ultralytics 8.0.169TQDM, INTERP_LINEAR and RTDETR load_image() updates (#4704)
Co-authored-by: Rustem Galiullin <rustemgal@gmail.com> Co-authored-by: Rustem Galiullin <rustem.galiullin@bayanat.ai> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Glenn Jocher
GitHub
parent
a4fabfdacf
commit
187b504d68
23 changed files with 101 additions and 120 deletions
|
|
@ -13,9 +13,8 @@ import cv2
|
|||
import numpy as np
|
||||
import psutil
|
||||
from torch.utils.data import Dataset
|
||||
from tqdm import tqdm
|
||||
|
||||
from ultralytics.utils import DEFAULT_CFG, LOCAL_RANK, LOGGER, NUM_THREADS, TQDM_BAR_FORMAT
|
||||
from ultralytics.utils import DEFAULT_CFG, LOCAL_RANK, LOGGER, NUM_THREADS, TQDM
|
||||
|
||||
from .utils import HELP_URL, IMG_FORMATS
|
||||
|
||||
|
|
@ -141,7 +140,7 @@ class BaseDataset(Dataset):
|
|||
if self.single_cls:
|
||||
self.labels[i]['cls'][:, 0] = 0
|
||||
|
||||
def load_image(self, i):
|
||||
def load_image(self, i, rect_mode=True):
|
||||
"""Loads 1 image from dataset index 'i', returns (im, resized hw)."""
|
||||
im, f, fn = self.ims[i], self.im_files[i], self.npy_files[i]
|
||||
if im is None: # not cached in RAM
|
||||
|
|
@ -152,11 +151,13 @@ class BaseDataset(Dataset):
|
|||
if im is None:
|
||||
raise FileNotFoundError(f'Image Not Found {f}')
|
||||
h0, w0 = im.shape[:2] # orig hw
|
||||
r = self.imgsz / max(h0, w0) # ratio
|
||||
if r != 1: # if sizes are not equal
|
||||
interp = cv2.INTER_LINEAR if (self.augment or r > 1) else cv2.INTER_AREA
|
||||
im = cv2.resize(im, (min(math.ceil(w0 * r), self.imgsz), min(math.ceil(h0 * r), self.imgsz)),
|
||||
interpolation=interp)
|
||||
if rect_mode: # resize long side to imgsz while maintaining aspect ratio
|
||||
r = self.imgsz / max(h0, w0) # ratio
|
||||
if r != 1: # if sizes are not equal
|
||||
w, h = (min(math.ceil(w0 * r), self.imgsz), min(math.ceil(h0 * r), self.imgsz))
|
||||
im = cv2.resize(im, (w, h), interpolation=cv2.INTER_LINEAR)
|
||||
elif not (h0 == w0 == self.imgsz): # resize by stretching image to square imgsz
|
||||
im = cv2.resize(im, (self.imgsz, self.imgsz), interpolation=cv2.INTER_LINEAR)
|
||||
|
||||
# Add to buffer if training with augmentations
|
||||
if self.augment:
|
||||
|
|
@ -176,7 +177,7 @@ class BaseDataset(Dataset):
|
|||
fcn = self.cache_images_to_disk if cache == 'disk' else self.load_image
|
||||
with ThreadPool(NUM_THREADS) as pool:
|
||||
results = pool.imap(fcn, range(self.ni))
|
||||
pbar = tqdm(enumerate(results), total=self.ni, bar_format=TQDM_BAR_FORMAT, disable=LOCAL_RANK > 0)
|
||||
pbar = TQDM(enumerate(results), total=self.ni, disable=LOCAL_RANK > 0)
|
||||
for i, x in pbar:
|
||||
if cache == 'disk':
|
||||
b += self.npy_files[i].stat().st_size
|
||||
|
|
@ -190,7 +191,7 @@ class BaseDataset(Dataset):
|
|||
"""Saves an image as an *.npy file for faster loading."""
|
||||
f = self.npy_files[i]
|
||||
if not f.exists():
|
||||
np.save(f.as_posix(), cv2.imread(self.im_files[i]))
|
||||
np.save(f.as_posix(), cv2.imread(self.im_files[i]), allow_pickle=False)
|
||||
|
||||
def check_cache_ram(self, safety_margin=0.5):
|
||||
"""Check image caching requirements vs available memory."""
|
||||
|
|
|
|||
|
|
@ -7,7 +7,8 @@ from pathlib import Path
|
|||
|
||||
import cv2
|
||||
import numpy as np
|
||||
from tqdm import tqdm
|
||||
|
||||
from ultralytics.utils import TQDM
|
||||
|
||||
|
||||
def coco91_to_coco80_class():
|
||||
|
|
@ -90,7 +91,7 @@ def convert_coco(labels_dir='../coco/annotations/', use_segments=False, use_keyp
|
|||
imgToAnns[ann['image_id']].append(ann)
|
||||
|
||||
# Write labels file
|
||||
for img_id, anns in tqdm(imgToAnns.items(), desc=f'Annotations {json_file}'):
|
||||
for img_id, anns in TQDM(imgToAnns.items(), desc=f'Annotations {json_file}'):
|
||||
img = images[f'{img_id:d}']
|
||||
h, w, f = img['height'], img['width'], img['file_name']
|
||||
|
||||
|
|
@ -222,7 +223,7 @@ def convert_dota_to_yolo_obb(dota_root_path: str):
|
|||
save_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
image_paths = list(image_dir.iterdir())
|
||||
for image_path in tqdm(image_paths, desc=f'Processing {phase} images'):
|
||||
for image_path in TQDM(image_paths, desc=f'Processing {phase} images'):
|
||||
if image_path.suffix != '.png':
|
||||
continue
|
||||
image_name_without_ext = image_path.stem
|
||||
|
|
|
|||
|
|
@ -8,9 +8,8 @@ import cv2
|
|||
import numpy as np
|
||||
import torch
|
||||
import torchvision
|
||||
from tqdm import tqdm
|
||||
|
||||
from ultralytics.utils import LOCAL_RANK, NUM_THREADS, TQDM_BAR_FORMAT, colorstr, is_dir_writeable
|
||||
from ultralytics.utils import LOCAL_RANK, NUM_THREADS, TQDM, colorstr, is_dir_writeable
|
||||
|
||||
from .augment import Compose, Format, Instances, LetterBox, classify_albumentations, classify_transforms, v8_transforms
|
||||
from .base import BaseDataset
|
||||
|
|
@ -60,7 +59,7 @@ class YOLODataset(BaseDataset):
|
|||
iterable=zip(self.im_files, self.label_files, repeat(self.prefix),
|
||||
repeat(self.use_keypoints), repeat(len(self.data['names'])), repeat(nkpt),
|
||||
repeat(ndim)))
|
||||
pbar = tqdm(results, desc=desc, total=total, bar_format=TQDM_BAR_FORMAT)
|
||||
pbar = TQDM(results, desc=desc, total=total)
|
||||
for im_file, lb, shape, segments, keypoint, nm_f, nf_f, ne_f, nc_f, msg in pbar:
|
||||
nm += nm_f
|
||||
nf += nf_f
|
||||
|
|
@ -107,7 +106,7 @@ class YOLODataset(BaseDataset):
|
|||
nf, nm, ne, nc, n = cache.pop('results') # found, missing, empty, corrupt, total
|
||||
if exists and LOCAL_RANK in (-1, 0):
|
||||
d = f'Scanning {cache_path}... {nf} images, {nm + ne} backgrounds, {nc} corrupt'
|
||||
tqdm(None, desc=self.prefix + d, total=n, initial=n, bar_format=TQDM_BAR_FORMAT) # display results
|
||||
TQDM(None, desc=self.prefix + d, total=n, initial=n) # display results
|
||||
if cache['msgs']:
|
||||
LOGGER.info('\n'.join(cache['msgs'])) # display warnings
|
||||
|
||||
|
|
@ -244,7 +243,7 @@ class ClassificationDataset(torchvision.datasets.ImageFolder):
|
|||
im = self.samples[i][3] = cv2.imread(f)
|
||||
elif self.cache_disk:
|
||||
if not fn.exists(): # load npy
|
||||
np.save(fn.as_posix(), cv2.imread(f))
|
||||
np.save(fn.as_posix(), cv2.imread(f), allow_pickle=False)
|
||||
im = np.load(fn)
|
||||
else: # read image
|
||||
im = cv2.imread(f) # BGR
|
||||
|
|
@ -269,7 +268,7 @@ class ClassificationDataset(torchvision.datasets.ImageFolder):
|
|||
nf, nc, n, samples = cache.pop('results') # found, missing, empty, corrupt, total
|
||||
if LOCAL_RANK in (-1, 0):
|
||||
d = f'{desc} {nf} images, {nc} corrupt'
|
||||
tqdm(None, desc=d, total=n, initial=n, bar_format=TQDM_BAR_FORMAT)
|
||||
TQDM(None, desc=d, total=n, initial=n)
|
||||
if cache['msgs']:
|
||||
LOGGER.info('\n'.join(cache['msgs'])) # display warnings
|
||||
return samples
|
||||
|
|
@ -278,7 +277,7 @@ class ClassificationDataset(torchvision.datasets.ImageFolder):
|
|||
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), bar_format=TQDM_BAR_FORMAT)
|
||||
pbar = TQDM(results, desc=desc, total=len(self.samples))
|
||||
for sample, nf_f, nc_f, msg in pbar:
|
||||
if nf_f:
|
||||
samples.append(sample)
|
||||
|
|
|
|||
|
|
@ -15,11 +15,10 @@ from tarfile import is_tarfile
|
|||
import cv2
|
||||
import numpy as np
|
||||
from PIL import Image, ImageOps
|
||||
from tqdm import tqdm
|
||||
|
||||
from ultralytics.nn.autobackend import check_class_names
|
||||
from ultralytics.utils import (DATASETS_DIR, LOGGER, NUM_THREADS, ROOT, SETTINGS_YAML, clean_url, colorstr, emojis,
|
||||
yaml_load)
|
||||
from ultralytics.utils import (DATASETS_DIR, LOGGER, NUM_THREADS, ROOT, SETTINGS_YAML, TQDM, clean_url, colorstr,
|
||||
emojis, yaml_load)
|
||||
from ultralytics.utils.checks import check_file, check_font, is_ascii
|
||||
from ultralytics.utils.downloads import download, safe_download, unzip_file
|
||||
from ultralytics.utils.ops import segments2boxes
|
||||
|
|
@ -510,7 +509,7 @@ class HUBDatasetStats:
|
|||
use_keypoints=self.task == 'pose')
|
||||
x = np.array([
|
||||
np.bincount(label['cls'].astype(int).flatten(), minlength=self.data['nc'])
|
||||
for label in tqdm(dataset.labels, total=len(dataset), desc='Statistics')]) # shape(128x80)
|
||||
for label in TQDM(dataset.labels, total=len(dataset), desc='Statistics')]) # shape(128x80)
|
||||
self.stats[split] = {
|
||||
'instance_stats': {
|
||||
'total': int(x.sum()),
|
||||
|
|
@ -541,7 +540,7 @@ class HUBDatasetStats:
|
|||
continue
|
||||
dataset = YOLODataset(img_path=self.data[split], data=self.data)
|
||||
with ThreadPool(NUM_THREADS) as pool:
|
||||
for _ in tqdm(pool.imap(self._hub_ops, dataset.im_files), total=len(dataset), desc=f'{split} images'):
|
||||
for _ in TQDM(pool.imap(self._hub_ops, dataset.im_files), total=len(dataset), desc=f'{split} images'):
|
||||
pass
|
||||
LOGGER.info(f'Done. All images saved to {self.im_dir}')
|
||||
return self.im_dir
|
||||
|
|
@ -614,7 +613,7 @@ def autosplit(path=DATASETS_DIR / 'coco8/images', weights=(0.9, 0.1, 0.0), annot
|
|||
(path.parent / x).unlink() # remove existing
|
||||
|
||||
LOGGER.info(f'Autosplitting images from {path}' + ', using *.txt labeled images only' * annotated_only)
|
||||
for i, img in tqdm(zip(indices, files), total=n):
|
||||
for i, img in TQDM(zip(indices, files), total=n):
|
||||
if not annotated_only or Path(img2label_paths([str(img)])[0]).exists(): # check label
|
||||
with open(path.parent / txt[i], 'a') as f:
|
||||
f.write(f'./{img.relative_to(path.parent).as_posix()}' + '\n') # add image to txt file
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue