SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Apply ruff flake8-comprehensions (#21694)

Browse Source
This commit is contained in:
Aaron Gokaslan
2023-02-22 03:14:54 -05:00
committed by GitHub
parent df06fb1f0b
commit 5e8c8eb5ba
230 changed files with 971 additions and 955 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/models/bart/test_modeling_bart.py
View File

@@ -939,7 +939,7 @@ class BartModelIntegrationTests(unittest.TestCase):
def test_xsum_config_generation_params(self):
config = BartConfig.from_pretrained("facebook/bart-large-xsum")
expected_params = dict(num_beams=6, do_sample=False, early_stopping=True, length_penalty=1.0)
expected_params = {"num_beams": 6, "do_sample": False, "early_stopping": True, "length_penalty": 1.0}
config_params = {k: getattr(config, k, "MISSING") for k, v in expected_params.items()}
self.assertDictEqual(expected_params, config_params)

4
tests/models/blenderbot/test_modeling_blenderbot.py
View File

@@ -299,8 +299,8 @@ class Blenderbot3BIntegrationTests(unittest.TestCase):
@slow
def test_generation_from_short_input_same_as_parlai_3B(self):
FASTER_GEN_KWARGS = dict(num_beams=1, early_stopping=True, min_length=15, max_length=25)
TOK_DECODE_KW = dict(skip_special_tokens=True, clean_up_tokenization_spaces=True)
FASTER_GEN_KWARGS = {"num_beams": 1, "early_stopping": True, "min_length": 15, "max_length": 25}
TOK_DECODE_KW = {"skip_special_tokens": True, "clean_up_tokenization_spaces": True}
torch.cuda.empty_cache()
model = BlenderbotForConditionalGeneration.from_pretrained(self.ckpt).half().to(torch_device)

4
tests/models/blenderbot/test_modeling_flax_blenderbot.py
View File

@@ -402,8 +402,8 @@ class FlaxBlenderbotModelTest(FlaxModelTesterMixin, unittest.TestCase, FlaxGener
@unittest.skipUnless(jax_device != "cpu", "3B test too slow on CPU.")
@slow
def test_generation_from_short_input_same_as_parlai_3B(self):
FASTER_GEN_KWARGS = dict(num_beams=1, early_stopping=True, min_length=15, max_length=25)
TOK_DECODE_KW = dict(skip_special_tokens=True, clean_up_tokenization_spaces=True)
FASTER_GEN_KWARGS = {"num_beams": 1, "early_stopping": True, "min_length": 15, "max_length": 25}
TOK_DECODE_KW = {"skip_special_tokens": True, "clean_up_tokenization_spaces": True}
model = FlaxBlenderbotForConditionalGeneration.from_pretrained("facebook/blenderbot-3B", from_pt=True)
tokenizer = BlenderbotTokenizer.from_pretrained("facebook/blenderbot-3B")

2
tests/models/bloom/test_tokenization_bloom.py
View File

@@ -124,7 +124,7 @@ class BloomTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
input_text = list(sample_data.values())
output_tokens = list(map(tokenizer.encode, input_text))
predicted_text = list(map(lambda x: tokenizer.decode(x, clean_up_tokenization_spaces=False), output_tokens))
predicted_text = [tokenizer.decode(x, clean_up_tokenization_spaces=False) for x in output_tokens]
self.assertListEqual(predicted_text, input_text)
def test_pretrained_model_lists(self):

4
tests/models/clip/test_modeling_tf_clip.py
View File

@@ -551,7 +551,7 @@ class TFCLIPModelTest(TFModelTesterMixin, unittest.TestCase):
if self.__class__.__name__ == "TFCLIPModelTest":
inputs_dict.pop("return_loss", None)
tf_main_layer_classes = set(
tf_main_layer_classes = {
module_member
for model_class in self.all_model_classes
for module in (import_module(model_class.__module__),)
@@ -563,7 +563,7 @@ class TFCLIPModelTest(TFModelTesterMixin, unittest.TestCase):
if isinstance(module_member, type)
and tf.keras.layers.Layer in module_member.__bases__
and getattr(module_member, "_keras_serializable", False)
)
}
for main_layer_class in tf_main_layer_classes:
# T5MainLayer needs an embed_tokens parameter when called without the inputs_embeds parameter
if "T5" in main_layer_class.__name__:

2
tests/models/data2vec/test_modeling_tf_data2vec_vision.py
View File

@@ -398,7 +398,7 @@ class TFData2VecVisionModelTest(TFModelTesterMixin, unittest.TestCase):
# The number of elements in the loss should be the same as the number of elements in the label
_, prepared_for_class = self.model_tester.prepare_config_and_inputs_for_keras_fit()
added_label = prepared_for_class[
sorted(list(prepared_for_class.keys() - inputs_dict.keys()), reverse=True)[0]
sorted(prepared_for_class.keys() - inputs_dict.keys(), reverse=True)[0]
]
loss_size = tf.size(added_label)

4
tests/models/groupvit/test_modeling_tf_groupvit.py
View File

@@ -628,7 +628,7 @@ class TFGroupViTModelTest(TFModelTesterMixin, unittest.TestCase):
if self.__class__.__name__ == "TFGroupViTModelTest":
inputs_dict.pop("return_loss", None)
tf_main_layer_classes = set(
tf_main_layer_classes = {
module_member
for model_class in self.all_model_classes
for module in (import_module(model_class.__module__),)
@@ -640,7 +640,7 @@ class TFGroupViTModelTest(TFModelTesterMixin, unittest.TestCase):
if isinstance(module_member, type)
and tf.keras.layers.Layer in module_member.__bases__
and getattr(module_member, "_keras_serializable", False)
)
}
for main_layer_class in tf_main_layer_classes:
# T5MainLayer needs an embed_tokens parameter when called without the inputs_embeds parameter
if "T5" in main_layer_class.__name__:

22
tests/models/jukebox/test_modeling_jukebox.py
View File

@@ -30,10 +30,10 @@ if is_torch_available():
class Jukebox1bModelTester(unittest.TestCase):
all_model_classes = (JukeboxModel,) if is_torch_available() else ()
model_id = "openai/jukebox-1b-lyrics"
metas = dict(
artist="Zac Brown Band",
genres="Country",
lyrics="""I met a traveller from an antique land,
metas = {
"artist": "Zac Brown Band",
"genres": "Country",
"lyrics": """I met a traveller from an antique land,
Who said "Two vast and trunkless legs of stone
Stand in the desert. . . . Near them, on the sand,
Half sunk a shattered visage lies, whose frown,
@@ -48,7 +48,7 @@ class Jukebox1bModelTester(unittest.TestCase):
Of that colossal Wreck, boundless and bare
The lone and level sands stretch far away
""",
)
}
# fmt: off
EXPECTED_OUTPUT_2 = [
1864, 1536, 1213, 1870, 1357, 1536, 519, 880, 1323, 789, 1082, 534,
@@ -180,7 +180,7 @@ class Jukebox1bModelTester(unittest.TestCase):
model = JukeboxModel.from_pretrained(self.model_id, min_duration=0).eval()
set_seed(0)
waveform = torch.rand((1, 5120, 1))
tokens = [i for i in self.prepare_inputs()]
tokens = list(self.prepare_inputs())
zs = [model.vqvae.encode(waveform, start_level=2, bs_chunks=waveform.shape[0])[0], None, None]
zs = model._sample(
@@ -220,10 +220,10 @@ class Jukebox1bModelTester(unittest.TestCase):
class Jukebox5bModelTester(unittest.TestCase):
all_model_classes = (JukeboxModel,) if is_torch_available() else ()
model_id = "openai/jukebox-5b-lyrics"
metas = dict(
artist="Zac Brown Band",
genres="Country",
lyrics="""I met a traveller from an antique land,
metas = {
"artist": "Zac Brown Band",
"genres": "Country",
"lyrics": """I met a traveller from an antique land,
Who said "Two vast and trunkless legs of stone
Stand in the desert. . . . Near them, on the sand,
Half sunk a shattered visage lies, whose frown,
@@ -238,7 +238,7 @@ class Jukebox5bModelTester(unittest.TestCase):
Of that colossal Wreck, boundless and bare
The lone and level sands stretch far away
""",
)
}
# fmt: off
EXPECTED_OUTPUT_2 = [

10
tests/models/jukebox/test_tokenization_jukebox.py
View File

@@ -21,10 +21,10 @@ from transformers.testing_utils import require_torch
class JukeboxTokenizationTest(unittest.TestCase):
tokenizer_class = JukeboxTokenizer
metas = dict(
artist="Zac Brown Band",
genres="Country",
lyrics="""I met a traveller from an antique land,
metas = {
"artist": "Zac Brown Band",
"genres": "Country",
"lyrics": """I met a traveller from an antique land,
Who said "Two vast and trunkless legs of stone
Stand in the desert. . . . Near them, on the sand,
Half sunk a shattered visage lies, whose frown,
@@ -39,7 +39,7 @@ class JukeboxTokenizationTest(unittest.TestCase):
Of that colossal Wreck, boundless and bare
The lone and level sands stretch far away
""",
)
}
@require_torch
def test_1b_lyrics_tokenizer(self):

18
tests/models/layoutlmv2/test_processor_layoutlmv2.py
View File

@@ -233,7 +233,7 @@ class LayoutLMv2ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids", "token_type_ids"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify image
@@ -253,7 +253,7 @@ class LayoutLMv2ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids", "token_type_ids"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify images
@@ -301,7 +301,7 @@ class LayoutLMv2ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids", "token_type_ids"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -340,7 +340,7 @@ class LayoutLMv2ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids", "labels", "token_type_ids"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -362,7 +362,7 @@ class LayoutLMv2ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids", "labels", "token_type_ids"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -403,7 +403,7 @@ class LayoutLMv2ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids", "token_type_ids"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -422,7 +422,7 @@ class LayoutLMv2ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids", "token_type_ids"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -456,7 +456,7 @@ class LayoutLMv2ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids", "token_type_ids"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -472,7 +472,7 @@ class LayoutLMv2ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids", "token_type_ids"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids

2
tests/models/layoutlmv3/test_modeling_tf_layoutlmv3.py
View File

@@ -320,7 +320,7 @@ class TFLayoutLMv3ModelTest(TFModelTesterMixin, unittest.TestCase):
# The number of elements in the loss should be the same as the number of elements in the label
prepared_for_class = self._prepare_for_class(inputs_dict.copy(), model_class, return_labels=True)
added_label = prepared_for_class[
sorted(list(prepared_for_class.keys() - inputs_dict.keys()), reverse=True)[0]
sorted(prepared_for_class.keys() - inputs_dict.keys(), reverse=True)[0]
]
expected_loss_size = added_label.shape.as_list()[:1]

18
tests/models/layoutlmv3/test_processor_layoutlmv3.py
View File

@@ -213,7 +213,7 @@ class LayoutLMv3ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "input_ids", "pixel_values"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify image
@@ -235,7 +235,7 @@ class LayoutLMv3ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "input_ids", "pixel_values"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify images
@@ -285,7 +285,7 @@ class LayoutLMv3ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "input_ids", "pixel_values"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -324,7 +324,7 @@ class LayoutLMv3ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "input_ids", "labels", "pixel_values"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -346,7 +346,7 @@ class LayoutLMv3ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "input_ids", "labels", "pixel_values"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -387,7 +387,7 @@ class LayoutLMv3ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "input_ids", "pixel_values"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -406,7 +406,7 @@ class LayoutLMv3ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "input_ids", "pixel_values"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -440,7 +440,7 @@ class LayoutLMv3ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "input_ids", "pixel_values"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -456,7 +456,7 @@ class LayoutLMv3ProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "input_ids", "pixel_values"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids

18
tests/models/layoutxlm/test_processor_layoutxlm.py
View File

@@ -228,7 +228,7 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify image
@@ -250,7 +250,7 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify images
@@ -300,7 +300,7 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -339,7 +339,7 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids", "labels"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -361,7 +361,7 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids", "labels"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -402,7 +402,7 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -421,7 +421,7 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -455,7 +455,7 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -471,7 +471,7 @@ class LayoutXLMProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "bbox", "image", "input_ids"]
actual_keys = sorted(list(input_processor.keys()))
actual_keys = sorted(input_processor.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids

18
tests/models/markuplm/test_processor_markuplm.py
View File

@@ -204,7 +204,7 @@ class MarkupLMProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "input_ids", "token_type_ids", "xpath_subs_seq", "xpath_tags_seq"]
actual_keys = sorted(list(inputs.keys()))
actual_keys = sorted(inputs.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -216,7 +216,7 @@ class MarkupLMProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "input_ids", "token_type_ids", "xpath_subs_seq", "xpath_tags_seq"]
actual_keys = sorted(list(inputs.keys()))
actual_keys = sorted(inputs.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -260,7 +260,7 @@ class MarkupLMProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "input_ids", "token_type_ids", "xpath_subs_seq", "xpath_tags_seq"]
actual_keys = sorted(list(inputs.keys()))
actual_keys = sorted(inputs.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -294,7 +294,7 @@ class MarkupLMProcessorIntegrationTests(unittest.TestCase):
"xpath_subs_seq",
"xpath_tags_seq",
]
actual_keys = sorted(list(inputs.keys()))
actual_keys = sorted(inputs.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -331,7 +331,7 @@ class MarkupLMProcessorIntegrationTests(unittest.TestCase):
"xpath_subs_seq",
"xpath_tags_seq",
]
actual_keys = sorted(list(inputs.keys()))
actual_keys = sorted(inputs.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -367,7 +367,7 @@ class MarkupLMProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "input_ids", "token_type_ids", "xpath_subs_seq", "xpath_tags_seq"]
actual_keys = sorted(list(inputs.keys()))
actual_keys = sorted(inputs.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -390,7 +390,7 @@ class MarkupLMProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "input_ids", "token_type_ids", "xpath_subs_seq", "xpath_tags_seq"]
actual_keys = sorted(list(inputs.keys()))
actual_keys = sorted(inputs.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -425,7 +425,7 @@ class MarkupLMProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "input_ids", "token_type_ids", "xpath_subs_seq", "xpath_tags_seq"]
actual_keys = sorted(list(inputs.keys()))
actual_keys = sorted(inputs.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids
@@ -444,7 +444,7 @@ class MarkupLMProcessorIntegrationTests(unittest.TestCase):
# verify keys
expected_keys = ["attention_mask", "input_ids", "token_type_ids", "xpath_subs_seq", "xpath_tags_seq"]
actual_keys = sorted(list(inputs.keys()))
actual_keys = sorted(inputs.keys())
self.assertListEqual(actual_keys, expected_keys)
# verify input_ids

2
tests/models/mobilevit/test_modeling_tf_mobilevit.py
View File

@@ -295,7 +295,7 @@ class MobileViTModelTest(TFModelTesterMixin, unittest.TestCase):
# The number of elements in the loss should be the same as the number of elements in the label
prepared_for_class = self._prepare_for_class(inputs_dict.copy(), model_class, return_labels=True)
added_label = prepared_for_class[
sorted(list(prepared_for_class.keys() - inputs_dict.keys()), reverse=True)[0]
sorted(prepared_for_class.keys() - inputs_dict.keys(), reverse=True)[0]
]
expected_loss_size = added_label.shape.as_list()[:1]

10
tests/models/perceiver/test_modeling_perceiver.py
View File

@@ -166,9 +166,11 @@ class PerceiverModelTester:
audio = torch.randn(
(self.batch_size, self.num_frames * self.audio_samples_per_frame, 1), device=torch_device
)
inputs = dict(
image=images, audio=audio, label=torch.zeros((self.batch_size, self.num_labels), device=torch_device)
)
inputs = {
"image": images,
"audio": audio,
"label": torch.zeros((self.batch_size, self.num_labels), device=torch_device),
}
else:
raise ValueError(f"Model class {model_class} not supported")
@@ -734,7 +736,7 @@ class PerceiverModelTest(ModelTesterMixin, unittest.TestCase):
continue
config, inputs, input_mask, _, _ = self.model_tester.prepare_config_and_inputs(model_class=model_class)
inputs_dict = dict(inputs=inputs, attention_mask=input_mask)
inputs_dict = {"inputs": inputs, "attention_mask": input_mask}
for problem_type in problem_types:
with self.subTest(msg=f"Testing {model_class} with {problem_type['title']}"):

4
tests/models/roc_bert/test_tokenization_roc_bert.py
View File

@@ -44,8 +44,8 @@ class BertTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
super().setUp()
vocab_tokens = ["[UNK]", "[CLS]", "[SEP]", "[PAD]", "[MASK]", "你", "好", "是", "谁", "a", "b", "c", "d"]
word_shape = dict()
word_pronunciation = dict()
word_shape = {}
word_pronunciation = {}
for i, value in enumerate(vocab_tokens):
word_shape[value] = i
word_pronunciation[value] = i

4
tests/models/segformer/test_modeling_tf_segformer.py
View File

@@ -362,9 +362,7 @@ class TFSegformerModelTest(TFModelTesterMixin, unittest.TestCase):
_, prepared_for_class = self.model_tester.prepare_config_and_inputs_for_keras_fit(
for_segmentation=for_segmentation
)
added_label = prepared_for_class[
sorted(list(prepared_for_class.keys() - inputs_dict.keys()), reverse=True)[0]
]
added_label = prepared_for_class[sorted(prepared_for_class.keys() - inputs_dict.keys(), reverse=True)[0]]
loss_size = tf.size(added_label)
# Test that model correctly compute the loss with kwargs

2
tests/models/speecht5/test_feature_extraction_speecht5.py
View File

@@ -372,7 +372,7 @@ class SpeechT5FeatureExtractionTest(SequenceFeatureExtractionTestMixin, unittest
)
self.assertIn("attention_mask", processed_pad)
self.assertListEqual(
list(processed_pad.attention_mask.shape), list((processed_pad[input_name].shape[0], max_length))
list(processed_pad.attention_mask.shape), [processed_pad[input_name].shape[0], max_length]
)
self.assertListEqual(
processed_pad.attention_mask[:, :max_length].sum(-1).tolist(), [max_length for x in speech_inputs]

4
tests/models/t5/test_tokenization_t5.py
View File

@@ -387,7 +387,7 @@ class T5TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
def test_get_sentinel_token_ids(self):
tokenizer = T5Tokenizer(SAMPLE_VOCAB, extra_ids=10)
self.assertListEqual(sorted(tokenizer.get_sentinel_token_ids()), sorted([i for i in range(1000, 1010)]))
self.assertListEqual(sorted(tokenizer.get_sentinel_token_ids()), sorted(range(1000, 1010)))
def test_get_sentinel_tokens_for_fasttokenizer(self):
tokenizer = T5TokenizerFast(SAMPLE_VOCAB, extra_ids=10)
@@ -398,4 +398,4 @@ class T5TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
def test_get_sentinel_token_ids_for_fasttokenizer(self):
tokenizer = T5TokenizerFast(SAMPLE_VOCAB, extra_ids=10)
self.assertListEqual(sorted(tokenizer.get_sentinel_token_ids()), sorted([i for i in range(1000, 1010)]))
self.assertListEqual(sorted(tokenizer.get_sentinel_token_ids()), sorted(range(1000, 1010)))

2
tests/models/transfo_xl/test_modeling_transfo_xl.py
View File

@@ -347,7 +347,7 @@ class TransfoXLModelTest(ModelTesterMixin, GenerationTesterMixin, unittest.TestC
# Retrieve the cutoffs and copy them
copied_cutoffs = copy.copy(model_embed.cutoffs)
test_layers = [x for x in range(config.div_val)]
test_layers = list(range(config.div_val))
for layer in test_layers:
# Check that resizing the token embeddings with a larger vocab size increases the model's vocab size
model_embed = model.resize_token_embeddings(model_vocab_size + 10, layer)

4
tests/models/tvlt/test_modeling_tvlt.py
View File

@@ -581,7 +581,7 @@ class TvltModelIntegrationTest(unittest.TestCase):
audio = prepare_audio()
video_inputs = image_processor(video, return_tensors="pt").to(torch_device)
audio_inputs = audio_feature_extractor(audio, return_tensors="pt").to(torch_device)
inputs = dict()
inputs = {}
inputs.update(video_inputs)
inputs.update(audio_inputs)
@@ -606,7 +606,7 @@ class TvltModelIntegrationTest(unittest.TestCase):
video_mixed_inputs = image_processor(video_mixed, is_mixed=True, return_tensors="pt").to(torch_device)
audio_inputs = audio_feature_extractor(audio, return_tensors="pt", mask_audio=True).to(torch_device)
labels = torch.tensor([[0.0]], device=torch_device)
inputs = dict()
inputs = {}
inputs.update(video_inputs)
inputs.update(video_mixed_inputs)
inputs.update(audio_inputs)

4
tests/models/vit_mae/test_modeling_tf_vit_mae.py
View File

@@ -333,7 +333,7 @@ class TFViTMAEModelTest(TFModelTesterMixin, unittest.TestCase):
config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common()
tf_main_layer_classes = set(
tf_main_layer_classes = {
module_member
for model_class in self.all_model_classes
for module in (import_module(model_class.__module__),)
@@ -345,7 +345,7 @@ class TFViTMAEModelTest(TFModelTesterMixin, unittest.TestCase):
if isinstance(module_member, type)
and tf.keras.layers.Layer in module_member.__bases__
and getattr(module_member, "_keras_serializable", False)
)
}
num_patches = int((config.image_size // config.patch_size) ** 2)
noise = np.random.uniform(size=(self.model_tester.batch_size, num_patches))

4
tests/models/wav2vec2/test_tokenization_wav2vec2.py
View File

@@ -231,7 +231,7 @@ class Wav2Vec2TokenizerTest(unittest.TestCase):
tokenizer_files = tokenizer.save_pretrained(tmpdirname2)
self.assertSequenceEqual(
sorted(tuple(VOCAB_FILES_NAMES.values()) + ("special_tokens_map.json", "added_tokens.json")),
sorted(tuple(x.split(os.path.sep)[-1] for x in tokenizer_files)),
sorted(x.split(os.path.sep)[-1] for x in tokenizer_files),
)
# Checks everything loads correctly in the same way
@@ -456,7 +456,7 @@ class Wav2Vec2CTCTokenizerTest(TokenizerTesterMixin, unittest.TestCase):
def test_special_characters_in_vocab(self):
sent = "ʈʰ æ æ̃ ˧ kʰ"
vocab_dict = {k: v for v, k in enumerate({phoneme for phoneme in sent.split()})}
vocab_dict = {k: v for v, k in enumerate(set(sent.split()))}
vocab_file = os.path.join(self.tmpdirname, "vocab_special.json")
with open(vocab_file, "w") as f:

6
tests/models/wav2vec2_with_lm/test_processor_wav2vec2_with_lm.py
View File

@@ -215,7 +215,7 @@ class Wav2Vec2ProcessorWithLMTest(unittest.TestCase):
with get_context(pool_context).Pool() as pool:
decoded_processor = processor.batch_decode(logits, pool)
logits_list = [array for array in logits]
logits_list = list(logits)
with get_context("fork").Pool() as p:
decoded_beams = decoder.decode_beams_batch(p, logits_list)
@@ -252,7 +252,7 @@ class Wav2Vec2ProcessorWithLMTest(unittest.TestCase):
)
decoded_processor = decoded_processor_out.text
logits_list = [array for array in logits]
logits_list = list(logits)
with get_context("fork").Pool() as pool:
decoded_decoder_out = decoder.decode_beams_batch(
@@ -299,7 +299,7 @@ class Wav2Vec2ProcessorWithLMTest(unittest.TestCase):
)
decoded_processor = decoded_processor_out.text
logits_list = [array for array in logits]
logits_list = list(logits)
decoder.reset_params(
alpha=alpha,
beta=beta,

2
tests/models/xlnet/test_modeling_tf_xlnet.py
View File

@@ -400,7 +400,7 @@ class TFXLNetModelTest(TFModelTesterMixin, unittest.TestCase):
# The number of elements in the loss should be the same as the number of elements in the label
prepared_for_class = self._prepare_for_class(inputs_dict.copy(), model_class, return_labels=True)
added_label = prepared_for_class[
sorted(list(prepared_for_class.keys() - inputs_dict.keys()), reverse=True)[0]
sorted(prepared_for_class.keys() - inputs_dict.keys(), reverse=True)[0]
]
expected_loss_size = added_label.shape.as_list()[:1]