def __init__(self, input, label, ignored_tokens=None, **kwargs):
super(EditDistance, self).__init__("edit_distance", **kwargs)
main_program = self.helper.main_program
if main_program.current_block().idx != 0:
raise ValueError("You can only invoke Evaluator in root block")
self.total_distance = self._create_state(dtype='float32',
shape=[1],
suffix='total_distance')
self.seq_num = self._create_state(dtype='int64',
shape=[1],
suffix='seq_num')
self.instance_error = self._create_state(dtype='int64',
shape=[1],
suffix='instance_error')
distances, seq_num = layers.edit_distance(
input=input, label=label, ignored_tokens=ignored_tokens)
zero = layers.fill_constant(shape=[1], value=0.0, dtype='float32')
compare_result = layers.equal(distances, zero)
compare_result_int = layers.cast(x=compare_result, dtype='int')
seq_right_count = layers.reduce_sum(compare_result_int)
instance_error_count = layers.elementwise_sub(x=seq_num,
y=seq_right_count)
total_distance = layers.reduce_sum(distances)
layers.sums(input=[self.total_distance, total_distance],
out=self.total_distance)
layers.sums(input=[self.seq_num, seq_num], out=self.seq_num)
layers.sums(input=[self.instance_error, instance_error_count],
out=self.instance_error)
self.metrics.append(total_distance)
self.metrics.append(instance_error_count)
def __init__(self, input, label, ignored_tokens=None, **kwargs):
super(EditDistance, self).__init__("edit_distance", **kwargs)
main_program = self.helper.main_program
if main_program.current_block().idx != 0:
raise ValueError("You can only invoke Evaluator in root block")
self.total_distance = self.create_state(
dtype='float32', shape=[1], suffix='total_distance')
self.seq_num = self.create_state(
dtype='int64', shape=[1], suffix='seq_num')
self.instance_error = self.create_state(
dtype='int64', shape=[1], suffix='instance_error')
distances, seq_num = layers.edit_distance(
input=input, label=label, ignored_tokens=ignored_tokens)
zero = layers.fill_constant(shape=[1], value=0.0, dtype='float32')
compare_result = layers.equal(distances, zero)
compare_result_int = layers.cast(x=compare_result, dtype='int')
seq_right_count = layers.reduce_sum(compare_result_int)
instance_error_count = layers.elementwise_sub(
x=seq_num, y=seq_right_count)
total_distance = layers.reduce_sum(distances)
layers.sums(
input=[self.total_distance, total_distance],
out=self.total_distance)
layers.sums(input=[self.seq_num, seq_num], out=self.seq_num)
layers.sums(
input=[self.instance_error, instance_error_count],
out=self.instance_error)
self.metrics.append(total_distance)
self.metrics.append(instance_error_count)
def process_context(self, context, param, grad):
if self.group_name not in context:
context[self.group_name] = []
context[self.group_name + "_clip_value"] = self.clip_norm
context[self.group_name + "_clip"] = layers.fill_constant(
shape=[1], dtype="float32", value=self.clip_norm)
else:
if not self.clip_norm == context[self.group_name + "_clip_value"]:
raise ValueError(
"All parameters' 'clip_norm' of a same group should be the same"
)
local_norm_var = layers.reduce_sum(input=layers.pow(x=grad, factor=2.0))
context[self.group_name].append(local_norm_var)
self.context = context
def process_context(self, context, param, grad):
if self.group_name not in context:
context[self.group_name] = []
context[self.group_name + "_clip_value"] = self.clip_norm
context[self.group_name + "_clip"] = layers.fill_constant(
shape=[1], dtype="float32", value=self.clip_norm)
else:
if not self.clip_norm == context[self.group_name + "_clip_value"]:
raise ValueError(
"All parameters' 'clip_norm' of a same group should be the same"
)
local_norm_var = layers.reduce_sum(
input=layers.pow(x=grad, factor=2.0))
context[self.group_name].append(local_norm_var)
self.context = context