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

[FIX] Error in unpacking archive of CORD dataset #1190

Merged
merged 2 commits into from
May 1, 2023
Merged

[FIX] Error in unpacking archive of CORD dataset #1190

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7b11315
[FIX] Error in unpacking archive of CORD dataset
HamzaGbada Apr 30, 2023
4bea0da
[FIX] Error in unpacking archive of CORD dataset
HamzaGbada Apr 30, 2023
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
6 changes: 4 additions & 2 deletions doctr/datasets/cord.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,11 +38,13 @@ class CORD(VisionDataset):
TRAIN = (
"https://doctr-static.mindee.com/models?id=v0.1.1/cord_train.zip&src=0",
"45f9dc77f126490f3e52d7cb4f70ef3c57e649ea86d19d862a2757c9c455d7f8",
"cord_train.zip",
)

TEST = (
"https://doctr-static.mindee.com/models?id=v0.1.1/cord_test.zip&src=0",
"8c895e3d6f7e1161c5b7245e3723ce15c04d84be89eaa6093949b75a66fb3c58",
"cord_test.zip",
)

def __init__(
Expand All @@ -52,10 +54,10 @@ def __init__(
recognition_task: bool = False,
**kwargs: Any,
) -> None:
url, sha256 = self.TRAIN if train else self.TEST
url, sha256, name = self.TRAIN if train else self.TEST
super().__init__(
url,
None,
name,
sha256,
True,
pre_transforms=convert_target_to_relative if not recognition_task else None,
Expand Down
2 changes: 1 addition & 1 deletion tests/pytorch/test_datasets_pt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -414,7 +414,7 @@ def test_funsd(input_size, num_samples, rotate, recognition, mock_funsd_dataset)
)
def test_cord(input_size, num_samples, rotate, recognition, mock_cord_dataset):
# monkeypatch the path to temporary dataset
datasets.CORD.TRAIN = (mock_cord_dataset, None)
datasets.CORD.TRAIN = (mock_cord_dataset, None, "cord_train.zip")

ds = datasets.CORD(
train=True,
Expand Down
2 changes: 1 addition & 1 deletion tests/tensorflow/test_datasets_tf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -388,7 +388,7 @@ def test_funsd(input_size, num_samples, rotate, recognition, mock_funsd_dataset)
)
def test_cord(input_size, num_samples, rotate, recognition, mock_cord_dataset):
# monkeypatch the path to temporary dataset
datasets.CORD.TRAIN = (mock_cord_dataset, None)
datasets.CORD.TRAIN = (mock_cord_dataset, None, "cord_train.zip")

ds = datasets.CORD(
train=True,
Expand Down