Skip to content

Display dataset download progress #267

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

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Display dataset download progress #267

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
20 changes: 18 additions & 2 deletions benchmark/dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,9 +3,11 @@
import tarfile
import urllib.request
from dataclasses import dataclass, field
from typing import Dict, Optional
from typing import Callable, Dict, Optional
from urllib.request import build_opener, install_opener

import tqdm

from benchmark import DATASETS_DIR
from dataset_reader.ann_compound_reader import AnnCompoundReader
from dataset_reader.ann_h5_reader import AnnH5Reader
Expand Down Expand Up @@ -54,7 +56,12 @@ def download(self):

if self.config.link:
print(f"Downloading {self.config.link}...")
tmp_path, _ = urllib.request.urlretrieve(self.config.link)
with tqdm.tqdm(
unit="B", unit_scale=True, miniters=1, dynamic_ncols=True, disable=None
) as t:
tmp_path, _ = urllib.request.urlretrieve(
self.config.link, reporthook=_tqdm_reporthook(t)
)

if self.config.link.endswith(".tgz") or self.config.link.endswith(
".tar.gz"
Expand All @@ -76,6 +83,15 @@ def get_reader(self, normalize: bool) -> BaseReader:
return reader_class(DATASETS_DIR / self.config.path, normalize=normalize)


def _tqdm_reporthook(t: tqdm.tqdm) -> Callable[[int, int, int], None]:
def reporthook(blocknum: int, block_size: int, total_size: int) -> None:
if total_size > 0:
t.total = total_size
t.update(blocknum * block_size - t.n)

return reporthook


if __name__ == "__main__":
dataset = Dataset(
{
Expand Down