def linear(args,
output_size,
bias,
bias_start=0.0,
scope=None,
squeeze=False,
wd=0.0,
input_keep_prob=1.0,
is_train=None):
if args is None or (nest.is_sequence(args) and not args):
raise ValueError("`args` must be specified")
if not nest.is_sequence(args):
args = [args]
flat_args = [flatten(arg, 1) for arg in args]
if input_keep_prob < 1.0:
assert is_train is not None
flat_args = [
tf.cond(is_train, lambda: tf.nn.dropout(arg, input_keep_prob),
lambda: arg) for arg in flat_args
]
with tf.variable_scope(scope or 'Linear'):
flat_out = _linear(
flat_args,
output_size,
bias,
bias_initializer=tf.constant_initializer(bias_start))
out = reconstruct(flat_out, args[0], 1)
if squeeze:
out = tf.squeeze(out, [len(args[0].get_shape().as_list()) - 1])
if wd:
add_wd(wd)
return out
def linear(args, output_size, bias, bias_start=0.0, scope=None, squeeze=False, wd=0.0, input_keep_prob=1.0,
is_train=None):
"""
output the same shape of the args/inputs,
:param args: here it's [60, ?, ?, 200] shape tensor
:param output_size: output size is same with args's final dimension, which is 200 here
:param bias: true,
:param bias_start: here it's 0
:param scope: trans, i don't know what this scope means,
:param squeeze: False, todo what'is this one?
:param wd: weight decay, 0 here
:param input_keep_prob: 1 here
:param is_train: place holder
:return:
"""
if args is None or (nest.is_sequence(args) and not args):
raise ValueError("`args` must be specified")
if not nest.is_sequence(args):
args = [args]
flat_args = [flatten(arg, 1) for arg in args] # [60, ?, ?, 200] -> [?, 200]
if input_keep_prob < 1.0:
assert is_train is not None
flat_args = [tf.cond(is_train, lambda: tf.nn.dropout(arg, input_keep_prob), lambda: arg)
for arg in flat_args]
with tf.variable_scope(scope or 'Linear'):
flat_out = _linear(flat_args, output_size, bias, bias_initializer=tf.constant_initializer(bias_start))
out = reconstruct(flat_out, args[0], 1)
if squeeze:
out = tf.squeeze(out, [len(args[0].get_shape().as_list()) - 1])
if wd:
add_wd(wd)
return out
def linear(args, output_size, bias, bias_start=0.0, scope=None, squeeze=False, wd=0.0, input_keep_prob=1.0,
is_train=None):
if args is None or (nest.is_sequence(args) and not args):
raise ValueError("`args` must be specified")
if not nest.is_sequence(args):
args = [args]
flat_args = [flatten(arg, 1) for arg in args]
if input_keep_prob < 1.0:
assert is_train is not None
flat_args = [tf.cond(is_train, lambda: tf.nn.dropout(arg, input_keep_prob), lambda: arg)
for arg in flat_args]
flat_out = _linear(flat_args, output_size, bias, bias_start=bias_start, scope=scope)
out = reconstruct(flat_out, args[0], 1)
if squeeze:
out = tf.squeeze(out, [len(args[0].get_shape().as_list())-1])
if wd:
add_wd(wd)
return out
def linear(args,
output_size,
bias,
bias_start=0.0,
scope=None,
squeeze=False,
wd=0.0,
input_keep_prob=1.0,
is_train=None):
if args is None or (nest.is_sequence(args) and not args):
raise ValueError("`args` must be specified")
if not nest.is_sequence(args):
args = [args]
flat_args = [flatten(arg, 1) for arg in args]
if input_keep_prob < 1.0:
assert is_train is not None
flat_args = [
tf.cond(is_train, lambda: tf.nn.dropout(arg, input_keep_prob),
lambda: arg) for arg in flat_args
]
print(flat_args)
print(output_size)
print(bias)
print(bias_start)
print(scope)
flat_out = tf.contrib.layers.fully_connected(
inputs=flat_args,
num_outputs=output_size,
biases_initializer=tf.constant_initializer(bias_start),
activation_fn=None)
#flat_out = _linear(flat_args, output_size, bias, bias_start=bias_start, scope=scope)
out = reconstruct(flat_out, args[0], 1)
if squeeze:
out = tf.squeeze(out, [len(args[0].get_shape().as_list()) - 1])
if wd:
add_wd(wd)
return out
