def tf_apply(self, x):
if util.tf_dtype('int') not in (tf.int32, tf.int64):
x = tf.dtypes.cast(x=x, dtype=tf.int32)
elif util.dtype(x=x) == 'bool':
x = tf.dtypes.cast(x=x, dtype=util.tf_dtype('int'))
x = tf.nn.embedding_lookup(params=self.weights, ids=x, max_norm=self.max_norm)
return super().tf_apply(x=x)
def get_parameter_value(self, step):
parameter = tf.keras.optimizers.schedules.PiecewiseConstantDecay(
boundaries=self.boundaries, values=self.values)(step=step)
if util.dtype(x=parameter) != self.dtype:
parameter = tf.dtypes.cast(x=parameter,
dtype=util.tf_dtype(dtype=self.dtype))
return parameter
def get_parameter_value(self, step):
parameter = tf.compat.v1.train.piecewise_constant(
x=step, boundaries=self.boundaries, values=self.values)
if util.dtype(x=parameter) != self.dtype:
parameter = tf.dtypes.cast(x=parameter,
dtype=util.tf_dtype(dtype=self.dtype))
return parameter
def assign_variable(self, *, variable, value):
if variable.startswith(self.name + '/'):
variable = variable[len(self.name) + 1:]
module = self
scope = variable.split('/')
for _ in range(len(scope) - 1):
module = module.modules[scope.pop(0)]
fetches = util.join_scopes(self.name, variable) + '-assign'
dtype = util.dtype(x=module.variables[scope[0]])
feed_dict = {util.join_scopes(self.name, 'assignment-') + dtype + '-input:0': value}
self.monitored_session.run(fetches=fetches, feed_dict=feed_dict)
def add_placeholder(self, name, dtype, shape, batched, default=None):
# name
name = name + '-input'
if not util.is_valid_name(name=name):
raise TensorforceError.value(name='placeholder',
argument='name',
value=name)
# dtype
if not util.is_valid_type(dtype=dtype):
raise TensorforceError.value(name='placeholder',
argument='dtype',
value=dtype)
# shape
if not util.is_iterable(x=shape) or \
not all(isinstance(num_dims, int) for num_dims in shape):
raise TensorforceError.type(name='placeholder',
argument='shape',
value=shape)
elif not all(num_dims > 0 for num_dims in shape):
raise TensorforceError.value(name='placeholder',
argument='shape',
value=shape)
# batched
if not isinstance(batched, bool):
raise TensorforceError.type(name='placeholder',
argument='batched',
value=batched)
# default
if default is not None:
if batched:
raise TensorforceError.unexpected()
elif not isinstance(default, tf.Tensor):
raise TensorforceError.unexpected()
elif util.dtype(x=default) != dtype:
raise TensorforceError.unexpected()
# Placeholder
if batched:
shape = (None, ) + shape
if default is None:
dtype = util.tf_dtype(dtype=dtype)
placeholder = tf.placeholder(dtype=dtype, shape=shape, name=name)
else:
# check dtype and shape !!!
placeholder = tf.placeholder_with_default(input=default,
shape=shape,
name=name)
return placeholder
def get_parameter_value(self):
if self.unit == 'timesteps':
step = Module.retrieve_tensor(name='timestep')
elif self.unit == 'episodes':
step = Module.retrieve_tensor(name='episode')
parameter = tf.train.piecewise_constant(x=step,
boundaries=self.boundaries,
values=self.values)
if util.dtype(x=parameter) != self.dtype:
parameter = tf.dtypes.cast(x=parameter,
dtype=util.tf_dtype(dtype=self.dtype))
return parameter
def add_variable(
self, name, dtype, shape, is_trainable, initializer='zeros', is_saved=True, summarize=None,
shared=None
):
# name
if not util.is_valid_name(name=name):
raise TensorforceError.value(name='Module.add_variable', argument='name', value=name)
elif name in self.variables:
raise TensorforceError.exists(name='variable', value=name)
# dtype
if not util.is_valid_type(dtype=dtype):
raise TensorforceError.value(name='Module.add_variable', argument='dtype', value=dtype)
# shape
if not util.is_iterable(x=shape) or not all(isinstance(dims, int) for dims in shape):
raise TensorforceError.value(name='Module.add_variable', argument='shape', value=shape)
elif not all(dims > 0 for dims in shape):
raise TensorforceError.value(name='Module.add_variable', argument='shape', value=shape)
# is_trainable
if not isinstance(is_trainable, bool):
raise TensorforceError.type(
name='Module.add_variable', argument='is_trainable', dtype=type(is_trainable)
)
elif is_trainable and dtype != 'float':
raise TensorforceError.value(
name='Module.add_variable', argument='is_trainable', value=is_trainable,
condition='dtype != float'
)
# initializer
initializer_names = (
'normal', 'normal-relu', 'orthogonal', 'orthogonal-relu', 'zeros', 'ones'
)
if not isinstance(initializer, (util.py_dtype(dtype=dtype), np.ndarray, tf.Tensor)) and \
initializer not in initializer_names:
raise TensorforceError.value(
name='Module.add_variable', argument='initializer', value=initializer
)
elif isinstance(initializer, np.ndarray) and \
initializer.dtype != util.np_dtype(dtype=dtype):
raise TensorforceError.type(
name='Module.add_variable', argument='initializer', dtype=type(initializer)
)
elif isinstance(initializer, tf.Tensor) and util.dtype(x=initializer) != dtype:
raise TensorforceError.type(
name='Module.add_variable', argument='initializer', dtype=type(initializer)
)
# is_saved
if not isinstance(is_saved, bool):
raise TensorforceError.type(
name='Module.add_variable', argument='is_saved', dtype=type(is_saved)
)
# summarize
if summarize is not None and not isinstance(summarize, bool):
raise TensorforceError.type(
name='Module.add_variable', argument='summarize', dtype=type(summarize)
)
# shared
if shared is not None and not isinstance(shared, str):
raise TensorforceError.type(
name='Module.add_variable', argument='shared',dtype=type(shared)
)
variable = None
if shared is not None and len(self.graph.get_collection(name=shared)) > 0:
# Retrieve shared variable from TensorFlow
collection = self.graph.get_collection(name=shared)
if len(collection) > 1:
raise TensorforceError.unexpected()
variable = collection[0]
else:
tf_dtype = util.tf_dtype(dtype=dtype)
# Variable initializer
if isinstance(initializer, util.py_dtype(dtype=dtype)):
initializer = tf.constant(value=initializer, dtype=tf_dtype, shape=shape)
elif isinstance(initializer, np.ndarray):
if initializer.shape != shape:
raise TensorforceError.mismatch(
name='Module.add_variable', value1='shape', value2='initializer'
)
initializer = tf.constant(value=initializer, dtype=tf_dtype)
elif isinstance(initializer, tf.Tensor):
if util.shape(x=initializer) != shape:
raise TensorforceError.mismatch(
name='Module.add_variable', value1='shape', value2='initializer'
)
initializer = initializer
elif not isinstance(initializer, str):
raise TensorforceError("Invalid variable initializer: {}".format(initializer))
elif initializer[:6] == 'normal':
if dtype != 'float':
raise TensorforceError(
message="Invalid variable initializer value for non-float variable: {}.".format(
initializer
)
)
if initializer[6:] == '-relu':
stddev = min(0.1, sqrt(2.0 / util.product(xs=shape[:-1])))
else:
stddev = min(0.1, sqrt(2.0 / (util.product(xs=shape[:-1]) + shape[-1])))
initializer = tf.random.normal(shape=shape, stddev=stddev, dtype=tf_dtype)
elif initializer[:10] == 'orthogonal':
if dtype != 'float':
raise TensorforceError(
message="Invalid variable initializer value for non-float variable: {}.".format(
initializer
)
)
if len(shape) < 2:
raise TensorforceError(
message="Invalid variable initializer value for 0/1-rank variable: {}.".format(
initializer
)
)
normal = np.random.normal(size=(util.product(xs=shape[:-1]), shape[-1]))
u, _, v = np.linalg.svd(a=normal, full_matrices=False)
orthogonal = u if u.shape[1] == shape[-1] else v
if initializer[10:] == '-relu':
orthogonal = orthogonal * sqrt(2.0)
initializer = tf.constant(value=orthogonal.reshape(shape), dtype=tf_dtype)
elif initializer == 'zeros':
initializer = tf.zeros(shape=shape, dtype=tf_dtype)
elif initializer == 'ones':
initializer = tf.ones(shape=shape, dtype=tf_dtype)
# Variable
variable = tf.Variable(
initial_value=initializer, trainable=is_trainable, validate_shape=True, name=name,
dtype=tf_dtype, shape=shape
)
# Register shared variable with TensorFlow
if shared is not None:
self.graph.add_to_collection(name=shared, value=variable)
# Register variable
self.variables[name] = variable
if is_trainable:
self.trainable_variables[name] = variable
if is_saved:
self.saved_variables[name] = variable
# Add summary
if (summarize is None and is_trainable) or summarize:
variable = self.add_summary(
label='variables', name=name, tensor=variable, mean_variance=True
)
variable = self.add_summary(label='variables-histogram', name=name, tensor=variable)
return variable
def add_variable(self,
name,
dtype,
shape,
is_trainable,
initializer='zeros',
summarize=None,
shared=None):
# name
if not util.is_valid_name(name=name):
raise TensorforceError.value(name='variable',
argument='name',
value=name)
elif name in self.variables:
raise TensorforceError.exists(name='variable', value=name)
# dtype
if not util.is_valid_type(dtype=dtype):
raise TensorforceError.value(name='variable',
argument='dtype',
value=dtype)
# shape
if not util.is_iterable(x=shape) or \
not all(isinstance(num_dims, int) for num_dims in shape):
raise TensorforceError.type(name='variable',
argument='shape',
value=shape)
elif not all(num_dims > 0 for num_dims in shape):
raise TensorforceError.value(name='variable',
argument='shape',
value=shape)
# is_trainable
if not isinstance(is_trainable, bool):
raise TensorforceError.type(name='variable',
argument='is_trainable',
value=is_trainable)
# initializer
if not isinstance(initializer, (util.py_dtype(dtype=dtype), np.ndarray, tf.Tensor)) and \
initializer not in ('random', 'zeros', 'ones'):
raise TensorforceError.value(name='variable',
argument='initializer',
value=initializer)
elif isinstance(initializer, np.ndarray) and \
initializer.dtype != util.np_dtype(dtype=dtype):
raise TensorforceError.type(name='variable',
argument='initializer',
value=initializer)
elif isinstance(initializer,
tf.Tensor) and util.dtype(x=initializer) != dtype:
raise TensorforceError.type(name='variable',
argument='initializer',
value=initializer)
elif isinstance(initializer,
str) and initializer == 'random' and dtype != 'float':
raise TensorforceError(
message=
"Invalid variable initializer value for non-float variable: {}."
.format(initializer))
# summarize
if summarize is not None and not isinstance(summarize, bool):
raise TensorforceError.type(name='variable',
argument='summarize',
value=summarize)
# shared
if shared is not None and not isinstance(shared, str):
raise TensorforceError.type(name='variable',
argument='shared',
value=shared)
variable = None
if shared is not None and len(tf.get_collection(key=shared)) > 0:
# Retrieve shared variable from TensorFlow
collection = tf.get_collection(key=shared)
if len(collection) > 1:
raise TensorforceError.unexpected()
variable = collection[0]
else:
tf_dtype = util.tf_dtype(dtype=dtype)
# Variable initializer
if isinstance(initializer, util.py_dtype(dtype=dtype)):
initializer = tf.constant(value=initializer,
dtype=tf_dtype,
shape=shape)
elif isinstance(initializer, np.ndarray):
if initializer.shape != shape:
raise TensorforceError(
"Invalid variable initializer shape: {}.".format(
initializer.shape))
initializer = initializer
elif isinstance(initializer, tf.Tensor):
if util.shape(x=initializer) != shape:
raise TensorforceError(
"Invalid variable initializer shape: {}.".format(
util.shape(x=initializer)))
initializer = initializer
elif not isinstance(initializer, str):
raise TensorforceError(
"Invalid variable initializer: {}".format(initializer))
elif initializer == 'random':
stddev = min(
0.1, sqrt(2.0 / (util.product(xs=shape[:-1]) + shape[-1])))
initializer = tf.random_normal(
shape=shape,
mean=0.0,
stddev=stddev,
dtype=util.tf_dtype(dtype=dtype))
elif initializer == 'zeros':
initializer = tf.zeros(shape=shape, dtype=tf_dtype)
elif initializer == 'ones':
initializer = tf.ones(shape=shape, dtype=tf_dtype)
# Variable
variable = tf.Variable(initial_value=initializer,
trainable=is_trainable,
validate_shape=True,
name=name,
dtype=tf_dtype,
expected_shape=shape) # collections=
# Register shared variable with TensorFlow
if shared is not None:
tf.add_to_collection(name=shared, value=variable)
# Register variable
self.variables[name] = variable
if is_trainable:
self.trainable_variables[name] = variable
# Add summary
if (summarize is None and is_trainable) or summarize:
variable = tf.identity(input=variable)
variable = self.add_summary(label='variables',
name=name,
tensor=variable,
mean_variance=True)
return variable
