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

Generalize problem_type to all sequence classification models (#14180)

Browse Source 
* Generalize problem_type to all classification models

* Missing import

* Deberta BC and fix tests

* Fix template

* Missing imports

* Revert change to reformer test

* Fix style
This commit is contained in:
Sylvain Gugger
2021-10-29 10:32:56 -04:00
committed by GitHub
parent 4ab6a4a086
commit c28bc80bbb
38 changed files with 474 additions and 191 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
templates/adding_a_new_model/cookiecutter-template-{{cookiecutter.modelname}}/modeling_{{cookiecutter.lowercase_modelname}}.py
View File

@@ -24,7 +24,7 @@ import torch
import torch.utils.checkpoint
from packaging import version
from torch import nn
from torch.nn import CrossEntropyLoss, MSELoss
from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
from ...activations import ACT2FN
from ...file_utils import (
@@ -1265,14 +1265,26 @@ class {{cookiecutter.camelcase_modelname}}ForSequenceClassification({{cookiecutt
loss = None
if labels is not None:
if self.num_labels == 1:
# We are doing regression
if self.config.problem_type is None:
if self.num_labels == 1:
self.config.problem_type = "regression"
elif self.num_labels > 1 and (labels.dtype == torch.long or labels.dtype == torch.int):
self.config.problem_type = "single_label_classification"
else:
self.config.problem_type = "multi_label_classification"
if self.config.problem_type == "regression":
loss_fct = MSELoss()
loss = loss_fct(logits.view(-1), labels.view(-1))
else:
if self.num_labels == 1:
loss = loss_fct(logits.squeeze(), labels.squeeze())
else:
loss = loss_fct(logits, labels)
elif self.config.problem_type == "single_label_classification":
loss_fct = CrossEntropyLoss()
loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
elif self.config.problem_type == "multi_label_classification":
loss_fct = BCEWithLogitsLoss()
loss = loss_fct(logits, labels)
if not return_dict:
output = (logits,) + outputs[1:]
return ((loss,) + output) if loss is not None else output
@@ -1564,7 +1576,7 @@ from typing import Optional, Tuple
import torch
from torch import nn
from torch.nn import CrossEntropyLoss
from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
from ...activations import ACT2FN
from ...file_utils import (
@@ -2981,9 +2993,26 @@ class {{cookiecutter.camelcase_modelname}}ForSequenceClassification({{cookiecutt
loss = None
if labels is not None:
loss_fct = CrossEntropyLoss()
loss = loss_fct(logits.view(-1, self.config.num_labels), labels.view(-1))
if self.config.problem_type is None:
if self.config.num_labels == 1:
self.config.problem_type = "regression"
elif self.config.num_labels > 1 and (labels.dtype == torch.long or labels.dtype == torch.int):
self.config.problem_type = "single_label_classification"
else:
self.config.problem_type = "multi_label_classification"
if self.config.problem_type == "regression":
loss_fct = MSELoss()
if self.config.num_labels == 1:
loss = loss_fct(logits.squeeze(), labels.squeeze())
else:
loss = loss_fct(logits, labels)
elif self.config.problem_type == "single_label_classification":
loss_fct = CrossEntropyLoss()
loss = loss_fct(logits.view(-1, self.config.num_labels), labels.view(-1))
elif self.config.problem_type == "multi_label_classification":
loss_fct = BCEWithLogitsLoss()
loss = loss_fct(logits, labels)
if not return_dict:
output = (logits,) + outputs[1:]
return ((loss,) + output) if loss is not None else output