Spaces:
Running
on
A10G
Running
on
A10G
File size: 3,746 Bytes
320e465 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 |
import math
import os
import requests
from torch.hub import download_url_to_file, get_dir
from tqdm import tqdm
from urllib.parse import urlparse
def sizeof_fmt(size, suffix='B'):
"""Get human readable file size.
Args:
size (int): File size.
suffix (str): Suffix. Default: 'B'.
Return:
str: Formated file siz.
"""
for unit in ['', 'K', 'M', 'G', 'T', 'P', 'E', 'Z']:
if abs(size) < 1024.0:
return f'{size:3.1f} {unit}{suffix}'
size /= 1024.0
return f'{size:3.1f} Y{suffix}'
def download_file_from_google_drive(file_id, save_path):
"""Download files from google drive.
Ref:
https://stackoverflow.com/questions/25010369/wget-curl-large-file-from-google-drive # noqa E501
Args:
file_id (str): File id.
save_path (str): Save path.
"""
session = requests.Session()
URL = 'https://docs.google.com/uc?export=download'
params = {'id': file_id}
response = session.get(URL, params=params, stream=True)
token = get_confirm_token(response)
if token:
params['confirm'] = token
response = session.get(URL, params=params, stream=True)
# get file size
response_file_size = session.get(URL, params=params, stream=True, headers={'Range': 'bytes=0-2'})
print(response_file_size)
if 'Content-Range' in response_file_size.headers:
file_size = int(response_file_size.headers['Content-Range'].split('/')[1])
else:
file_size = None
save_response_content(response, save_path, file_size)
def get_confirm_token(response):
for key, value in response.cookies.items():
if key.startswith('download_warning'):
return value
return None
def save_response_content(response, destination, file_size=None, chunk_size=32768):
if file_size is not None:
pbar = tqdm(total=math.ceil(file_size / chunk_size), unit='chunk')
readable_file_size = sizeof_fmt(file_size)
else:
pbar = None
with open(destination, 'wb') as f:
downloaded_size = 0
for chunk in response.iter_content(chunk_size):
downloaded_size += chunk_size
if pbar is not None:
pbar.update(1)
pbar.set_description(f'Download {sizeof_fmt(downloaded_size)} / {readable_file_size}')
if chunk: # filter out keep-alive new chunks
f.write(chunk)
if pbar is not None:
pbar.close()
def load_file_from_url(url, model_dir=None, progress=True, file_name=None):
"""Load file form http url, will download models if necessary.
Ref:https://github.com/1adrianb/face-alignment/blob/master/face_alignment/utils.py
Args:
url (str): URL to be downloaded.
model_dir (str): The path to save the downloaded model. Should be a full path. If None, use pytorch hub_dir.
Default: None.
progress (bool): Whether to show the download progress. Default: True.
file_name (str): The downloaded file name. If None, use the file name in the url. Default: None.
Returns:
str: The path to the downloaded file.
"""
if model_dir is None: # use the pytorch hub_dir
hub_dir = get_dir()
model_dir = os.path.join(hub_dir, 'checkpoints')
os.makedirs(model_dir, exist_ok=True)
parts = urlparse(url)
filename = os.path.basename(parts.path)
if file_name is not None:
filename = file_name
cached_file = os.path.abspath(os.path.join(model_dir, filename))
if not os.path.exists(cached_file):
print(f'Downloading: "{url}" to {cached_file}\n')
download_url_to_file(url, cached_file, hash_prefix=None, progress=progress)
return cached_file |