Expose get_config() on ModelTesters (#12812)
* Expose get_config() on ModelTesters * Typo
This commit is contained in:
Lysandre Debut
@@ -16,7 +16,7 @@
|
||||
|
||||
import unittest
|
||||
|
||||
from transformers import is_torch_available
|
||||
from transformers import DistilBertConfig, is_torch_available
|
||||
from transformers.testing_utils import require_torch, slow, torch_device
|
||||
|
||||
from .test_configuration_common import ConfigTester
|
||||
@@ -28,7 +28,6 @@ if is_torch_available():
|
||||
|
||||
from transformers import (
|
||||
DISTILBERT_PRETRAINED_MODEL_ARCHIVE_LIST,
|
||||
DistilBertConfig,
|
||||
DistilBertForMaskedLM,
|
||||
DistilBertForMultipleChoice,
|
||||
DistilBertForQuestionAnswering,
|
||||
@@ -37,160 +36,162 @@ if is_torch_available():
|
||||
DistilBertModel,
|
||||
)
|
||||
|
||||
class DistilBertModelTester(object):
|
||||
def __init__(
|
||||
self,
|
||||
parent,
|
||||
batch_size=13,
|
||||
seq_length=7,
|
||||
is_training=True,
|
||||
use_input_mask=True,
|
||||
use_token_type_ids=False,
|
||||
use_labels=True,
|
||||
vocab_size=99,
|
||||
hidden_size=32,
|
||||
num_hidden_layers=5,
|
||||
num_attention_heads=4,
|
||||
intermediate_size=37,
|
||||
hidden_act="gelu",
|
||||
hidden_dropout_prob=0.1,
|
||||
attention_probs_dropout_prob=0.1,
|
||||
max_position_embeddings=512,
|
||||
type_vocab_size=16,
|
||||
type_sequence_label_size=2,
|
||||
initializer_range=0.02,
|
||||
num_labels=3,
|
||||
num_choices=4,
|
||||
scope=None,
|
||||
):
|
||||
self.parent = parent
|
||||
self.batch_size = batch_size
|
||||
self.seq_length = seq_length
|
||||
self.is_training = is_training
|
||||
self.use_input_mask = use_input_mask
|
||||
self.use_token_type_ids = use_token_type_ids
|
||||
self.use_labels = use_labels
|
||||
self.vocab_size = vocab_size
|
||||
self.hidden_size = hidden_size
|
||||
self.num_hidden_layers = num_hidden_layers
|
||||
self.num_attention_heads = num_attention_heads
|
||||
self.intermediate_size = intermediate_size
|
||||
self.hidden_act = hidden_act
|
||||
self.hidden_dropout_prob = hidden_dropout_prob
|
||||
self.attention_probs_dropout_prob = attention_probs_dropout_prob
|
||||
self.max_position_embeddings = max_position_embeddings
|
||||
self.type_vocab_size = type_vocab_size
|
||||
self.type_sequence_label_size = type_sequence_label_size
|
||||
self.initializer_range = initializer_range
|
||||
self.num_labels = num_labels
|
||||
self.num_choices = num_choices
|
||||
self.scope = scope
|
||||
|
||||
def prepare_config_and_inputs(self):
|
||||
input_ids = ids_tensor([self.batch_size, self.seq_length], self.vocab_size)
|
||||
class DistilBertModelTester(object):
|
||||
def __init__(
|
||||
self,
|
||||
parent,
|
||||
batch_size=13,
|
||||
seq_length=7,
|
||||
is_training=True,
|
||||
use_input_mask=True,
|
||||
use_token_type_ids=False,
|
||||
use_labels=True,
|
||||
vocab_size=99,
|
||||
hidden_size=32,
|
||||
num_hidden_layers=5,
|
||||
num_attention_heads=4,
|
||||
intermediate_size=37,
|
||||
hidden_act="gelu",
|
||||
hidden_dropout_prob=0.1,
|
||||
attention_probs_dropout_prob=0.1,
|
||||
max_position_embeddings=512,
|
||||
type_vocab_size=16,
|
||||
type_sequence_label_size=2,
|
||||
initializer_range=0.02,
|
||||
num_labels=3,
|
||||
num_choices=4,
|
||||
scope=None,
|
||||
):
|
||||
self.parent = parent
|
||||
self.batch_size = batch_size
|
||||
self.seq_length = seq_length
|
||||
self.is_training = is_training
|
||||
self.use_input_mask = use_input_mask
|
||||
self.use_token_type_ids = use_token_type_ids
|
||||
self.use_labels = use_labels
|
||||
self.vocab_size = vocab_size
|
||||
self.hidden_size = hidden_size
|
||||
self.num_hidden_layers = num_hidden_layers
|
||||
self.num_attention_heads = num_attention_heads
|
||||
self.intermediate_size = intermediate_size
|
||||
self.hidden_act = hidden_act
|
||||
self.hidden_dropout_prob = hidden_dropout_prob
|
||||
self.attention_probs_dropout_prob = attention_probs_dropout_prob
|
||||
self.max_position_embeddings = max_position_embeddings
|
||||
self.type_vocab_size = type_vocab_size
|
||||
self.type_sequence_label_size = type_sequence_label_size
|
||||
self.initializer_range = initializer_range
|
||||
self.num_labels = num_labels
|
||||
self.num_choices = num_choices
|
||||
self.scope = scope
|
||||
|
||||
input_mask = None
|
||||
if self.use_input_mask:
|
||||
input_mask = random_attention_mask([self.batch_size, self.seq_length])
|
||||
def prepare_config_and_inputs(self):
|
||||
input_ids = ids_tensor([self.batch_size, self.seq_length], self.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)
|
||||
input_mask = None
|
||||
if self.use_input_mask:
|
||||
input_mask = random_attention_mask([self.batch_size, self.seq_length])
|
||||
|
||||
config = DistilBertConfig(
|
||||
vocab_size=self.vocab_size,
|
||||
dim=self.hidden_size,
|
||||
n_layers=self.num_hidden_layers,
|
||||
n_heads=self.num_attention_heads,
|
||||
hidden_dim=self.intermediate_size,
|
||||
hidden_act=self.hidden_act,
|
||||
dropout=self.hidden_dropout_prob,
|
||||
attention_dropout=self.attention_probs_dropout_prob,
|
||||
max_position_embeddings=self.max_position_embeddings,
|
||||
initializer_range=self.initializer_range,
|
||||
)
|
||||
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)
|
||||
|
||||
return config, input_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
config = self.get_config()
|
||||
|
||||
def create_and_check_distilbert_model(
|
||||
self, config, input_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
model = DistilBertModel(config=config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
result = model(input_ids, input_mask)
|
||||
result = model(input_ids)
|
||||
self.parent.assertEqual(
|
||||
result.last_hidden_state.shape, (self.batch_size, self.seq_length, self.hidden_size)
|
||||
)
|
||||
return config, input_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
|
||||
def create_and_check_distilbert_for_masked_lm(
|
||||
self, config, input_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
model = DistilBertForMaskedLM(config=config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
result = model(input_ids, attention_mask=input_mask, labels=token_labels)
|
||||
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.seq_length, self.vocab_size))
|
||||
def get_config(self):
|
||||
return DistilBertConfig(
|
||||
vocab_size=self.vocab_size,
|
||||
dim=self.hidden_size,
|
||||
n_layers=self.num_hidden_layers,
|
||||
n_heads=self.num_attention_heads,
|
||||
hidden_dim=self.intermediate_size,
|
||||
hidden_act=self.hidden_act,
|
||||
dropout=self.hidden_dropout_prob,
|
||||
attention_dropout=self.attention_probs_dropout_prob,
|
||||
max_position_embeddings=self.max_position_embeddings,
|
||||
initializer_range=self.initializer_range,
|
||||
)
|
||||
|
||||
def create_and_check_distilbert_for_question_answering(
|
||||
self, config, input_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
model = DistilBertForQuestionAnswering(config=config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
result = model(
|
||||
input_ids, attention_mask=input_mask, start_positions=sequence_labels, end_positions=sequence_labels
|
||||
)
|
||||
self.parent.assertEqual(result.start_logits.shape, (self.batch_size, self.seq_length))
|
||||
self.parent.assertEqual(result.end_logits.shape, (self.batch_size, self.seq_length))
|
||||
def create_and_check_distilbert_model(
|
||||
self, config, input_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
model = DistilBertModel(config=config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
result = model(input_ids, input_mask)
|
||||
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_distilbert_for_sequence_classification(
|
||||
self, config, input_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
config.num_labels = self.num_labels
|
||||
model = DistilBertForSequenceClassification(config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
result = model(input_ids, attention_mask=input_mask, labels=sequence_labels)
|
||||
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.num_labels))
|
||||
def create_and_check_distilbert_for_masked_lm(
|
||||
self, config, input_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
model = DistilBertForMaskedLM(config=config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
result = model(input_ids, attention_mask=input_mask, labels=token_labels)
|
||||
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.seq_length, self.vocab_size))
|
||||
|
||||
def create_and_check_distilbert_for_token_classification(
|
||||
self, config, input_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
config.num_labels = self.num_labels
|
||||
model = DistilBertForTokenClassification(config=config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
def create_and_check_distilbert_for_question_answering(
|
||||
self, config, input_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
model = DistilBertForQuestionAnswering(config=config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
result = model(
|
||||
input_ids, attention_mask=input_mask, start_positions=sequence_labels, end_positions=sequence_labels
|
||||
)
|
||||
self.parent.assertEqual(result.start_logits.shape, (self.batch_size, self.seq_length))
|
||||
self.parent.assertEqual(result.end_logits.shape, (self.batch_size, self.seq_length))
|
||||
|
||||
result = model(input_ids, attention_mask=input_mask, labels=token_labels)
|
||||
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.seq_length, self.num_labels))
|
||||
def create_and_check_distilbert_for_sequence_classification(
|
||||
self, config, input_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
config.num_labels = self.num_labels
|
||||
model = DistilBertForSequenceClassification(config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
result = model(input_ids, attention_mask=input_mask, labels=sequence_labels)
|
||||
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.num_labels))
|
||||
|
||||
def create_and_check_distilbert_for_multiple_choice(
|
||||
self, config, input_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
config.num_choices = self.num_choices
|
||||
model = DistilBertForMultipleChoice(config=config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
multiple_choice_inputs_ids = input_ids.unsqueeze(1).expand(-1, self.num_choices, -1).contiguous()
|
||||
multiple_choice_input_mask = input_mask.unsqueeze(1).expand(-1, self.num_choices, -1).contiguous()
|
||||
result = model(
|
||||
multiple_choice_inputs_ids,
|
||||
attention_mask=multiple_choice_input_mask,
|
||||
labels=choice_labels,
|
||||
)
|
||||
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.num_choices))
|
||||
def create_and_check_distilbert_for_token_classification(
|
||||
self, config, input_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
config.num_labels = self.num_labels
|
||||
model = DistilBertForTokenClassification(config=config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
|
||||
def prepare_config_and_inputs_for_common(self):
|
||||
config_and_inputs = self.prepare_config_and_inputs()
|
||||
(config, input_ids, input_mask, sequence_labels, token_labels, choice_labels) = config_and_inputs
|
||||
inputs_dict = {"input_ids": input_ids, "attention_mask": input_mask}
|
||||
return config, inputs_dict
|
||||
result = model(input_ids, attention_mask=input_mask, labels=token_labels)
|
||||
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.seq_length, self.num_labels))
|
||||
|
||||
def create_and_check_distilbert_for_multiple_choice(
|
||||
self, config, input_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
config.num_choices = self.num_choices
|
||||
model = DistilBertForMultipleChoice(config=config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
multiple_choice_inputs_ids = input_ids.unsqueeze(1).expand(-1, self.num_choices, -1).contiguous()
|
||||
multiple_choice_input_mask = input_mask.unsqueeze(1).expand(-1, self.num_choices, -1).contiguous()
|
||||
result = model(
|
||||
multiple_choice_inputs_ids,
|
||||
attention_mask=multiple_choice_input_mask,
|
||||
labels=choice_labels,
|
||||
)
|
||||
self.parent.assertEqual(result.logits.shape, (self.batch_size, self.num_choices))
|
||||
|
||||
def prepare_config_and_inputs_for_common(self):
|
||||
config_and_inputs = self.prepare_config_and_inputs()
|
||||
(config, input_ids, input_mask, sequence_labels, token_labels, choice_labels) = config_and_inputs
|
||||
inputs_dict = {"input_ids": input_ids, "attention_mask": input_mask}
|
||||
return config, inputs_dict
|
||||
|
||||
|
||||
@require_torch
|
||||
|
||||
Reference in New Issue
Block a user