-
Notifications
You must be signed in to change notification settings - Fork 28.5k
/
Copy pathtest_tokenization_t5.py
196 lines (165 loc) · 7.15 KB
/
test_tokenization_t5.py
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
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
# coding=utf-8
# Copyright 2018 Google T5 Authors and HuggingFace Inc. team.
#
# 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.
import os
import unittest
from transformers import BatchEncoding
from transformers.file_utils import cached_property
from transformers.testing_utils import _torch_available
from transformers.tokenization_t5 import T5Tokenizer
from transformers.tokenization_xlnet import SPIECE_UNDERLINE
from .test_tokenization_common import TokenizerTesterMixin
SAMPLE_VOCAB = os.path.join(os.path.dirname(os.path.abspath(__file__)), "fixtures/test_sentencepiece.model")
FRAMEWORK = "pt" if _torch_available else "tf"
class T5TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
tokenizer_class = T5Tokenizer
def setUp(self):
super().setUp()
# We have a SentencePiece fixture for testing
tokenizer = T5Tokenizer(SAMPLE_VOCAB)
tokenizer.save_pretrained(self.tmpdirname)
def test_full_tokenizer(self):
tokenizer = T5Tokenizer(SAMPLE_VOCAB)
tokens = tokenizer.tokenize("This is a test")
self.assertListEqual(tokens, ["▁This", "▁is", "▁a", "▁t", "est"])
self.assertListEqual(tokenizer.convert_tokens_to_ids(tokens), [285, 46, 10, 170, 382])
tokens = tokenizer.tokenize("I was born in 92000, and this is falsé.")
self.assertListEqual(
tokens,
[
SPIECE_UNDERLINE + "I",
SPIECE_UNDERLINE + "was",
SPIECE_UNDERLINE + "b",
"or",
"n",
SPIECE_UNDERLINE + "in",
SPIECE_UNDERLINE + "",
"9",
"2",
"0",
"0",
"0",
",",
SPIECE_UNDERLINE + "and",
SPIECE_UNDERLINE + "this",
SPIECE_UNDERLINE + "is",
SPIECE_UNDERLINE + "f",
"al",
"s",
"é",
".",
],
)
ids = tokenizer.convert_tokens_to_ids(tokens)
self.assertListEqual(ids, [8, 21, 84, 55, 24, 19, 7, 0, 602, 347, 347, 347, 3, 12, 66, 46, 72, 80, 6, 0, 4])
back_tokens = tokenizer.convert_ids_to_tokens(ids)
self.assertListEqual(
back_tokens,
[
SPIECE_UNDERLINE + "I",
SPIECE_UNDERLINE + "was",
SPIECE_UNDERLINE + "b",
"or",
"n",
SPIECE_UNDERLINE + "in",
SPIECE_UNDERLINE + "",
"<unk>",
"2",
"0",
"0",
"0",
",",
SPIECE_UNDERLINE + "and",
SPIECE_UNDERLINE + "this",
SPIECE_UNDERLINE + "is",
SPIECE_UNDERLINE + "f",
"al",
"s",
"<unk>",
".",
],
)
@cached_property
def t5_base_tokenizer(self):
return T5Tokenizer.from_pretrained("t5-base")
def test_eos_treatment(self):
tokenizer = self.t5_base_tokenizer
batch_with_eos_added = tokenizer(["hi</s>", "I went to the gym</s>", "</s>"])
batch_without_eos_added = tokenizer(["hi", "I went to the gym", ""])
self.assertListEqual(batch_with_eos_added["input_ids"], batch_without_eos_added["input_ids"])
def test_prepare_seq2seq_batch(self):
tokenizer = self.t5_base_tokenizer
src_text = ["A long paragraph for summrization.", "Another paragraph for summrization."]
tgt_text = [
"Summary of the text.",
"Another summary.",
]
expected_src_tokens = [71, 307, 8986, 21, 4505, 51, 52, 1707, 5, tokenizer.eos_token_id]
batch = tokenizer.prepare_seq2seq_batch(
src_text,
tgt_texts=tgt_text,
return_tensors=FRAMEWORK,
)
self.assertIsInstance(batch, BatchEncoding)
result = list(batch.input_ids.numpy()[0])
self.assertListEqual(expected_src_tokens, result)
self.assertEqual((2, 10), batch.input_ids.shape)
self.assertEqual((2, 10), batch.attention_mask.shape)
# Test that special tokens are reset
self.assertEqual(tokenizer.prefix_tokens, [])
def test_empty_target_text(self):
tokenizer = self.t5_base_tokenizer
src_text = ["A long paragraph for summrization.", "Another paragraph for summrization."]
batch = tokenizer.prepare_seq2seq_batch(src_text, return_tensors=FRAMEWORK)
# check if input_ids are returned and no decoder_input_ids
self.assertIn("input_ids", batch)
self.assertIn("attention_mask", batch)
self.assertNotIn("decoder_input_ids", batch)
self.assertNotIn("decoder_attention_mask", batch)
def test_max_target_length(self):
tokenizer = self.t5_base_tokenizer
src_text = ["A long paragraph for summrization.", "Another paragraph for summrization."]
tgt_text = [
"Summary of the text.",
"Another summary.",
]
batch = tokenizer.prepare_seq2seq_batch(
src_text, tgt_texts=tgt_text, max_target_length=32, padding="max_length", return_tensors=FRAMEWORK
)
self.assertEqual(32, batch["decoder_input_ids"].shape[1])
self.assertEqual(32, batch["decoder_attention_mask"].shape[1])
# test None max_target_length
batch = tokenizer.prepare_seq2seq_batch(
src_text, tgt_texts=tgt_text, max_length=32, padding="max_length", return_tensors=FRAMEWORK
)
self.assertEqual(32, batch["decoder_input_ids"].shape[1])
self.assertEqual(32, batch["decoder_attention_mask"].shape[1])
def test_outputs_not_longer_than_maxlen(self):
tokenizer = self.t5_base_tokenizer
batch = tokenizer.prepare_seq2seq_batch(
["I am a small frog" * 1000, "I am a small frog"], return_tensors=FRAMEWORK
)
self.assertIsInstance(batch, BatchEncoding)
self.assertEqual(batch.input_ids.shape, (2, 512))
def test_eos_in_input(self):
tokenizer = self.t5_base_tokenizer
src_text = ["A long paragraph for summrization. </s>"]
tgt_text = ["Summary of the text. </s>"]
expected_src_tokens = [71, 307, 8986, 21, 4505, 51, 52, 1707, 5, 1]
expected_tgt_tokens = [0, 20698, 13, 8, 1499, 5, 1]
batch = tokenizer.prepare_seq2seq_batch(src_text, tgt_texts=tgt_text, return_tensors=FRAMEWORK)
src_ids = list(batch.input_ids.numpy()[0])
tgt_ids = list(batch.decoder_input_ids.numpy()[0])
self.assertEqual(expected_src_tokens, src_ids)
self.assertEqual(expected_tgt_tokens, tgt_ids)