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

Fixed the broken devkit link #944

Merged
merged 4 commits into from
Mar 28, 2023
Merged

Fixed the broken devkit link #944

Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
4ed7d4d
Fixed the broken devkit link
NeoKish Nov 9, 2022
c1201e5
Merge branch 'master' into neokish-906-pr-1
Borda Mar 28, 2023
f0375b4
Update imagenet_datamodule.py
Borda Mar 28, 2023
d24963c
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Mar 28, 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
30 changes: 14 additions & 16 deletions pl_bolts/datamodules/imagenet_datamodule.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,22 +126,20 @@ def prepare_data(self) -> None:
for split in ["train", "val"]:
files = os.listdir(os.path.join(self.data_dir, split))
if "meta.bin" not in files:
raise FileNotFoundError(
"""
no meta.bin present. Imagenet is no longer automatically downloaded by PyTorch.
To get imagenet:
1. download yourself from http://www.image-net.org/challenges/LSVRC/2012/downloads
2. download the devkit (ILSVRC2012_devkit_t12.tar.gz)
3. generate the meta.bin file using the devkit
4. copy the meta.bin file into both train and val split folders

To generate the meta.bin do the following:

from pl_bolts.datasets import UnlabeledImagenet
path = '/path/to/folder/with/ILSVRC2012_devkit_t12.tar.gz/'
UnlabeledImagenet.generate_meta_bins(path)
"""
)
raise FileNotFoundError("""
no meta.bin present. Imagenet is no longer automatically downloaded by PyTorch.
To get imagenet:

1. download the devkit (https://image-net.org/data/ILSVRC/2012/ILSVRC2012_devkit_t12.tar.gz)
2. generate the meta.bin file using the devkit
3. copy the meta.bin file into both train and val split folders

To generate the meta.bin do the following:

from pl_bolts.datasets import UnlabeledImagenet
path = '/path/to/folder/with/ILSVRC2012_devkit_t12.tar.gz/'
UnlabeledImagenet.generate_meta_bins(path)
""")

def train_dataloader(self) -> DataLoader:
"""Uses the train split of imagenet2012 and puts away a portion of it for the validation split."""
Expand Down