HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

ultralytics 8.3.8 replace contextlib with try for speed (#16782)

Browse source 
Signed-off-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
This commit is contained in:
Glenn Jocher 2024-10-08 21:02:40 +02:00 • committed by GitHub
parent 1e6c454460
commit a6a577961f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 115 additions and 88 deletions
Download patch file Download diff file Expand all files Collapse all files

46
ultralytics/data/dataset.py
View file

@ -1,6 +1,5 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
import contextlib
import json
from collections import defaultdict
from itertools import repeat
@ -483,7 +482,7 @@ class ClassificationDataset:
desc = f"{self.prefix}Scanning {self.root}..."
path = Path(self.root).with_suffix(".cache") # *.cache file path
with contextlib.suppress(FileNotFoundError, AssertionError, AttributeError):
try:
cache = load_dataset_cache_file(path) # attempt to load a *.cache file
assert cache["version"] == DATASET_CACHE_VERSION # matches current version
assert cache["hash"] == get_hash([x[0] for x in self.samples]) # identical hash
@ -495,24 +494,25 @@ class ClassificationDataset:
LOGGER.info("\n".join(cache["msgs"])) # display warnings
return samples
# Run scan if *.cache retrieval failed
nf, nc, msgs, samples, x = 0, 0, [], [], {}
with ThreadPool(NUM_THREADS) as pool:
results = pool.imap(func=verify_image, iterable=zip(self.samples, repeat(self.prefix)))
pbar = TQDM(results, desc=desc, total=len(self.samples))
for sample, nf_f, nc_f, msg in pbar:
if nf_f:
samples.append(sample)
if msg:
msgs.append(msg)
nf += nf_f
nc += nc_f
pbar.desc = f"{desc} {nf} images, {nc} corrupt"
pbar.close()
if msgs:
LOGGER.info("\n".join(msgs))
x["hash"] = get_hash([x[0] for x in self.samples])
x["results"] = nf, nc, len(samples), samples
x["msgs"] = msgs # warnings
save_dataset_cache_file(self.prefix, path, x, DATASET_CACHE_VERSION)
return samples
except (FileNotFoundError, AssertionError, AttributeError):
# Run scan if *.cache retrieval failed
nf, nc, msgs, samples, x = 0, 0, [], [], {}
with ThreadPool(NUM_THREADS) as pool:
results = pool.imap(func=verify_image, iterable=zip(self.samples, repeat(self.prefix)))
pbar = TQDM(results, desc=desc, total=len(self.samples))
for sample, nf_f, nc_f, msg in pbar:
if nf_f:
samples.append(sample)
if msg:
msgs.append(msg)
nf += nf_f
nc += nc_f
pbar.desc = f"{desc} {nf} images, {nc} corrupt"
pbar.close()
if msgs:
LOGGER.info("\n".join(msgs))
x["hash"] = get_hash([x[0] for x in self.samples])
x["results"] = nf, nc, len(samples), samples
x["msgs"] = msgs # warnings
save_dataset_cache_file(self.prefix, path, x, DATASET_CACHE_VERSION)
return samples

5
ultralytics/data/utils.py
View file

@ -1,6 +1,5 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
import contextlib
import hashlib
import json
import os
@ -60,12 +59,14 @@ def exif_size(img: Image.Image):
"""Returns exif-corrected PIL size."""
s = img.size # (width, height)
if img.format == "JPEG": # only support JPEG images
with contextlib.suppress(Exception):
try:
exif = img.getexif()
if exif:
rotation = exif.get(274, None) # the EXIF key for the orientation tag is 274
if rotation in {6, 8}: # rotation 270 or 90
s = s[1], s[0]
except: # noqa E722
pass
return s