Skip to content

Fixed Caltech-101 and Caltech-256 broken links with the official ones #9205

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

Merged
merged 4 commits into from
Sep 9, 2025
+13 −12
Merged

Fixed Caltech-101 and Caltech-256 broken links with the official ones #9205

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
7607454
Fixed Caltech-101 and Caltech-256 broken links with the official ones
hrsvrn Sep 4, 2025
c99aaa0
used the reccomended method for unzipping the files
hrsvrn Sep 5, 2025
bb31716
Merge branch 'main' into main
AntoineSimoulin Sep 8, 2025
3bb37f4
lint
AntoineSimoulin Sep 8, 2025
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
27 changes: 14 additions & 13 deletions torchvision/datasets/caltech.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,10 @@
import os.path
from pathlib import Path
from typing import Any, Callable, Optional, Union

import shutil
from PIL import Image

from .utils import download_and_extract_archive, verify_str_arg
from .utils import download_and_extract_archive, verify_str_arg,extract_archive
from .vision import VisionDataset


Expand Down Expand Up @@ -133,17 +133,18 @@ def download(self) -> None:
return

download_and_extract_archive(
"https://drive.google.com/file/d/137RyRjvTBkBiIfeYBNZBtViDHQ6_Ewsp",
self.root,
filename="101_ObjectCategories.tar.gz",
md5="b224c7392d521a49829488ab0f1120d9",
)
download_and_extract_archive(
"https://drive.google.com/file/d/175kQy3UsZ0wUEHZjqkUDdNVssr7bgh_m",
self.root,
filename="Annotations.tar",
md5="6f83eeb1f24d99cab4eb377263132c91",
"https://data.caltech.edu/records/mzrjq-6wc02/files/caltech-101.zip",
download_root=self.root,
filename="caltech-101.zip",
md5="3138e1922a9193bfa496528edbbc45d0",
)
extracted_dir = os.path.join(self.root, "caltech-101")
extract_archive(os.path.join(extracted_dir, "101_ObjectCategories.tar.gz"), self.root)
extract_archive(os.path.join(extracted_dir, "Annotations.tar.gz"), self.root) # Note: Annotations is now also .tar.gz in the new archive
shutil.rmtree(extracted_dir)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should we re-use the code from other datasets? For instance in "mnist.py" to extract all possible subdirectories?

for gzip_file in os.listdir(gzip_folder):
    if gzip_file.endswith(".gz"):
        extract_archive(os.path.join(gzip_folder, gzip_file), self.raw_folder)
    shutil.rmtree(gzip_folder)

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes that works as well.. I will change this one :)

os.remove(os.path.join(self.root, "caltech-101.zip"))



def extra_repr(self) -> str:
return "Target type: {target_type}".format(**self.__dict__)
Expand Down Expand Up @@ -233,7 +234,7 @@ def download(self) -> None:
return

download_and_extract_archive(
"https://drive.google.com/file/d/1r6o0pSROcV1_VwT4oSjA2FBUSCWGuxLK",
"https://data.caltech.edu/records/nyy15-4j048/files/256_ObjectCategories.tar",
self.root,
filename="256_ObjectCategories.tar",
md5="67b4f42ca05d46448c6bb8ecd2220f6d",
Expand Down
Loading