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

Move test model folders (#17034)

Browse Source 
* move test model folders (TODO: fix imports and others)

* fix (potentially partially) imports (in model test modules)

* fix (potentially partially) imports (in tokenization test modules)

* fix (potentially partially) imports (in feature extraction test modules)

* fix import utils.test_modeling_tf_core

* fix path ../fixtures/

* fix imports about generation.test_generation_flax_utils

* fix more imports

* fix fixture path

* fix get_test_dir

* update module_to_test_file

* fix get_tests_dir from wrong transformers.utils

* update config.yml (CircleCI)

* fix style

* remove missing imports

* update new model script

* update check_repo

* update SPECIAL_MODULE_TO_TEST_MAP

* fix style

* add __init__

* update self-scheduled

* fix add_new_model scripts

* check one way to get location back

* python setup.py build install

* fix import in test auto

* update self-scheduled.yml

* update slack notification script

* Add comments about artifact names

* fix for yolos

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
This commit is contained in:
Yih-Dar
2022-05-03 14:42:02 +02:00
committed by GitHub
parent cd9274d010
commit 19420fd99e
408 changed files with 616 additions and 607 deletions
Download Patch File Download Diff File Expand all files Collapse all files

0
tests/models/openai/__init__.py Normal file
View File

267
tests/models/openai/test_modeling_openai.py Normal file
View File

@@ -0,0 +1,267 @@
# coding=utf-8
# Copyright 2020 The HuggingFace Team. 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.
import unittest
from transformers import is_torch_available
from transformers.testing_utils import require_torch, slow, torch_device
from ...generation.test_generation_utils import GenerationTesterMixin
from ...test_configuration_common import ConfigTester
from ...test_modeling_common import ModelTesterMixin, ids_tensor
if is_torch_available():
import torch
from transformers import (
OPENAI_GPT_PRETRAINED_MODEL_ARCHIVE_LIST,
OpenAIGPTConfig,
OpenAIGPTDoubleHeadsModel,
OpenAIGPTForSequenceClassification,
OpenAIGPTLMHeadModel,
OpenAIGPTModel,
)
class OpenAIGPTModelTester:
def __init__(
self,
parent,
):
self.parent = parent
self.batch_size = 13
self.seq_length = 7
self.is_training = True
self.use_token_type_ids = True
self.use_labels = True
self.vocab_size = 99
self.hidden_size = 32
self.num_hidden_layers = 5
self.num_attention_heads = 4
self.intermediate_size = 37
self.hidden_act = "gelu"
self.hidden_dropout_prob = 0.1
self.attention_probs_dropout_prob = 0.1
self.max_position_embeddings = 512
self.type_vocab_size = 16
self.type_sequence_label_size = 2
self.initializer_range = 0.02
self.num_labels = 3
self.num_choices = 4
self.scope = None
self.pad_token_id = self.vocab_size - 1
def prepare_config_and_inputs(self):
input_ids = ids_tensor([self.batch_size, self.seq_length], self.vocab_size)
token_type_ids = None
if self.use_token_type_ids:
token_type_ids = ids_tensor([self.batch_size, self.seq_length], self.type_vocab_size)
sequence_labels = None
token_labels = None
choice_labels = None
if self.use_labels:
sequence_labels = ids_tensor([self.batch_size], self.type_sequence_label_size)
token_labels = ids_tensor([self.batch_size, self.seq_length], self.num_labels)
choice_labels = ids_tensor([self.batch_size], self.num_choices)
config = OpenAIGPTConfig(
vocab_size=self.vocab_size,
n_embd=self.hidden_size,
n_layer=self.num_hidden_layers,
n_head=self.num_attention_heads,
# intermediate_size=self.intermediate_size,
# hidden_act=self.hidden_act,
# hidden_dropout_prob=self.hidden_dropout_prob,
# attention_probs_dropout_prob=self.attention_probs_dropout_prob,
n_positions=self.max_position_embeddings,
# type_vocab_size=self.type_vocab_size,
# initializer_range=self.initializer_range
pad_token_id=self.pad_token_id,
)
head_mask = ids_tensor([self.num_hidden_layers, self.num_attention_heads], 2)
return (
config,
input_ids,
head_mask,
token_type_ids,
sequence_labels,
token_labels,
choice_labels,
)
def create_and_check_openai_gpt_model(self, config, input_ids, head_mask, token_type_ids, *args):
model = OpenAIGPTModel(config=config)
model.to(torch_device)
model.eval()
result = model(input_ids, token_type_ids=token_type_ids, head_mask=head_mask)
result = model(input_ids, token_type_ids=token_type_ids)
result = model(input_ids)
self.parent.assertEqual(result.last_hidden_state.shape, (self.batch_size, self.seq_length, self.hidden_size))
def create_and_check_lm_head_model(self, config, input_ids, head_mask, token_type_ids, *args):
model = OpenAIGPTLMHeadModel(config)
model.to(torch_device)
model.eval()
result = model(input_ids, token_type_ids=token_type_ids, labels=input_ids)
self.parent.assertEqual(result.loss.shape, ())
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.seq_length, self.vocab_size))
def create_and_check_double_lm_head_model(self, config, input_ids, head_mask, token_type_ids, *args):
model = OpenAIGPTDoubleHeadsModel(config)
model.to(torch_device)
model.eval()
result = model(input_ids, token_type_ids=token_type_ids, labels=input_ids)
self.parent.assertEqual(result.loss.shape, ())
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.seq_length, self.vocab_size))
def create_and_check_openai_gpt_for_sequence_classification(
self, config, input_ids, head_mask, token_type_ids, *args
):
config.num_labels = self.num_labels
model = OpenAIGPTForSequenceClassification(config)
model.to(torch_device)
model.eval()
sequence_labels = ids_tensor([self.batch_size], self.type_sequence_label_size)
result = model(input_ids, token_type_ids=token_type_ids, labels=sequence_labels)
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.num_labels))
def prepare_config_and_inputs_for_common(self):
config_and_inputs = self.prepare_config_and_inputs()
(
config,
input_ids,
head_mask,
token_type_ids,
sequence_labels,
token_labels,
choice_labels,
) = config_and_inputs
inputs_dict = {
"input_ids": input_ids,
"token_type_ids": token_type_ids,
"head_mask": head_mask,
}
return config, inputs_dict
@require_torch
class OpenAIGPTModelTest(ModelTesterMixin, GenerationTesterMixin, unittest.TestCase):
all_model_classes = (
(OpenAIGPTModel, OpenAIGPTLMHeadModel, OpenAIGPTDoubleHeadsModel, OpenAIGPTForSequenceClassification)
if is_torch_available()
else ()
)
all_generative_model_classes = (
(OpenAIGPTLMHeadModel,) if is_torch_available() else ()
) # TODO (PVP): Add Double HeadsModel when generate() function is changed accordingly
# special case for DoubleHeads model
def _prepare_for_class(self, inputs_dict, model_class, return_labels=False):
inputs_dict = super()._prepare_for_class(inputs_dict, model_class, return_labels=return_labels)
if return_labels:
if model_class.__name__ == "OpenAIGPTDoubleHeadsModel":
inputs_dict["labels"] = torch.zeros(
(self.model_tester.batch_size, self.model_tester.num_choices, self.model_tester.seq_length),
dtype=torch.long,
device=torch_device,
)
inputs_dict["input_ids"] = inputs_dict["labels"]
inputs_dict["token_type_ids"] = inputs_dict["labels"]
inputs_dict["mc_token_ids"] = torch.zeros(
(self.model_tester.batch_size, self.model_tester.num_choices),
dtype=torch.long,
device=torch_device,
)
inputs_dict["mc_labels"] = torch.zeros(
self.model_tester.batch_size, dtype=torch.long, device=torch_device
)
return inputs_dict
def setUp(self):
self.model_tester = OpenAIGPTModelTester(self)
self.config_tester = ConfigTester(self, config_class=OpenAIGPTConfig, n_embd=37)
def test_config(self):
self.config_tester.run_common_tests()
def test_openai_gpt_model(self):
config_and_inputs = self.model_tester.prepare_config_and_inputs()
self.model_tester.create_and_check_openai_gpt_model(*config_and_inputs)
def test_openai_gpt_lm_head_model(self):
config_and_inputs = self.model_tester.prepare_config_and_inputs()
self.model_tester.create_and_check_lm_head_model(*config_and_inputs)
def test_openai_gpt_double_lm_head_model(self):
config_and_inputs = self.model_tester.prepare_config_and_inputs()
self.model_tester.create_and_check_double_lm_head_model(*config_and_inputs)
def test_openai_gpt_classification_model(self):
config_and_inputs = self.model_tester.prepare_config_and_inputs()
self.model_tester.create_and_check_openai_gpt_for_sequence_classification(*config_and_inputs)
@slow
def test_model_from_pretrained(self):
for model_name in OPENAI_GPT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]:
model = OpenAIGPTModel.from_pretrained(model_name)
self.assertIsNotNone(model)
@require_torch
class OPENAIGPTModelLanguageGenerationTest(unittest.TestCase):
@slow
def test_lm_generate_openai_gpt(self):
model = OpenAIGPTLMHeadModel.from_pretrained("openai-gpt")
model.to(torch_device)
input_ids = torch.tensor([[481, 4735, 544]], dtype=torch.long, device=torch_device) # the president is
expected_output_ids = [
481,
4735,
544,
246,
963,
870,
762,
239,
244,
40477,
244,
249,
719,
881,
487,
544,
240,
244,
603,
481,
] # the president is a very good man. " \n " i\'m sure he is, " said the
output_ids = model.generate(input_ids, do_sample=False)
self.assertListEqual(output_ids[0].tolist(), expected_output_ids)

285
tests/models/openai/test_modeling_tf_openai.py Normal file
View File

@@ -0,0 +1,285 @@
# coding=utf-8
# Copyright 2020 The HuggingFace Team. 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.
import unittest
from transformers import OpenAIGPTConfig, is_tf_available
from transformers.testing_utils import require_tf, slow
from ...test_configuration_common import ConfigTester
from ...test_modeling_tf_common import TFModelTesterMixin, ids_tensor, random_attention_mask
if is_tf_available():
import tensorflow as tf
from transformers.models.openai.modeling_tf_openai import (
TF_OPENAI_GPT_PRETRAINED_MODEL_ARCHIVE_LIST,
TFOpenAIGPTDoubleHeadsModel,
TFOpenAIGPTForSequenceClassification,
TFOpenAIGPTLMHeadModel,
TFOpenAIGPTModel,
)
class TFOpenAIGPTModelTester:
def __init__(
self,
parent,
):
self.parent = parent
self.batch_size = 13
self.seq_length = 7
self.is_training = True
self.use_token_type_ids = True
self.use_input_mask = True
self.use_labels = True
self.use_mc_token_ids = True
self.vocab_size = 99
self.hidden_size = 32
self.num_hidden_layers = 5
self.num_attention_heads = 4
self.intermediate_size = 37
self.hidden_act = "gelu"
self.hidden_dropout_prob = 0.1
self.attention_probs_dropout_prob = 0.1
self.max_position_embeddings = 512
self.type_vocab_size = 16
self.type_sequence_label_size = 2
self.initializer_range = 0.02
self.num_labels = 3
self.num_choices = 4
self.scope = None
self.pad_token_id = self.vocab_size - 1
def prepare_config_and_inputs(self):
input_ids = ids_tensor([self.batch_size, self.seq_length], self.vocab_size)
input_mask = None
if self.use_input_mask:
input_mask = random_attention_mask([self.batch_size, self.seq_length])
token_type_ids = None
if self.use_token_type_ids:
token_type_ids = ids_tensor([self.batch_size, self.seq_length], self.type_vocab_size)
mc_token_ids = None
if self.use_mc_token_ids:
mc_token_ids = ids_tensor([self.batch_size, self.num_choices], self.seq_length)
sequence_labels = None
token_labels = None
choice_labels = None
if self.use_labels:
sequence_labels = ids_tensor([self.batch_size], self.type_sequence_label_size)
token_labels = ids_tensor([self.batch_size, self.seq_length], self.num_labels)
choice_labels = ids_tensor([self.batch_size], self.num_choices)
config = OpenAIGPTConfig(
vocab_size=self.vocab_size,
n_embd=self.hidden_size,
n_layer=self.num_hidden_layers,
n_head=self.num_attention_heads,
# intermediate_size=self.intermediate_size,
# hidden_act=self.hidden_act,
# hidden_dropout_prob=self.hidden_dropout_prob,
# attention_probs_dropout_prob=self.attention_probs_dropout_prob,
n_positions=self.max_position_embeddings,
# type_vocab_size=self.type_vocab_size,
# initializer_range=self.initializer_range,
pad_token_id=self.pad_token_id,
)
head_mask = ids_tensor([self.num_hidden_layers, self.num_attention_heads], 2)
return (
config,
input_ids,
input_mask,
head_mask,
token_type_ids,
mc_token_ids,
sequence_labels,
token_labels,
choice_labels,
)
def create_and_check_openai_gpt_model(self, config, input_ids, input_mask, head_mask, token_type_ids, *args):
model = TFOpenAIGPTModel(config=config)
inputs = {"input_ids": input_ids, "attention_mask": input_mask, "token_type_ids": token_type_ids}
result = model(inputs)
inputs = [input_ids, input_mask]
result = model(inputs)
result = model(input_ids)
self.parent.assertEqual(result.last_hidden_state.shape, (self.batch_size, self.seq_length, self.hidden_size))
def create_and_check_openai_gpt_lm_head(self, config, input_ids, input_mask, head_mask, token_type_ids, *args):
model = TFOpenAIGPTLMHeadModel(config=config)
inputs = {"input_ids": input_ids, "attention_mask": input_mask, "token_type_ids": token_type_ids}
result = model(inputs)
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.seq_length, self.vocab_size))
def create_and_check_openai_gpt_double_head(
self, config, input_ids, input_mask, head_mask, token_type_ids, mc_token_ids, *args
):
model = TFOpenAIGPTDoubleHeadsModel(config=config)
multiple_choice_inputs_ids = tf.tile(tf.expand_dims(input_ids, 1), (1, self.num_choices, 1))
multiple_choice_input_mask = tf.tile(tf.expand_dims(input_mask, 1), (1, self.num_choices, 1))
multiple_choice_token_type_ids = tf.tile(tf.expand_dims(token_type_ids, 1), (1, self.num_choices, 1))
inputs = {
"input_ids": multiple_choice_inputs_ids,
"mc_token_ids": mc_token_ids,
"attention_mask": multiple_choice_input_mask,
"token_type_ids": multiple_choice_token_type_ids,
}
result = model(inputs)
self.parent.assertEqual(
result.logits.shape, (self.batch_size, self.num_choices, self.seq_length, self.vocab_size)
)
self.parent.assertEqual(result.mc_logits.shape, (self.batch_size, self.num_choices))
def create_and_check_openai_gpt_for_sequence_classification(
self, config, input_ids, input_mask, head_mask, token_type_ids, *args
):
config.num_labels = self.num_labels
sequence_labels = ids_tensor([self.batch_size], self.type_sequence_label_size)
inputs = {
"input_ids": input_ids,
"attention_mask": input_mask,
"token_type_ids": token_type_ids,
"labels": sequence_labels,
}
model = TFOpenAIGPTForSequenceClassification(config)
result = model(inputs)
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.num_labels))
def prepare_config_and_inputs_for_common(self):
config_and_inputs = self.prepare_config_and_inputs()
(
config,
input_ids,
input_mask,
head_mask,
token_type_ids,
mc_token_ids,
sequence_labels,
token_labels,
choice_labels,
) = config_and_inputs
inputs_dict = {"input_ids": input_ids, "token_type_ids": token_type_ids, "attention_mask": input_mask}
return config, inputs_dict
@require_tf
class TFOpenAIGPTModelTest(TFModelTesterMixin, unittest.TestCase):
all_model_classes = (
(TFOpenAIGPTModel, TFOpenAIGPTLMHeadModel, TFOpenAIGPTDoubleHeadsModel, TFOpenAIGPTForSequenceClassification)
if is_tf_available()
else ()
)
all_generative_model_classes = (
(TFOpenAIGPTLMHeadModel,) if is_tf_available() else ()
) # TODO (PVP): Add Double HeadsModel when generate() function is changed accordingly
test_head_masking = False
test_onnx = False
def setUp(self):
self.model_tester = TFOpenAIGPTModelTester(self)
self.config_tester = ConfigTester(self, config_class=OpenAIGPTConfig, n_embd=37)
def test_config(self):
self.config_tester.run_common_tests()
def test_openai_gpt_model(self):
config_and_inputs = self.model_tester.prepare_config_and_inputs()
self.model_tester.create_and_check_openai_gpt_model(*config_and_inputs)
def test_openai_gpt_lm_head(self):
config_and_inputs = self.model_tester.prepare_config_and_inputs()
self.model_tester.create_and_check_openai_gpt_lm_head(*config_and_inputs)
def test_openai_gpt_double_head(self):
config_and_inputs = self.model_tester.prepare_config_and_inputs()
self.model_tester.create_and_check_openai_gpt_double_head(*config_and_inputs)
def test_model_common_attributes(self):
config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common()
for model_class in self.all_model_classes:
model = model_class(config)
assert isinstance(model.get_input_embeddings(), tf.keras.layers.Layer)
if model_class in self.all_generative_model_classes:
x = model.get_output_embeddings()
assert isinstance(x, tf.keras.layers.Layer)
name = model.get_bias()
assert name is None
else:
x = model.get_output_embeddings()
assert x is None
name = model.get_bias()
assert name is None
def test_openai_gpt_sequence_classification_model(self):
config_and_inputs = self.model_tester.prepare_config_and_inputs()
self.model_tester.create_and_check_openai_gpt_for_sequence_classification(*config_and_inputs)
@slow
def test_model_from_pretrained(self):
for model_name in TF_OPENAI_GPT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]:
model = TFOpenAIGPTModel.from_pretrained(model_name)
self.assertIsNotNone(model)
@require_tf
class TFOPENAIGPTModelLanguageGenerationTest(unittest.TestCase):
@slow
def test_lm_generate_openai_gpt(self):
model = TFOpenAIGPTLMHeadModel.from_pretrained("openai-gpt")
input_ids = tf.convert_to_tensor([[481, 4735, 544]], dtype=tf.int32) # the president is
expected_output_ids = [
481,
4735,
544,
246,
963,
870,
762,
239,
244,
40477,
244,
249,
719,
881,
487,
544,
240,
244,
603,
481,
] # the president is a very good man. " \n " i\'m sure he is, " said the
output_ids = model.generate(input_ids, do_sample=False)
self.assertListEqual(output_ids[0].numpy().tolist(), expected_output_ids)

144
tests/models/openai/test_tokenization_openai.py Normal file
View File

@@ -0,0 +1,144 @@
# coding=utf-8
# Copyright 2018 The Google AI Language Team Authors.
#
# 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 json
import os
import unittest
from transformers import OpenAIGPTTokenizer, OpenAIGPTTokenizerFast
from transformers.models.openai.tokenization_openai import VOCAB_FILES_NAMES
from transformers.testing_utils import require_ftfy, require_spacy, require_tokenizers
from ...test_tokenization_common import TokenizerTesterMixin
@require_tokenizers
class OpenAIGPTTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
"""Tests OpenAIGPTTokenizer that uses BERT BasicTokenizer."""
tokenizer_class = OpenAIGPTTokenizer
rust_tokenizer_class = OpenAIGPTTokenizerFast
test_rust_tokenizer = True
test_seq2seq = False
def setUp(self):
super().setUp()
# Adapted from Sennrich et al. 2015 and https://github.com/rsennrich/subword-nmt
vocab = [
"l",
"o",
"w",
"e",
"r",
"s",
"t",
"i",
"d",
"n",
"w</w>",
"r</w>",
"t</w>",
"lo",
"low",
"er</w>",
"low</w>",
"lowest</w>",
"newer</w>",
"wider</w>",
"<unk>",
]
vocab_tokens = dict(zip(vocab, range(len(vocab))))
merges = ["#version: 0.2", "l o", "lo w", "e r</w>", ""]
self.vocab_file = os.path.join(self.tmpdirname, VOCAB_FILES_NAMES["vocab_file"])
self.merges_file = os.path.join(self.tmpdirname, VOCAB_FILES_NAMES["merges_file"])
with open(self.vocab_file, "w") as fp:
fp.write(json.dumps(vocab_tokens))
with open(self.merges_file, "w") as fp:
fp.write("\n".join(merges))
def get_input_output_texts(self, tokenizer):
return "lower newer", "lower newer"
def test_full_tokenizer(self):
tokenizer = OpenAIGPTTokenizer(self.vocab_file, self.merges_file)
text = "lower"
bpe_tokens = ["low", "er</w>"]
tokens = tokenizer.tokenize(text)
self.assertListEqual(tokens, bpe_tokens)
input_tokens = tokens + ["<unk>"]
input_bpe_tokens = [14, 15, 20]
self.assertListEqual(tokenizer.convert_tokens_to_ids(input_tokens), input_bpe_tokens)
def test_padding(self, max_length=15):
for tokenizer, pretrained_name, kwargs in self.tokenizers_list:
with self.subTest(f"{tokenizer.__class__.__name__} ({pretrained_name})"):
tokenizer_r = self.rust_tokenizer_class.from_pretrained(pretrained_name, **kwargs)
# Simple input
s = "This is a simple input"
s2 = ["This is a simple input 1", "This is a simple input 2"]
p = ("This is a simple input", "This is a pair")
p2 = [
("This is a simple input 1", "This is a simple input 2"),
("This is a simple pair 1", "This is a simple pair 2"),
]
# Simple input tests
self.assertRaises(ValueError, tokenizer_r.encode, s, max_length=max_length, padding="max_length")
# Simple input
self.assertRaises(ValueError, tokenizer_r.encode_plus, s, max_length=max_length, padding="max_length")
# Simple input
self.assertRaises(
ValueError,
tokenizer_r.batch_encode_plus,
s2,
max_length=max_length,
padding="max_length",
)
# Pair input
self.assertRaises(ValueError, tokenizer_r.encode, p, max_length=max_length, padding="max_length")
# Pair input
self.assertRaises(ValueError, tokenizer_r.encode_plus, p, max_length=max_length, padding="max_length")
# Pair input
self.assertRaises(
ValueError,
tokenizer_r.batch_encode_plus,
p2,
max_length=max_length,
padding="max_length",
)
# tokenizer has no padding token
def test_padding_different_model_input_name(self):
pass
@require_ftfy
@require_spacy
@require_tokenizers
class OpenAIGPTTokenizationTestWithSpacy(OpenAIGPTTokenizationTest):
"""Tests OpenAIGPTTokenizer that uses SpaCy and ftfy."""
pass