riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-02 19:21:31 +06:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Fix tensor label type inference in default collator (#5250)

Browse Source 
* allow tensor label inputs to default collator

* replace try/except with type check
This commit is contained in:
Joe Davison 2020-07-01 10:40:14 -06:00 committed by GitHub
parent fe81f7d12c
commit 35befd9ce3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/transformers/data/data_collator.py
View File

@ -43,7 +43,8 @@ def default_data_collator(features: List[InputDataClass]) -> Dict[str, torch.Ten
# Ensure that tensor is created with the correct type
# (it should be automatically the case, but let's make sure of it.)
if "label" in first and first["label"] is not None:
dtype = torch.long if type(first["label"]) is int else torch.float
label = first["label"].item() if isinstance(first["label"], torch.Tensor) else first["label"]
dtype = torch.long if isinstance(label, int) else torch.float
batch["labels"] = torch.tensor([f["label"] for f in features], dtype=dtype)
elif "label_ids" in first and first["label_ids"] is not None:
if isinstance(first["label_ids"], torch.Tensor):

8
tests/test_trainer.py
View File

@ -44,6 +44,14 @@ class DataCollatorIntegrationTest(unittest.TestCase):
self.assertEqual(batch["labels"].dtype, torch.long)
self.assertEqual(batch["inputs"].shape, torch.Size([8, 10]))
# Labels can already be tensors
features = [{"label": torch.tensor(i), "inputs": torch.randint(10, [10])} for i in range(8)]
batch = default_data_collator(features)
self.assertEqual(batch["labels"].dtype, torch.long)
self.assertTrue(batch["labels"].equal(torch.tensor(list(range(8)))))
self.assertEqual(batch["labels"].dtype, torch.long)
self.assertEqual(batch["inputs"].shape, torch.Size([8, 10]))
def test_default_with_no_labels(self):
features = [{"label": None, "inputs": [0, 1, 2, 3, 4, 5]} for i in range(8)]
batch = default_data_collator(features)