mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-31 02:02:21 +06:00
Removed unused encoder_hidden_states and encoder_attention_mask (#8972)
* Removed unused `encoder_hidden_states` and `encoder_attention_mask` from MobileBert * Removed decoder tests for MobileBert * Removed now unnecessary import
This commit is contained in:
guillaume-be
GitHub
parent
b7cdd00f15
commit
7809eb82ae
@ -251,8 +251,6 @@ class MobileBertSelfAttention(nn.Module):
|
||||
value_tensor,
|
||||
attention_mask=None,
|
||||
head_mask=None,
|
||||
encoder_hidden_states=None,
|
||||
encoder_attention_mask=None,
|
||||
output_attentions=None,
|
||||
):
|
||||
mixed_query_layer = self.query(query_tensor)
|
||||
@ -335,8 +333,6 @@ class MobileBertAttention(nn.Module):
|
||||
layer_input,
|
||||
attention_mask=None,
|
||||
head_mask=None,
|
||||
encoder_hidden_states=None,
|
||||
encoder_attention_mask=None,
|
||||
output_attentions=None,
|
||||
):
|
||||
self_outputs = self.self(
|
||||
@ -345,8 +341,6 @@ class MobileBertAttention(nn.Module):
|
||||
value_tensor,
|
||||
attention_mask,
|
||||
head_mask,
|
||||
encoder_hidden_states,
|
||||
encoder_attention_mask,
|
||||
output_attentions,
|
||||
)
|
||||
# Run a linear projection of `hidden_size` then add a residual
|
||||
@ -498,8 +492,6 @@ class MobileBertLayer(nn.Module):
|
||||
hidden_states,
|
||||
attention_mask=None,
|
||||
head_mask=None,
|
||||
encoder_hidden_states=None,
|
||||
encoder_attention_mask=None,
|
||||
output_attentions=None,
|
||||
):
|
||||
if self.use_bottleneck:
|
||||
@ -554,8 +546,6 @@ class MobileBertEncoder(nn.Module):
|
||||
hidden_states,
|
||||
attention_mask=None,
|
||||
head_mask=None,
|
||||
encoder_hidden_states=None,
|
||||
encoder_attention_mask=None,
|
||||
output_attentions=False,
|
||||
output_hidden_states=False,
|
||||
return_dict=True,
|
||||
@ -570,8 +560,6 @@ class MobileBertEncoder(nn.Module):
|
||||
hidden_states,
|
||||
attention_mask,
|
||||
head_mask[i],
|
||||
encoder_hidden_states,
|
||||
encoder_attention_mask,
|
||||
output_attentions,
|
||||
)
|
||||
hidden_states = layer_outputs[0]
|
||||
@ -783,16 +771,6 @@ MOBILEBERT_INPUTS_DOCSTRING = r"""
|
||||
Optionally, instead of passing :obj:`input_ids` you can choose to directly pass an embedded representation.
|
||||
This is useful if you want more control over how to convert :obj:`input_ids` indices into associated
|
||||
vectors than the model's internal embedding lookup matrix.
|
||||
encoder_hidden_states (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
|
||||
Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if
|
||||
the model is configured as a decoder.
|
||||
encoder_attention_mask (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
|
||||
Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
|
||||
the cross-attention if the model is configured as a decoder. Mask values selected in ``[0, 1]``:
|
||||
|
||||
- 1 for tokens that are **not masked**,
|
||||
- 0 for tokens that are **masked**.
|
||||
|
||||
output_attentions (:obj:`bool`, `optional`):
|
||||
Whether or not to return the attentions tensors of all attention layers. See ``attentions`` under returned
|
||||
tensors for more detail.
|
||||
@ -852,8 +830,6 @@ class MobileBertModel(MobileBertPreTrainedModel):
|
||||
position_ids=None,
|
||||
head_mask=None,
|
||||
inputs_embeds=None,
|
||||
encoder_hidden_states=None,
|
||||
encoder_attention_mask=None,
|
||||
output_hidden_states=None,
|
||||
output_attentions=None,
|
||||
return_dict=None,
|
||||
@ -886,17 +862,6 @@ class MobileBertModel(MobileBertPreTrainedModel):
|
||||
attention_mask, input_shape, self.device
|
||||
)
|
||||
|
||||
# If a 2D ou 3D attention mask is provided for the cross-attention
|
||||
# we need to make broadcastable to [batch_size, num_heads, seq_length, seq_length]
|
||||
if self.config.is_decoder and encoder_hidden_states is not None:
|
||||
encoder_batch_size, encoder_sequence_length, _ = encoder_hidden_states.size()
|
||||
encoder_hidden_shape = (encoder_batch_size, encoder_sequence_length)
|
||||
if encoder_attention_mask is None:
|
||||
encoder_attention_mask = torch.ones(encoder_hidden_shape, device=device)
|
||||
encoder_extended_attention_mask = self.invert_attention_mask(encoder_attention_mask)
|
||||
else:
|
||||
encoder_extended_attention_mask = None
|
||||
|
||||
# Prepare head mask if needed
|
||||
# 1.0 in head_mask indicate we keep the head
|
||||
# attention_probs has shape bsz x n_heads x N x N
|
||||
@ -911,8 +876,6 @@ class MobileBertModel(MobileBertPreTrainedModel):
|
||||
embedding_output,
|
||||
attention_mask=extended_attention_mask,
|
||||
head_mask=head_mask,
|
||||
encoder_hidden_states=encoder_hidden_states,
|
||||
encoder_attention_mask=encoder_extended_attention_mask,
|
||||
output_attentions=output_attentions,
|
||||
output_hidden_states=output_hidden_states,
|
||||
return_dict=return_dict,
|
||||
@ -1083,8 +1046,6 @@ class MobileBertForMaskedLM(MobileBertPreTrainedModel):
|
||||
head_mask=None,
|
||||
inputs_embeds=None,
|
||||
labels=None,
|
||||
encoder_hidden_states=None,
|
||||
encoder_attention_mask=None,
|
||||
output_attentions=None,
|
||||
output_hidden_states=None,
|
||||
return_dict=None,
|
||||
@ -1104,8 +1065,6 @@ class MobileBertForMaskedLM(MobileBertPreTrainedModel):
|
||||
position_ids=position_ids,
|
||||
head_mask=head_mask,
|
||||
inputs_embeds=inputs_embeds,
|
||||
encoder_hidden_states=encoder_hidden_states,
|
||||
encoder_attention_mask=encoder_attention_mask,
|
||||
output_attentions=output_attentions,
|
||||
output_hidden_states=output_hidden_states,
|
||||
return_dict=return_dict,
|
||||
|
||||
@ -20,7 +20,7 @@ from transformers import is_torch_available
|
||||
from transformers.testing_utils import require_sentencepiece, require_tokenizers, require_torch, slow, torch_device
|
||||
|
||||
from .test_configuration_common import ConfigTester
|
||||
from .test_modeling_common import ModelTesterMixin, floats_tensor, ids_tensor, random_attention_mask
|
||||
from .test_modeling_common import ModelTesterMixin, ids_tensor, random_attention_mask
|
||||
|
||||
|
||||
if is_torch_available():
|
||||
@ -128,33 +128,6 @@ class MobileBertModelTester:
|
||||
|
||||
return config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
|
||||
def prepare_config_and_inputs_for_decoder(self):
|
||||
(
|
||||
config,
|
||||
input_ids,
|
||||
token_type_ids,
|
||||
input_mask,
|
||||
sequence_labels,
|
||||
token_labels,
|
||||
choice_labels,
|
||||
) = self.prepare_config_and_inputs()
|
||||
|
||||
config.is_decoder = True
|
||||
encoder_hidden_states = floats_tensor([self.batch_size, self.seq_length, self.hidden_size])
|
||||
encoder_attention_mask = ids_tensor([self.batch_size, self.seq_length], vocab_size=2)
|
||||
|
||||
return (
|
||||
config,
|
||||
input_ids,
|
||||
token_type_ids,
|
||||
input_mask,
|
||||
sequence_labels,
|
||||
token_labels,
|
||||
choice_labels,
|
||||
encoder_hidden_states,
|
||||
encoder_attention_mask,
|
||||
)
|
||||
|
||||
def create_and_check_mobilebert_model(
|
||||
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
@ -168,39 +141,6 @@ class MobileBertModelTester:
|
||||
self.parent.assertEqual(result.last_hidden_state.shape, (self.batch_size, self.seq_length, self.hidden_size))
|
||||
self.parent.assertEqual(result.pooler_output.shape, (self.batch_size, self.hidden_size))
|
||||
|
||||
def create_and_check_mobilebert_model_as_decoder(
|
||||
self,
|
||||
config,
|
||||
input_ids,
|
||||
token_type_ids,
|
||||
input_mask,
|
||||
sequence_labels,
|
||||
token_labels,
|
||||
choice_labels,
|
||||
encoder_hidden_states,
|
||||
encoder_attention_mask,
|
||||
):
|
||||
model = MobileBertModel(config)
|
||||
model.to(torch_device)
|
||||
model.eval()
|
||||
result = model(
|
||||
input_ids,
|
||||
attention_mask=input_mask,
|
||||
token_type_ids=token_type_ids,
|
||||
encoder_hidden_states=encoder_hidden_states,
|
||||
encoder_attention_mask=encoder_attention_mask,
|
||||
)
|
||||
result = model(
|
||||
input_ids,
|
||||
attention_mask=input_mask,
|
||||
token_type_ids=token_type_ids,
|
||||
encoder_hidden_states=encoder_hidden_states,
|
||||
)
|
||||
result = model(input_ids, attention_mask=input_mask, token_type_ids=token_type_ids)
|
||||
|
||||
self.parent.assertEqual(result.last_hidden_state.shape, (self.batch_size, self.seq_length, self.hidden_size))
|
||||
self.parent.assertEqual(result.pooler_output.shape, (self.batch_size, self.hidden_size))
|
||||
|
||||
def create_and_check_mobilebert_for_masked_lm(
|
||||
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
|
||||
):
|
||||
@ -352,38 +292,6 @@ class MobileBertModelTest(ModelTesterMixin, unittest.TestCase):
|
||||
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
||||
self.model_tester.create_and_check_mobilebert_model(*config_and_inputs)
|
||||
|
||||
def test_mobilebert_model_as_decoder(self):
|
||||
config_and_inputs = self.model_tester.prepare_config_and_inputs_for_decoder()
|
||||
self.model_tester.create_and_check_mobilebert_model_as_decoder(*config_and_inputs)
|
||||
|
||||
def test_mobilebert_model_as_decoder_with_default_input_mask(self):
|
||||
# This regression test was failing with PyTorch < 1.3
|
||||
(
|
||||
config,
|
||||
input_ids,
|
||||
token_type_ids,
|
||||
input_mask,
|
||||
sequence_labels,
|
||||
token_labels,
|
||||
choice_labels,
|
||||
encoder_hidden_states,
|
||||
encoder_attention_mask,
|
||||
) = self.model_tester.prepare_config_and_inputs_for_decoder()
|
||||
|
||||
input_mask = None
|
||||
|
||||
self.model_tester.create_and_check_mobilebert_model_as_decoder(
|
||||
config,
|
||||
input_ids,
|
||||
token_type_ids,
|
||||
input_mask,
|
||||
sequence_labels,
|
||||
token_labels,
|
||||
choice_labels,
|
||||
encoder_hidden_states,
|
||||
encoder_attention_mask,
|
||||
)
|
||||
|
||||
def test_for_masked_lm(self):
|
||||
config_and_inputs = self.model_tester.prepare_config_and_inputs()
|
||||
self.model_tester.create_and_check_mobilebert_for_masked_lm(*config_and_inputs)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user