def __init__(self, input, label, k=1, **kwargs):
super(Accuracy, self).__init__("accuracy", **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 = self.create_state(dtype='int64',
shape=[1],
suffix='total')
self.correct = self.create_state(dtype='int64',
shape=[1],
suffix='correct')
kwargs = {'main_program': main_program}
total = self.helper.create_tmp_variable(dtype='int')
correct = self.helper.create_tmp_variable(dtype='int')
acc = layers.accuracy(input=input,
label=label,
k=k,
total=total,
correct=correct,
**kwargs)
total = layers.cast(x=total, dtype='int64', **kwargs)
correct = layers.cast(x=correct, dtype='int64', **kwargs)
layers.sums(input=[self.total, total], out=self.total, **kwargs)
layers.sums(input=[self.correct, correct], out=self.correct, **kwargs)
self.metrics.append(acc)
def __init__(self, input, label, k=1, **kwargs):
super(Accuracy, self).__init__("accuracy", **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 = self.create_state(dtype='int64', shape=[1], suffix='total')
self.correct = self.create_state(
dtype='int64', shape=[1], suffix='correct')
kwargs = {'main_program': main_program}
total = self.helper.create_tmp_variable(dtype='int')
correct = self.helper.create_tmp_variable(dtype='int')
acc = layers.accuracy(
input=input,
label=label,
k=k,
total=total,
correct=correct,
**kwargs)
total = layers.cast(x=total, dtype='int64', **kwargs)
correct = layers.cast(x=correct, dtype='int64', **kwargs)
layers.sums(input=[self.total, total], out=self.total, **kwargs)
layers.sums(input=[self.correct, correct], out=self.correct, **kwargs)
self.metrics.append(acc)
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 __init__(
self,
input,
label,
chunk_scheme,
num_chunk_types,
excluded_chunk_types=None, ):
super(ChunkEvaluator, self).__init__("chunk_eval")
main_program = self.helper.main_program
if main_program.current_block().idx != 0:
raise ValueError("You can only invoke Evaluator in root block")
self.num_infer_chunks = self.create_state(
dtype='int64', shape=[1], suffix='num_infer_chunks')
self.num_label_chunks = self.create_state(
dtype='int64', shape=[1], suffix='num_label_chunks')
self.num_correct_chunks = self.create_state(
dtype='int64', shape=[1], suffix='num_correct_chunks')
precision, recall, f1_score, num_infer_chunks, num_label_chunks, num_correct_chunks = layers.chunk_eval(
input=input,
label=label,
chunk_scheme=chunk_scheme,
num_chunk_types=num_chunk_types,
excluded_chunk_types=excluded_chunk_types, )
layers.sums(
input=[self.num_infer_chunks, num_infer_chunks],
out=self.num_infer_chunks)
layers.sums(
input=[self.num_label_chunks, num_label_chunks],
out=self.num_label_chunks)
layers.sums(
input=[self.num_correct_chunks, num_correct_chunks],
out=self.num_correct_chunks)
self.metrics.extend([precision, recall, f1_score])
def create_operators(self, param, grad):
group_scale_name = self.group_name + "_scale"
if group_scale_name not in self.context:
group_norm_var = layers.sums(input=self.context[self.group_name])
layers.sqrt(x=group_norm_var, out=group_norm_var)
clip_var = self.context[self.group_name + "_clip"]
group_scale_var = layers.elementwise_div(x=clip_var,
y=layers.elementwise_max(
x=clip_var,
y=group_norm_var))
assert group_scale_var.shape == (1L, )
self.context[group_scale_name] = group_scale_var
new_grad = layers.elementwise_mul(x=grad,
y=self.context[group_scale_name])
return param, new_grad
def create_operators(self, param, grad):
group_scale_name = self.group_name + "_scale"
if group_scale_name not in self.context:
group_norm_var = layers.sums(input=self.context[self.group_name])
layers.sqrt(x=group_norm_var, out=group_norm_var)
clip_var = self.context[self.group_name + "_clip"]
group_scale_var = layers.elementwise_div(
x=clip_var,
y=layers.elementwise_max(
x=clip_var, y=group_norm_var))
assert group_scale_var.shape == (1L, )
self.context[group_scale_name] = group_scale_var
new_grad = layers.elementwise_mul(
x=grad, y=self.context[group_scale_name])
return param, new_grad