Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
File size: 12,341 Bytes
75466df |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 |
import unittest
from typing import Iterable, List, Optional
from transformers import pipeline
from transformers.pipelines import Pipeline
from .utils import require_tf, require_torch
QA_FINETUNED_MODELS = {
("bert-base-uncased", "bert-large-uncased-whole-word-masking-finetuned-squad", None),
("bert-base-cased", "bert-large-cased-whole-word-masking-finetuned-squad", None),
("bert-base-uncased", "distilbert-base-uncased-distilled-squad", None),
}
TF_QA_FINETUNED_MODELS = {
("bert-base-uncased", "bert-large-uncased-whole-word-masking-finetuned-squad", None),
("bert-base-cased", "bert-large-cased-whole-word-masking-finetuned-squad", None),
("bert-base-uncased", "distilbert-base-uncased-distilled-squad", None),
}
TF_NER_FINETUNED_MODELS = {
(
"bert-base-cased",
"dbmdz/bert-large-cased-finetuned-conll03-english",
"dbmdz/bert-large-cased-finetuned-conll03-english",
)
}
NER_FINETUNED_MODELS = {
(
"bert-base-cased",
"dbmdz/bert-large-cased-finetuned-conll03-english",
"dbmdz/bert-large-cased-finetuned-conll03-english",
)
}
FEATURE_EXTRACT_FINETUNED_MODELS = {
("bert-base-cased", "bert-base-cased", None),
# ('xlnet-base-cased', 'xlnet-base-cased', None), # Disabled for now as it crash for TF2
("distilbert-base-uncased", "distilbert-base-uncased", None),
}
TF_FEATURE_EXTRACT_FINETUNED_MODELS = {
("bert-base-cased", "bert-base-cased", None),
# ('xlnet-base-cased', 'xlnet-base-cased', None), # Disabled for now as it crash for TF2
("distilbert-base-uncased", "distilbert-base-uncased", None),
}
TF_TEXT_CLASSIF_FINETUNED_MODELS = {
(
"bert-base-uncased",
"distilbert-base-uncased-finetuned-sst-2-english",
"distilbert-base-uncased-finetuned-sst-2-english",
)
}
TEXT_CLASSIF_FINETUNED_MODELS = {
(
"bert-base-uncased",
"distilbert-base-uncased-finetuned-sst-2-english",
"distilbert-base-uncased-finetuned-sst-2-english",
)
}
FILL_MASK_FINETUNED_MODELS = {
("distilroberta-base", "distilroberta-base", None),
}
TF_FILL_MASK_FINETUNED_MODELS = {
("distilroberta-base", "distilroberta-base", None),
}
class MonoColumnInputTestCase(unittest.TestCase):
def _test_mono_column_pipeline(
self,
nlp: Pipeline,
valid_inputs: List,
invalid_inputs: List,
output_keys: Iterable[str],
expected_multi_result: Optional[List] = None,
expected_check_keys: Optional[List[str]] = None,
):
self.assertIsNotNone(nlp)
mono_result = nlp(valid_inputs[0])
self.assertIsInstance(mono_result, list)
self.assertIsInstance(mono_result[0], (dict, list))
if isinstance(mono_result[0], list):
mono_result = mono_result[0]
for key in output_keys:
self.assertIn(key, mono_result[0])
multi_result = nlp(valid_inputs)
self.assertIsInstance(multi_result, list)
self.assertIsInstance(multi_result[0], (dict, list))
if expected_multi_result is not None:
for result, expect in zip(multi_result, expected_multi_result):
for key in expected_check_keys or []:
self.assertEqual(
set([o[key] for o in result]), set([o[key] for o in expect]),
)
if isinstance(multi_result[0], list):
multi_result = multi_result[0]
for result in multi_result:
for key in output_keys:
self.assertIn(key, result)
self.assertRaises(Exception, nlp, invalid_inputs)
@require_torch
def test_ner(self):
mandatory_keys = {"entity", "word", "score"}
valid_inputs = ["HuggingFace is solving NLP one commit at a time.", "HuggingFace is based in New-York & Paris"]
invalid_inputs = [None]
for tokenizer, model, config in NER_FINETUNED_MODELS:
nlp = pipeline(task="ner", model=model, config=config, tokenizer=tokenizer)
self._test_mono_column_pipeline(nlp, valid_inputs, invalid_inputs, mandatory_keys)
@require_tf
def test_tf_ner(self):
mandatory_keys = {"entity", "word", "score"}
valid_inputs = ["HuggingFace is solving NLP one commit at a time.", "HuggingFace is based in New-York & Paris"]
invalid_inputs = [None]
for tokenizer, model, config in TF_NER_FINETUNED_MODELS:
nlp = pipeline(task="ner", model=model, config=config, tokenizer=tokenizer)
self._test_mono_column_pipeline(nlp, valid_inputs, invalid_inputs, mandatory_keys)
@require_torch
def test_sentiment_analysis(self):
mandatory_keys = {"label", "score"}
valid_inputs = ["HuggingFace is solving NLP one commit at a time.", "HuggingFace is based in New-York & Paris"]
invalid_inputs = [None]
for tokenizer, model, config in TEXT_CLASSIF_FINETUNED_MODELS:
nlp = pipeline(task="sentiment-analysis", model=model, config=config, tokenizer=tokenizer)
self._test_mono_column_pipeline(nlp, valid_inputs, invalid_inputs, mandatory_keys)
@require_tf
def test_tf_sentiment_analysis(self):
mandatory_keys = {"label", "score"}
valid_inputs = ["HuggingFace is solving NLP one commit at a time.", "HuggingFace is based in New-York & Paris"]
invalid_inputs = [None]
for tokenizer, model, config in TF_TEXT_CLASSIF_FINETUNED_MODELS:
nlp = pipeline(task="sentiment-analysis", model=model, config=config, tokenizer=tokenizer)
self._test_mono_column_pipeline(nlp, valid_inputs, invalid_inputs, mandatory_keys)
@require_torch
def test_feature_extraction(self):
valid_inputs = ["HuggingFace is solving NLP one commit at a time.", "HuggingFace is based in New-York & Paris"]
invalid_inputs = [None]
for tokenizer, model, config in FEATURE_EXTRACT_FINETUNED_MODELS:
nlp = pipeline(task="feature-extraction", model=model, config=config, tokenizer=tokenizer)
self._test_mono_column_pipeline(nlp, valid_inputs, invalid_inputs, {})
@require_tf
def test_tf_feature_extraction(self):
valid_inputs = ["HuggingFace is solving NLP one commit at a time.", "HuggingFace is based in New-York & Paris"]
invalid_inputs = [None]
for tokenizer, model, config in TF_FEATURE_EXTRACT_FINETUNED_MODELS:
nlp = pipeline(task="feature-extraction", model=model, config=config, tokenizer=tokenizer)
self._test_mono_column_pipeline(nlp, valid_inputs, invalid_inputs, {})
@require_torch
def test_fill_mask(self):
mandatory_keys = {"sequence", "score", "token"}
valid_inputs = [
"My name is <mask>",
"The largest city in France is <mask>",
]
invalid_inputs = [None]
expected_multi_result = [
[
{"score": 0.008698059245944023, "sequence": "<s>My name is John</s>", "token": 610},
{"score": 0.007750614080578089, "sequence": "<s>My name is Chris</s>", "token": 1573},
],
[
{"score": 0.2721288502216339, "sequence": "<s>The largest city in France is Paris</s>", "token": 2201},
{
"score": 0.19764970242977142,
"sequence": "<s>The largest city in France is Lyon</s>",
"token": 12790,
},
],
]
for tokenizer, model, config in FILL_MASK_FINETUNED_MODELS:
nlp = pipeline(task="fill-mask", model=model, config=config, tokenizer=tokenizer, topk=2)
self._test_mono_column_pipeline(
nlp,
valid_inputs,
invalid_inputs,
mandatory_keys,
expected_multi_result=expected_multi_result,
expected_check_keys=["sequence"],
)
@require_tf
def test_tf_fill_mask(self):
mandatory_keys = {"sequence", "score", "token"}
valid_inputs = [
"My name is <mask>",
"The largest city in France is <mask>",
]
invalid_inputs = [None]
expected_multi_result = [
[
{"score": 0.008698059245944023, "sequence": "<s>My name is John</s>", "token": 610},
{"score": 0.007750614080578089, "sequence": "<s>My name is Chris</s>", "token": 1573},
],
[
{"score": 0.2721288502216339, "sequence": "<s>The largest city in France is Paris</s>", "token": 2201},
{
"score": 0.19764970242977142,
"sequence": "<s>The largest city in France is Lyon</s>",
"token": 12790,
},
],
]
for tokenizer, model, config in TF_FILL_MASK_FINETUNED_MODELS:
nlp = pipeline(task="fill-mask", model=model, config=config, tokenizer=tokenizer, topk=2)
self._test_mono_column_pipeline(
nlp,
valid_inputs,
invalid_inputs,
mandatory_keys,
expected_multi_result=expected_multi_result,
expected_check_keys=["sequence"],
)
class MultiColumnInputTestCase(unittest.TestCase):
def _test_multicolumn_pipeline(self, nlp, valid_inputs: list, invalid_inputs: list, output_keys: Iterable[str]):
self.assertIsNotNone(nlp)
mono_result = nlp(valid_inputs[0])
self.assertIsInstance(mono_result, dict)
for key in output_keys:
self.assertIn(key, mono_result)
multi_result = nlp(valid_inputs)
self.assertIsInstance(multi_result, list)
self.assertIsInstance(multi_result[0], dict)
for result in multi_result:
for key in output_keys:
self.assertIn(key, result)
self.assertRaises(Exception, nlp, invalid_inputs[0])
self.assertRaises(Exception, nlp, invalid_inputs)
@require_torch
def test_question_answering(self):
mandatory_output_keys = {"score", "answer", "start", "end"}
valid_samples = [
{"question": "Where was HuggingFace founded ?", "context": "HuggingFace was founded in Paris."},
{
"question": "In what field is HuggingFace working ?",
"context": "HuggingFace is a startup based in New-York founded in Paris which is trying to solve NLP.",
},
]
invalid_samples = [
{"question": "", "context": "This is a test to try empty question edge case"},
{"question": None, "context": "This is a test to try empty question edge case"},
{"question": "What is does with empty context ?", "context": ""},
{"question": "What is does with empty context ?", "context": None},
]
for tokenizer, model, config in QA_FINETUNED_MODELS:
nlp = pipeline(task="question-answering", model=model, config=config, tokenizer=tokenizer)
self._test_multicolumn_pipeline(nlp, valid_samples, invalid_samples, mandatory_output_keys)
@require_tf
def test_tf_question_answering(self):
mandatory_output_keys = {"score", "answer", "start", "end"}
valid_samples = [
{"question": "Where was HuggingFace founded ?", "context": "HuggingFace was founded in Paris."},
{
"question": "In what field is HuggingFace working ?",
"context": "HuggingFace is a startup based in New-York founded in Paris which is trying to solve NLP.",
},
]
invalid_samples = [
{"question": "", "context": "This is a test to try empty question edge case"},
{"question": None, "context": "This is a test to try empty question edge case"},
{"question": "What is does with empty context ?", "context": ""},
{"question": "What is does with empty context ?", "context": None},
]
for tokenizer, model, config in TF_QA_FINETUNED_MODELS:
nlp = pipeline(task="question-answering", model=model, config=config, tokenizer=tokenizer)
self._test_multicolumn_pipeline(nlp, valid_samples, invalid_samples, mandatory_output_keys)
|