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

ultralytics 8.0.47 Docker and reformat updates (#1153)

Browse source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Glenn Jocher 2023-02-25 22:49:19 -08:00 • committed by GitHub
parent d4be4cb24b
commit a58f766f94
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
41 changed files with 224 additions and 201 deletions
Download patch file Download diff file Expand all files Collapse all files

10
ultralytics/yolo/data/augment.py
View file

@ -564,7 +564,7 @@ class Albumentations:
A.CLAHE(p=0.01),
A.RandomBrightnessContrast(p=0.0),
A.RandomGamma(p=0.0),
A.ImageCompression(quality_lower=75, p=0.0),] # transforms
A.ImageCompression(quality_lower=75, p=0.0)] # transforms
self.transform = A.Compose(T, bbox_params=A.BboxParams(format='yolo', label_fields=['class_labels']))
LOGGER.info(prefix + ', '.join(f'{x}'.replace('always_apply=False, ', '') for x in T if x.p))
@ -671,14 +671,14 @@ def v8_transforms(dataset, imgsz, hyp):
shear=hyp.shear,
perspective=hyp.perspective,
pre_transform=LetterBox(new_shape=(imgsz, imgsz)),
),])
)])
return Compose([
pre_transform,
MixUp(dataset, pre_transform=pre_transform, p=hyp.mixup),
Albumentations(p=1.0),
RandomHSV(hgain=hyp.hsv_h, sgain=hyp.hsv_s, vgain=hyp.hsv_v),
RandomFlip(direction='vertical', p=hyp.flipud),
RandomFlip(direction='horizontal', p=hyp.fliplr),]) # transforms
RandomFlip(direction='horizontal', p=hyp.fliplr)]) # transforms
# Classification augmentations -----------------------------------------------------------------------------------------
@ -719,8 +719,8 @@ def classify_albumentations(
if vflip > 0:
T += [A.VerticalFlip(p=vflip)]
if jitter > 0:
color_jitter = (float(jitter),) * 3 # repeat value for brightness, contrast, saturation, 0 hue
T += [A.ColorJitter(*color_jitter, 0)]
jitter = float(jitter)
T += [A.ColorJitter(jitter, jitter, jitter, 0)] # brightness, contrast, saturation, 0 hue
else: # Use fixed crop for eval set (reproducibility)
T = [A.SmallestMaxSize(max_size=size), A.CenterCrop(height=size, width=size)]
T += [A.Normalize(mean=mean, std=std), ToTensorV2()] # Normalize and convert to Tensor