File size: 2,402 Bytes
23bd7af |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
# coding=utf-8
# Copyright 2018 The Google AI Language Team Authors, Facebook AI Research authors and The HuggingFace Inc. team.
# Copyright (c) 2018, NVIDIA CORPORATION. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
## from huggingface beam search
class BeamHypotheses(object):
def __init__(self, num_beams, length_penalty=1.0, early_stopping=False):
"""
Initialize n-best list of hypotheses.
"""
self.length_penalty = length_penalty
self.early_stopping = early_stopping
self.num_beams = num_beams
self.beams = []
self.worst_score = 1e9
def __len__(self):
"""
Number of hypotheses in the list.
"""
return len(self.beams)
def add(self, hyp, sum_logprobs, length):
"""
Add a new hypothesis to the list.
"""
score = sum_logprobs / length ** self.length_penalty
if len(self) < self.num_beams or score > self.worst_score:
self.beams.append((score, hyp))
if len(self) > self.num_beams:
sorted_scores = sorted([(s, idx) for idx, (s, _) in enumerate(self.beams)])
del self.beams[sorted_scores[0][1]]
self.worst_score = sorted_scores[1][0]
else:
self.worst_score = min(score, self.worst_score)
def is_done(self, best_sum_logprobs, cur_len):
"""
If there are enough hypotheses and that none of the hypotheses being generated
can become better than the worst one in the heap, then we are done with this sentence.
"""
if len(self) < self.num_beams:
return False
elif self.early_stopping:
return True
else:
cur_score = best_sum_logprobs / cur_len ** self.length_penalty
ret = self.worst_score >= cur_score
return ret
|