Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Allow passing encoder_ouputs as tuple to EncoderDecoder Models #16814

Merged
merged 3 commits into from
Apr 18, 2022
Merged

Allow passing encoder_ouputs as tuple to EncoderDecoder Models #16814

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
8259910
Add passing encoder_outputs as tuple to existing test
jsnfly Apr 18, 2022
4fad2ab
Add check for tuple
jsnfly Apr 18, 2022
45a9a18
Add check for tuple also for speech and vision
jsnfly Apr 18, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion src/transformers/models/encoder_decoder/modeling_encoder_decoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@
from torch.nn import CrossEntropyLoss

from ...configuration_utils import PretrainedConfig
from ...modeling_outputs import Seq2SeqLMOutput
from ...modeling_outputs import BaseModelOutput, Seq2SeqLMOutput
from ...modeling_utils import PreTrainedModel
from ...utils import add_start_docstrings, add_start_docstrings_to_model_forward, logging, replace_return_docstrings
from ..auto.configuration_auto import AutoConfig
Expand Down Expand Up @@ -494,6 +494,8 @@ def forward(
return_dict=return_dict,
**kwargs_encoder,
)
elif isinstance(encoder_outputs, tuple):
encoder_outputs = BaseModelOutput(*encoder_outputs)

encoder_hidden_states = encoder_outputs[0]

Expand Down
4 changes: 3 additions & 1 deletion src/transformers/models/speech_encoder_decoder/modeling_speech_encoder_decoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@
from torch.nn import CrossEntropyLoss

from ...configuration_utils import PretrainedConfig
from ...modeling_outputs import Seq2SeqLMOutput
from ...modeling_outputs import BaseModelOutput, Seq2SeqLMOutput
from ...modeling_utils import PreTrainedModel
from ...utils import add_start_docstrings, add_start_docstrings_to_model_forward, logging, replace_return_docstrings
from ..auto.configuration_auto import AutoConfig
Expand Down Expand Up @@ -514,6 +514,8 @@ def forward(
return_dict=return_dict,
**kwargs_encoder,
)
elif isinstance(encoder_outputs, tuple):
encoder_outputs = BaseModelOutput(*encoder_outputs)

encoder_hidden_states = encoder_outputs[0]

Expand Down
4 changes: 3 additions & 1 deletion src/transformers/models/vision_encoder_decoder/modeling_vision_encoder_decoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@
from torch.nn import CrossEntropyLoss

from ...configuration_utils import PretrainedConfig
from ...modeling_outputs import Seq2SeqLMOutput
from ...modeling_outputs import BaseModelOutput, Seq2SeqLMOutput
from ...modeling_utils import PreTrainedModel
from ...utils import add_start_docstrings, add_start_docstrings_to_model_forward, logging, replace_return_docstrings
from ..auto.configuration_auto import AutoConfig
Expand Down Expand Up @@ -466,6 +466,8 @@ def forward(
return_dict=return_dict,
**kwargs_encoder,
)
elif isinstance(encoder_outputs, tuple):
encoder_outputs = BaseModelOutput(*encoder_outputs)

encoder_hidden_states = encoder_outputs[0]

Expand Down
16 changes: 16 additions & 0 deletions tests/encoder_decoder/test_modeling_encoder_decoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -142,6 +142,22 @@ def check_encoder_decoder_model(
outputs_encoder_decoder["encoder_last_hidden_state"].shape, (input_ids.shape + (config.hidden_size,))
)

# Test passing encoder_outputs as tuple.
encoder_outputs = (encoder_hidden_states,)
outputs_encoder_decoder = enc_dec_model(
encoder_outputs=encoder_outputs,
decoder_input_ids=decoder_input_ids,
attention_mask=attention_mask,
decoder_attention_mask=decoder_attention_mask,
)

self.assertEqual(
outputs_encoder_decoder["logits"].shape, (decoder_input_ids.shape + (decoder_config.vocab_size,))
)
self.assertEqual(
outputs_encoder_decoder["encoder_last_hidden_state"].shape, (input_ids.shape + (config.hidden_size,))
)

def check_encoder_decoder_model_from_pretrained_using_model_paths(
self,
config,
Expand Down