浏览代码

Replace `os.system('unzip file.zip')` -> `ZipFile.extractall()` (#4919)

* Replace `os.system('unzip file.zip')` -> `ZipFile.extractall()`

* Cleanup
modifyDataloader
Glenn Jocher GitHub 3 年前
父节点
当前提交
a64a4c839f
找不到此签名对应的密钥 GPG 密钥 ID: 4AEE18F83AFDEB23
共有 3 个文件被更改,包括 16 次插入12 次删除
  1. +3
    -2
      utils/datasets.py
  2. +3
    -2
      utils/downloads.py
  3. +10
    -8
      utils/general.py

+ 3
- 2
utils/datasets.py 查看文件

@@ -15,6 +15,7 @@ from itertools import repeat
from multiprocessing.pool import ThreadPool, Pool
from pathlib import Path
from threading import Thread
from zipfile import ZipFile

import cv2
import numpy as np
@@ -928,8 +929,8 @@ def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False, profil
# Unzip data.zip TODO: CONSTRAINT: path/to/abc.zip MUST unzip to 'path/to/abc/'
if str(path).endswith('.zip'): # path is data.zip
assert Path(path).is_file(), f'Error unzipping {path}, file not found'
assert os.system(f'unzip -q {path} -d {path.parent}') == 0, f'Error unzipping {path}'
dir = path.with_suffix('') # dataset directory
ZipFile(path).extractall(path=path.parent) # unzip
dir = path.with_suffix('') # dataset directory == zip name
return True, str(dir), next(dir.rglob('*.yaml')) # zipped, data_dir, yaml_path
else: # path is data.yaml
return False, None, path

+ 3
- 2
utils/downloads.py 查看文件

@@ -9,6 +9,7 @@ import subprocess
import time
import urllib
from pathlib import Path
from zipfile import ZipFile

import requests
import torch
@@ -104,8 +105,8 @@ def gdrive_download(id='16TiPfZj7htmTyhntwcZyEEAejOUxuT6m', file='tmp.zip'):
# Unzip if archive
if file.suffix == '.zip':
print('unzipping... ', end='')
os.system(f'unzip -q {file}') # unzip
file.unlink() # remove zip to free space
ZipFile(file).extractall(path=file.parent) # unzip
file.unlink() # remove zip

print(f'Done ({time.time() - t:.1f}s)')
return r

+ 10
- 8
utils/general.py 查看文件

@@ -18,6 +18,7 @@ from itertools import repeat
from multiprocessing.pool import ThreadPool
from pathlib import Path
from subprocess import check_output
from zipfile import ZipFile

import cv2
import numpy as np
@@ -353,17 +354,19 @@ def check_dataset(data, autodownload=True):
if s and autodownload: # download script
if s.startswith('http') and s.endswith('.zip'): # URL
f = Path(s).name # filename
print(f'Downloading {s} ...')
print(f'Downloading {s} to {f}...')
torch.hub.download_url_to_file(s, f)
root = path.parent if 'path' in data else '..' # unzip directory i.e. '../'
Path(root).mkdir(parents=True, exist_ok=True) # create root
r = os.system(f'unzip -q {f} -d {root} && rm {f}') # unzip
ZipFile(f).extractall(path=root) # unzip
Path(f).unlink() # remove zip
r = None # success
elif s.startswith('bash '): # bash script
print(f'Running {s} ...')
r = os.system(s)
else: # python script
r = exec(s, {'yaml': data}) # return None
print('Dataset autodownload %s\n' % ('success' if r in (0, None) else 'failure')) # print result
print(f"Dataset autodownload {f'success, saved to {root}' if r in (0, None) else 'failure'}")
else:
raise Exception('Dataset not found.')

@@ -393,12 +396,11 @@ def download(url, dir='.', unzip=True, delete=True, curl=False, threads=1):
if unzip and f.suffix in ('.zip', '.gz'):
print(f'Unzipping {f}...')
if f.suffix == '.zip':
s = f'unzip -qo {f} -d {dir}' # unzip -quiet -overwrite
ZipFile(f).extractall(path=dir) # unzip
elif f.suffix == '.gz':
s = f'tar xfz {f} --directory {f.parent}' # unzip
if delete: # delete zip file after unzip
s += f' && rm {f}'
os.system(s)
os.system(f'tar xfz {f} --directory {f.parent}') # unzip
if delete:
f.unlink() # remove zip

dir = Path(dir)
dir.mkdir(parents=True, exist_ok=True) # make directory

正在加载...
取消
保存