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

Updated cache v0.2 with hashlib #3350

Merged
merged 2 commits into from
May 26, 2021
Merged

Updated cache v0.2 with hashlib #3350

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2a84878
Update cache v0.2 to include parent hash
glenn-jocher May 26, 2021
c53aeab
Update datasets.py
glenn-jocher May 26, 2021
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
16 changes: 10 additions & 6 deletions utils/datasets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
# Dataset utils and dataloaders

import glob
import hashlib
import logging
import math
import os
Expand Down Expand Up @@ -36,9 +37,12 @@
break


def get_hash(files):
# Returns a single hash value of a list of files
return sum(os.path.getsize(f) for f in files if os.path.isfile(f))
def get_hash(paths):
# Returns a single hash value of a list of paths (files or dirs)
size = sum(os.path.getsize(p) for p in paths if os.path.exists(p)) # sizes
h = hashlib.md5(str(size).encode()) # hash sizes
h.update(''.join(paths).encode()) # hash paths
return h.hexdigest() # return hash


def exif_size(img):
Expand Down Expand Up @@ -383,7 +387,7 @@ def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, r
cache_path = (p if p.is_file() else Path(self.label_files[0]).parent).with_suffix('.cache') # cached labels
if cache_path.is_file():
cache, exists = torch.load(cache_path), True # load
if cache['hash'] != get_hash(self.label_files + self.img_files) or 'version' not in cache: # changed
if cache['hash'] != get_hash(self.label_files + self.img_files): # changed
cache, exists = self.cache_labels(cache_path, prefix), False # re-cache
else:
cache, exists = self.cache_labels(cache_path, prefix), False # cache
Expand Down Expand Up @@ -501,9 +505,9 @@ def cache_labels(self, path=Path('./labels.cache'), prefix=''):

x['hash'] = get_hash(self.label_files + self.img_files)
x['results'] = nf, nm, ne, nc, i + 1
x['version'] = 0.1 # cache version
x['version'] = 0.2 # cache version
try:
torch.save(x, path) # save for next time
torch.save(x, path) # save cache for next time
logging.info(f'{prefix}New cache created: {path}')
except Exception as e:
logging.info(f'{prefix}WARNING: Cache directory {path.parent} is not writeable: {e}') # path not writeable
Expand Down