
assert len(input_shape) > 1, 'Incoming Tensor shape must be at least 2-D'
n_inputs = total_tensor_depth(tensor_shape=input_shape)
regularizer = getters.get_regularizer(self.regularizer, scale=self.scale, collect=True)
self._w = variable(
name='w', shape=[n_inputs, self.num_units], dtype=incoming.dtype, regularizer=regularizer,
initializer=getters.get_initializer(self.weights_init), trainable=self.trainable,
restore=self.restore)
track(self._w, tf.GraphKeys.LAYER_VARIABLES, self.module_name)
inference = incoming
# If input is not 2d, flatten it.
if len(input_shape) > 2:
inference = tf.reshape(tensor=inference, shape=[-1, n_inputs])
inference = tf.matmul(a=inference, b=self._w)
self._b = None
if self.bias:
self._b = variable(name='b', shape=[self.num_units], dtype=incoming.dtype,
initializer=getters.get_initializer(self.bias_init),
trainable=self.trainable, restore=self.restore)
track(self._b, tf.GraphKeys.LAYER_VARIABLES, self.module_name)
inference = tf.nn.bias_add(value=inference, bias=self._b)
if self.activation:
inference = getters.get_activation(self.activation, collect=True)(inference)
if self._dropout:
inference = self._dropout(inference)
track(inference, tf.GraphKeys.LAYER_TENSOR, self.module_name)
return inference
def _build(self, incoming, *args, **kwargs):
"""
Args:
incoming: 1-D Tensor [samples]. If not 2D, input will be flatten.
Returns:
1-D Tensor [samples].
"""
input_shape = get_shape(incoming)
n_inputs = total_tensor_depth(tensor_shape=input_shape)
initializer = tf.constant_initializer(value=np.random.randn())
self._w = variable(name='w',
shape=[n_inputs],
dtype=incoming.dtype,
initializer=initializer,
trainable=self.trainable,
restore=self.restore)
track(self._w, tf.GraphKeys.LAYER_VARIABLES, self.module_name)
inference = incoming
# If input is not 2d, flatten it.
if len(input_shape) > 1:
inference = tf.reshape(tensor=inference, shape=[-1])
inference = tf.multiply(x=inference, y=self._w)
self._b = None
if self.bias:
self._b = variable(name='b',
shape=[n_inputs],
dtype=incoming.dtype,
initializer=initializer,
trainable=self.trainable,
restore=self.restore)
inference = tf.add(inference, self._b)
track(self._b, tf.GraphKeys.LAYER_VARIABLES, self.module_name)
if self.activation:
inference = getters.get_activation(self.activation,
collect=True)(inference)
track(inference, tf.GraphKeys.LAYER_TENSOR, self.module_name)
return inference
def _build(self, incoming, *args, **kwargs):
"""
Args:
incoming: 1-D Tensor [samples]. If not 2D, input will be flatten.
Returns:
1-D Tensor [samples].
"""
input_shape = get_shape(incoming)
n_inputs = total_tensor_depth(tensor_shape=input_shape)
initializer = tf.constant_initializer(value=np.random.randn())
self._w = variable(name='w', shape=[n_inputs],
dtype=incoming.dtype, initializer=initializer,
trainable=self.trainable, restore=self.restore)
track(self._w, tf.GraphKeys.LAYER_VARIABLES, self.module_name)
inference = incoming
# If input is not 2d, flatten it.
if len(input_shape) > 1:
inference = tf.reshape(tensor=inference, shape=[-1])
inference = tf.multiply(x=inference, y=self._w)
self._b = None
if self.bias:
self._b = variable(name='b', shape=[n_inputs],
dtype=incoming.dtype, initializer=initializer,
trainable=self.trainable, restore=self.restore)
inference = tf.add(inference, self._b)
track(self._b, tf.GraphKeys.LAYER_VARIABLES, self.module_name)
if self.activation:
inference = getters.get_activation(self.activation, collect=True)(inference)
track(inference, tf.GraphKeys.LAYER_TENSOR, self.module_name)
return inference