mirror of
https://github.com/THU-MIG/yolov10.git
synced 2025-05-23 13:34:23 +08:00
ultralytics 8.0.135 remove deprecated v5loader (#3744)
This commit is contained in:
Glenn Jocher
GitHub
parent
114470361e
commit
8ebe94d1e9
@ -1,89 +0,0 @@
|
||||
---
|
||||
description: Enhance image data with Albumentations CenterCrop, normalize, augment_hsv, replicate, random_perspective, cutout, & box_candidates.
|
||||
keywords: YOLO, object detection, data loaders, V5 augmentations, CenterCrop, normalize, random_perspective
|
||||
---
|
||||
|
||||
## Albumentations
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5augmentations.Albumentations
|
||||
<br><br>
|
||||
|
||||
## LetterBox
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5augmentations.LetterBox
|
||||
<br><br>
|
||||
|
||||
## CenterCrop
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5augmentations.CenterCrop
|
||||
<br><br>
|
||||
|
||||
## ToTensor
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5augmentations.ToTensor
|
||||
<br><br>
|
||||
|
||||
## normalize
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5augmentations.normalize
|
||||
<br><br>
|
||||
|
||||
## denormalize
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5augmentations.denormalize
|
||||
<br><br>
|
||||
|
||||
## augment_hsv
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5augmentations.augment_hsv
|
||||
<br><br>
|
||||
|
||||
## hist_equalize
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5augmentations.hist_equalize
|
||||
<br><br>
|
||||
|
||||
## replicate
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5augmentations.replicate
|
||||
<br><br>
|
||||
|
||||
## letterbox
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5augmentations.letterbox
|
||||
<br><br>
|
||||
|
||||
## random_perspective
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5augmentations.random_perspective
|
||||
<br><br>
|
||||
|
||||
## copy_paste
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5augmentations.copy_paste
|
||||
<br><br>
|
||||
|
||||
## cutout
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5augmentations.cutout
|
||||
<br><br>
|
||||
|
||||
## mixup
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5augmentations.mixup
|
||||
<br><br>
|
||||
|
||||
## box_candidates
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5augmentations.box_candidates
|
||||
<br><br>
|
||||
|
||||
## classify_albumentations
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5augmentations.classify_albumentations
|
||||
<br><br>
|
||||
|
||||
## classify_transforms
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5augmentations.classify_transforms
|
||||
<br><br>
|
||||
@ -1,94 +0,0 @@
|
||||
---
|
||||
description: Efficiently load images and labels to models using Ultralytics YOLO's InfiniteDataLoader, LoadScreenshots, and LoadStreams.
|
||||
keywords: YOLO, data loader, image classification, object detection, Ultralytics
|
||||
---
|
||||
|
||||
## InfiniteDataLoader
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader.InfiniteDataLoader
|
||||
<br><br>
|
||||
|
||||
## _RepeatSampler
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader._RepeatSampler
|
||||
<br><br>
|
||||
|
||||
## LoadScreenshots
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader.LoadScreenshots
|
||||
<br><br>
|
||||
|
||||
## LoadImages
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader.LoadImages
|
||||
<br><br>
|
||||
|
||||
## LoadStreams
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader.LoadStreams
|
||||
<br><br>
|
||||
|
||||
## LoadImagesAndLabels
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader.LoadImagesAndLabels
|
||||
<br><br>
|
||||
|
||||
## ClassificationDataset
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader.ClassificationDataset
|
||||
<br><br>
|
||||
|
||||
## get_hash
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader.get_hash
|
||||
<br><br>
|
||||
|
||||
## exif_size
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader.exif_size
|
||||
<br><br>
|
||||
|
||||
## exif_transpose
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader.exif_transpose
|
||||
<br><br>
|
||||
|
||||
## seed_worker
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader.seed_worker
|
||||
<br><br>
|
||||
|
||||
## create_dataloader
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader.create_dataloader
|
||||
<br><br>
|
||||
|
||||
## img2label_paths
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader.img2label_paths
|
||||
<br><br>
|
||||
|
||||
## flatten_recursive
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader.flatten_recursive
|
||||
<br><br>
|
||||
|
||||
## extract_boxes
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader.extract_boxes
|
||||
<br><br>
|
||||
|
||||
## autosplit
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader.autosplit
|
||||
<br><br>
|
||||
|
||||
## verify_image_label
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader.verify_image_label
|
||||
<br><br>
|
||||
|
||||
## create_classification_dataloader
|
||||
---
|
||||
### ::: ultralytics.yolo.data.dataloaders.v5loader.create_classification_dataloader
|
||||
<br><br>
|
||||
@ -67,3 +67,8 @@ keywords: YOLOv4, Object Detection, Computer Vision, Deep Learning, Convolutiona
|
||||
---
|
||||
### ::: ultralytics.yolo.data.utils.zip_directory
|
||||
<br><br>
|
||||
|
||||
## autosplit
|
||||
---
|
||||
### ::: ultralytics.yolo.data.utils.autosplit
|
||||
<br><br>
|
||||
|
||||
@ -18,6 +18,11 @@ keywords: Ultralytics, YOLO, utils, SimpleClass, IterableSimpleNamespace, EmojiF
|
||||
### ::: ultralytics.yolo.utils.EmojiFilter
|
||||
<br><br>
|
||||
|
||||
## ThreadingLocked
|
||||
---
|
||||
### ::: ultralytics.yolo.utils.ThreadingLocked
|
||||
<br><br>
|
||||
|
||||
## TryExcept
|
||||
---
|
||||
### ::: ultralytics.yolo.utils.TryExcept
|
||||
|
||||
@ -23,6 +23,11 @@ keywords: Ultralytics YOLO, Torch, Utils, Pytorch, Object Detection
|
||||
### ::: ultralytics.yolo.utils.torch_utils.smart_inference_mode
|
||||
<br><br>
|
||||
|
||||
## get_cpu_info
|
||||
---
|
||||
### ::: ultralytics.yolo.utils.torch_utils.get_cpu_info
|
||||
<br><br>
|
||||
|
||||
## select_device
|
||||
---
|
||||
### ::: ultralytics.yolo.utils.torch_utils.select_device
|
||||
|
||||
@ -300,7 +300,7 @@
|
||||
"name": "stdout",
|
||||
"text": [
|
||||
"Ultralytics YOLOv8.0.71 🚀 Python-3.9.16 torch-2.0.0+cu118 CUDA:0 (Tesla T4, 15102MiB)\n",
|
||||
"\u001b[34m\u001b[1myolo/engine/trainer: \u001b[0mtask=detect, mode=train, model=yolov8n.pt, data=coco128.yaml, epochs=3, patience=50, batch=16, imgsz=640, save=True, save_period=-1, cache=False, device=None, workers=8, project=None, name=None, exist_ok=False, pretrained=False, optimizer=SGD, verbose=True, seed=0, deterministic=True, single_cls=False, image_weights=False, rect=False, cos_lr=False, close_mosaic=0, resume=False, amp=True, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, split=val, save_json=False, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, show=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, vid_stride=1, line_width=3, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, boxes=True, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=None, workspace=4, nms=False, lr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=7.5, cls=0.5, dfl=1.5, pose=12.0, kobj=1.0, label_smoothing=0.0, nbs=64, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0, cfg=None, v5loader=False, tracker=botsort.yaml, save_dir=runs/detect/train\n",
|
||||
"\u001b[34m\u001b[1myolo/engine/trainer: \u001b[0mtask=detect, mode=train, model=yolov8n.pt, data=coco128.yaml, epochs=3, patience=50, batch=16, imgsz=640, save=True, save_period=-1, cache=False, device=None, workers=8, project=None, name=None, exist_ok=False, pretrained=False, optimizer=SGD, verbose=True, seed=0, deterministic=True, single_cls=False, image_weights=False, rect=False, cos_lr=False, close_mosaic=0, resume=False, amp=True, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, split=val, save_json=False, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, show=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, vid_stride=1, line_width=3, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, boxes=True, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=None, workspace=4, nms=False, lr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=7.5, cls=0.5, dfl=1.5, pose=12.0, kobj=1.0, label_smoothing=0.0, nbs=64, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0, cfg=None, tracker=botsort.yaml, save_dir=runs/detect/train\n",
|
||||
"\n",
|
||||
" from n params module arguments \n",
|
||||
" 0 -1 1 464 ultralytics.nn.modules.Conv [3, 16, 3, 2] \n",
|
||||
|
||||
@ -305,8 +305,6 @@ nav:
|
||||
- converter: reference/yolo/data/converter.md
|
||||
- dataloaders:
|
||||
- stream_loaders: reference/yolo/data/dataloaders/stream_loaders.md
|
||||
- v5augmentations: reference/yolo/data/dataloaders/v5augmentations.md
|
||||
- v5loader: reference/yolo/data/dataloaders/v5loader.md
|
||||
- dataset: reference/yolo/data/dataset.md
|
||||
- dataset_wrappers: reference/yolo/data/dataset_wrappers.md
|
||||
- utils: reference/yolo/data/utils.md
|
||||
|
||||
@ -65,7 +65,6 @@ def test_detect():
|
||||
def test_segment():
|
||||
overrides = {'data': 'coco8-seg.yaml', 'model': CFG_SEG, 'imgsz': 32, 'epochs': 1, 'save': False}
|
||||
CFG.data = 'coco8-seg.yaml'
|
||||
CFG.v5loader = False
|
||||
# YOLO(CFG_SEG).train(**overrides) # works
|
||||
|
||||
# trainer
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# Ultralytics YOLO 🚀, AGPL-3.0 license
|
||||
|
||||
__version__ = '8.0.134'
|
||||
__version__ = '8.0.135'
|
||||
|
||||
from ultralytics.hub import start
|
||||
from ultralytics.vit.rtdetr import RTDETR
|
||||
|
||||
@ -87,7 +87,7 @@ download: |
|
||||
from PIL import Image
|
||||
from tqdm import tqdm
|
||||
|
||||
from ultralytics.yolo.data.dataloaders.v5loader import autosplit
|
||||
from ultralytics.yolo.data.utils import autosplit
|
||||
from ultralytics.yolo.utils.ops import xyxy2xywhn
|
||||
|
||||
|
||||
|
||||
@ -75,7 +75,7 @@ CFG_INT_KEYS = ('epochs', 'patience', 'batch', 'workers', 'seed', 'close_mosaic'
|
||||
CFG_BOOL_KEYS = ('save', 'exist_ok', 'verbose', 'deterministic', 'single_cls', 'rect', 'cos_lr', 'overlap_mask', 'val',
|
||||
'save_json', 'save_hybrid', 'half', 'dnn', 'plots', 'show', 'save_txt', 'save_conf', 'save_crop',
|
||||
'show_labels', 'show_conf', 'visualize', 'augment', 'agnostic_nms', 'retina_masks', 'boxes', 'keras',
|
||||
'optimize', 'int8', 'dynamic', 'simplify', 'nms', 'v5loader', 'profile')
|
||||
'optimize', 'int8', 'dynamic', 'simplify', 'nms', 'profile')
|
||||
|
||||
|
||||
def cfg2dict(cfg):
|
||||
|
||||
@ -110,8 +110,5 @@ copy_paste: 0.0 # (float) segment copy-paste (probability)
|
||||
# Custom config.yaml ---------------------------------------------------------------------------------------------------
|
||||
cfg: # (str, optional) for overriding defaults.yaml
|
||||
|
||||
# Debug, do not modify -------------------------------------------------------------------------------------------------
|
||||
v5loader: False # (bool) use legacy YOLOv5 dataloader (deprecated)
|
||||
|
||||
# Tracker settings ------------------------------------------------------------------------------------------------------
|
||||
tracker: botsort.yaml # (str) tracker type, choices=[botsort.yaml, bytetrack.yaml]
|
||||
|
||||
@ -1,407 +0,0 @@
|
||||
# Ultralytics YOLO 🚀, AGPL-3.0 license
|
||||
"""
|
||||
Image augmentation functions
|
||||
"""
|
||||
|
||||
import math
|
||||
import random
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
import torch
|
||||
import torchvision.transforms as T
|
||||
import torchvision.transforms.functional as TF
|
||||
|
||||
from ultralytics.yolo.utils import LOGGER, colorstr
|
||||
from ultralytics.yolo.utils.checks import check_version
|
||||
from ultralytics.yolo.utils.metrics import bbox_ioa
|
||||
from ultralytics.yolo.utils.ops import resample_segments, segment2box, xywhn2xyxy
|
||||
|
||||
IMAGENET_MEAN = 0.485, 0.456, 0.406 # RGB mean
|
||||
IMAGENET_STD = 0.229, 0.224, 0.225 # RGB standard deviation
|
||||
|
||||
|
||||
class Albumentations:
|
||||
# YOLOv5 Albumentations class (optional, only used if package is installed)
|
||||
def __init__(self, size=640):
|
||||
"""Instantiate object with image augmentations for YOLOv5."""
|
||||
self.transform = None
|
||||
prefix = colorstr('albumentations: ')
|
||||
try:
|
||||
import albumentations as A
|
||||
check_version(A.__version__, '1.0.3', hard=True) # version requirement
|
||||
|
||||
T = [
|
||||
A.RandomResizedCrop(height=size, width=size, scale=(0.8, 1.0), ratio=(0.9, 1.11), p=0.0),
|
||||
A.Blur(p=0.01),
|
||||
A.MedianBlur(p=0.01),
|
||||
A.ToGray(p=0.01),
|
||||
A.CLAHE(p=0.01),
|
||||
A.RandomBrightnessContrast(p=0.0),
|
||||
A.RandomGamma(p=0.0),
|
||||
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))
|
||||
except ImportError: # package not installed, skip
|
||||
pass
|
||||
except Exception as e:
|
||||
LOGGER.info(f'{prefix}{e}')
|
||||
|
||||
def __call__(self, im, labels, p=1.0):
|
||||
"""Transforms input image and labels with probability 'p'."""
|
||||
if self.transform and random.random() < p:
|
||||
new = self.transform(image=im, bboxes=labels[:, 1:], class_labels=labels[:, 0]) # transformed
|
||||
im, labels = new['image'], np.array([[c, *b] for c, b in zip(new['class_labels'], new['bboxes'])])
|
||||
return im, labels
|
||||
|
||||
|
||||
def normalize(x, mean=IMAGENET_MEAN, std=IMAGENET_STD, inplace=False):
|
||||
"""Denormalize RGB images x per ImageNet stats in BCHW format, i.e. = (x - mean) / std."""
|
||||
return TF.normalize(x, mean, std, inplace=inplace)
|
||||
|
||||
|
||||
def denormalize(x, mean=IMAGENET_MEAN, std=IMAGENET_STD):
|
||||
"""Denormalize RGB images x per ImageNet stats in BCHW format, i.e. = x * std + mean."""
|
||||
for i in range(3):
|
||||
x[:, i] = x[:, i] * std[i] + mean[i]
|
||||
return x
|
||||
|
||||
|
||||
def augment_hsv(im, hgain=0.5, sgain=0.5, vgain=0.5):
|
||||
"""HSV color-space augmentation."""
|
||||
if hgain or sgain or vgain:
|
||||
r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1 # random gains
|
||||
hue, sat, val = cv2.split(cv2.cvtColor(im, cv2.COLOR_BGR2HSV))
|
||||
dtype = im.dtype # uint8
|
||||
|
||||
x = np.arange(0, 256, dtype=r.dtype)
|
||||
lut_hue = ((x * r[0]) % 180).astype(dtype)
|
||||
lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
|
||||
lut_val = np.clip(x * r[2], 0, 255).astype(dtype)
|
||||
|
||||
im_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val)))
|
||||
cv2.cvtColor(im_hsv, cv2.COLOR_HSV2BGR, dst=im) # no return needed
|
||||
|
||||
|
||||
def hist_equalize(im, clahe=True, bgr=False):
|
||||
"""Equalize histogram on BGR image 'im' with im.shape(n,m,3) and range 0-255."""
|
||||
yuv = cv2.cvtColor(im, cv2.COLOR_BGR2YUV if bgr else cv2.COLOR_RGB2YUV)
|
||||
if clahe:
|
||||
c = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
|
||||
yuv[:, :, 0] = c.apply(yuv[:, :, 0])
|
||||
else:
|
||||
yuv[:, :, 0] = cv2.equalizeHist(yuv[:, :, 0]) # equalize Y channel histogram
|
||||
return cv2.cvtColor(yuv, cv2.COLOR_YUV2BGR if bgr else cv2.COLOR_YUV2RGB) # convert YUV image to RGB
|
||||
|
||||
|
||||
def replicate(im, labels):
|
||||
"""Replicate labels."""
|
||||
h, w = im.shape[:2]
|
||||
boxes = labels[:, 1:].astype(int)
|
||||
x1, y1, x2, y2 = boxes.T
|
||||
s = ((x2 - x1) + (y2 - y1)) / 2 # side length (pixels)
|
||||
for i in s.argsort()[:round(s.size * 0.5)]: # smallest indices
|
||||
x1b, y1b, x2b, y2b = boxes[i]
|
||||
bh, bw = y2b - y1b, x2b - x1b
|
||||
yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw)) # offset x, y
|
||||
x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh]
|
||||
im[y1a:y2a, x1a:x2a] = im[y1b:y2b, x1b:x2b] # im4[ymin:ymax, xmin:xmax]
|
||||
labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0)
|
||||
|
||||
return im, labels
|
||||
|
||||
|
||||
def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32):
|
||||
"""Resize and pad image while meeting stride-multiple constraints."""
|
||||
shape = im.shape[:2] # current shape [height, width]
|
||||
if isinstance(new_shape, int):
|
||||
new_shape = (new_shape, new_shape)
|
||||
|
||||
# Scale ratio (new / old)
|
||||
r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
|
||||
if not scaleup: # only scale down, do not scale up (for better val mAP)
|
||||
r = min(r, 1.0)
|
||||
|
||||
# Compute padding
|
||||
ratio = r, r # width, height ratios
|
||||
new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
|
||||
dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding
|
||||
if auto: # minimum rectangle
|
||||
dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding
|
||||
elif scaleFill: # stretch
|
||||
dw, dh = 0.0, 0.0
|
||||
new_unpad = (new_shape[1], new_shape[0])
|
||||
ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios
|
||||
|
||||
dw /= 2 # divide padding into 2 sides
|
||||
dh /= 2
|
||||
|
||||
if shape[::-1] != new_unpad: # resize
|
||||
im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
|
||||
top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
|
||||
left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
|
||||
im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
|
||||
return im, ratio, (dw, dh)
|
||||
|
||||
|
||||
def random_perspective(im,
|
||||
targets=(),
|
||||
segments=(),
|
||||
degrees=10,
|
||||
translate=.1,
|
||||
scale=.1,
|
||||
shear=10,
|
||||
perspective=0.0,
|
||||
border=(0, 0)):
|
||||
# torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(0.1, 0.1), scale=(0.9, 1.1), shear=(-10, 10))
|
||||
# targets = [cls, xyxy]
|
||||
|
||||
height = im.shape[0] + border[0] * 2 # shape(h,w,c)
|
||||
width = im.shape[1] + border[1] * 2
|
||||
|
||||
# Center
|
||||
C = np.eye(3)
|
||||
C[0, 2] = -im.shape[1] / 2 # x translation (pixels)
|
||||
C[1, 2] = -im.shape[0] / 2 # y translation (pixels)
|
||||
|
||||
# Perspective
|
||||
P = np.eye(3)
|
||||
P[2, 0] = random.uniform(-perspective, perspective) # x perspective (about y)
|
||||
P[2, 1] = random.uniform(-perspective, perspective) # y perspective (about x)
|
||||
|
||||
# Rotation and Scale
|
||||
R = np.eye(3)
|
||||
a = random.uniform(-degrees, degrees)
|
||||
# a += random.choice([-180, -90, 0, 90]) # add 90deg rotations to small rotations
|
||||
s = random.uniform(1 - scale, 1 + scale)
|
||||
# s = 2 ** random.uniform(-scale, scale)
|
||||
R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s)
|
||||
|
||||
# Shear
|
||||
S = np.eye(3)
|
||||
S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # x shear (deg)
|
||||
S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # y shear (deg)
|
||||
|
||||
# Translation
|
||||
T = np.eye(3)
|
||||
T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width # x translation (pixels)
|
||||
T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height # y translation (pixels)
|
||||
|
||||
# Combined rotation matrix
|
||||
M = T @ S @ R @ P @ C # order of operations (right to left) is IMPORTANT
|
||||
if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any(): # image changed
|
||||
if perspective:
|
||||
im = cv2.warpPerspective(im, M, dsize=(width, height), borderValue=(114, 114, 114))
|
||||
else: # affine
|
||||
im = cv2.warpAffine(im, M[:2], dsize=(width, height), borderValue=(114, 114, 114))
|
||||
|
||||
# Visualize
|
||||
# import matplotlib.pyplot as plt
|
||||
# ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel()
|
||||
# ax[0].imshow(im[:, :, ::-1]) # base
|
||||
# ax[1].imshow(im2[:, :, ::-1]) # warped
|
||||
|
||||
# Transform label coordinates
|
||||
n = len(targets)
|
||||
if n:
|
||||
use_segments = any(x.any() for x in segments)
|
||||
new = np.zeros((n, 4))
|
||||
if use_segments: # warp segments
|
||||
segments = resample_segments(segments) # upsample
|
||||
for i, segment in enumerate(segments):
|
||||
xy = np.ones((len(segment), 3))
|
||||
xy[:, :2] = segment
|
||||
xy = xy @ M.T # transform
|
||||
xy = xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2] # perspective rescale or affine
|
||||
|
||||
# Clip
|
||||
new[i] = segment2box(xy, width, height)
|
||||
|
||||
else: # warp boxes
|
||||
xy = np.ones((n * 4, 3))
|
||||
xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2) # x1y1, x2y2, x1y2, x2y1
|
||||
xy = xy @ M.T # transform
|
||||
xy = (xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]).reshape(n, 8) # perspective rescale or affine
|
||||
|
||||
# Create new boxes
|
||||
x = xy[:, [0, 2, 4, 6]]
|
||||
y = xy[:, [1, 3, 5, 7]]
|
||||
new = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T
|
||||
|
||||
# Clip
|
||||
new[:, [0, 2]] = new[:, [0, 2]].clip(0, width)
|
||||
new[:, [1, 3]] = new[:, [1, 3]].clip(0, height)
|
||||
|
||||
# Filter candidates
|
||||
i = box_candidates(box1=targets[:, 1:5].T * s, box2=new.T, area_thr=0.01 if use_segments else 0.10)
|
||||
targets = targets[i]
|
||||
targets[:, 1:5] = new[i]
|
||||
|
||||
return im, targets
|
||||
|
||||
|
||||
def copy_paste(im, labels, segments, p=0.5):
|
||||
"""Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy)."""
|
||||
n = len(segments)
|
||||
if p and n:
|
||||
h, w, c = im.shape # height, width, channels
|
||||
im_new = np.zeros(im.shape, np.uint8)
|
||||
|
||||
# Calculate ioa first then select indexes randomly
|
||||
boxes = np.stack([w - labels[:, 3], labels[:, 2], w - labels[:, 1], labels[:, 4]], axis=-1) # (n, 4)
|
||||
ioa = bbox_ioa(boxes, labels[:, 1:5]) # intersection over area
|
||||
indexes = np.nonzero((ioa < 0.30).all(1))[0] # (N, )
|
||||
n = len(indexes)
|
||||
for j in random.sample(list(indexes), k=round(p * n)):
|
||||
l, box, s = labels[j], boxes[j], segments[j]
|
||||
labels = np.concatenate((labels, [[l[0], *box]]), 0)
|
||||
segments.append(np.concatenate((w - s[:, 0:1], s[:, 1:2]), 1))
|
||||
cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (1, 1, 1), cv2.FILLED)
|
||||
|
||||
result = cv2.flip(im, 1) # augment segments (flip left-right)
|
||||
i = cv2.flip(im_new, 1).astype(bool)
|
||||
im[i] = result[i] # cv2.imwrite('debug.jpg', im) # debug
|
||||
|
||||
return im, labels, segments
|
||||
|
||||
|
||||
def cutout(im, labels, p=0.5):
|
||||
"""Applies image cutout augmentation https://arxiv.org/abs/1708.04552."""
|
||||
if random.random() < p:
|
||||
h, w = im.shape[:2]
|
||||
scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16 # image size fraction
|
||||
for s in scales:
|
||||
mask_h = random.randint(1, int(h * s)) # create random masks
|
||||
mask_w = random.randint(1, int(w * s))
|
||||
|
||||
# Box
|
||||
xmin = max(0, random.randint(0, w) - mask_w // 2)
|
||||
ymin = max(0, random.randint(0, h) - mask_h // 2)
|
||||
xmax = min(w, xmin + mask_w)
|
||||
ymax = min(h, ymin + mask_h)
|
||||
|
||||
# Apply random color mask
|
||||
im[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)]
|
||||
|
||||
# Return unobscured labels
|
||||
if len(labels) and s > 0.03:
|
||||
box = np.array([[xmin, ymin, xmax, ymax]], dtype=np.float32)
|
||||
ioa = bbox_ioa(box, xywhn2xyxy(labels[:, 1:5], w, h))[0] # intersection over area
|
||||
labels = labels[ioa < 0.60] # remove >60% obscured labels
|
||||
|
||||
return labels
|
||||
|
||||
|
||||
def mixup(im, labels, im2, labels2):
|
||||
"""Applies MixUp augmentation https://arxiv.org/pdf/1710.09412.pdf."""
|
||||
r = np.random.beta(32.0, 32.0) # mixup ratio, alpha=beta=32.0
|
||||
im = (im * r + im2 * (1 - r)).astype(np.uint8)
|
||||
labels = np.concatenate((labels, labels2), 0)
|
||||
return im, labels
|
||||
|
||||
|
||||
def box_candidates(box1, box2, wh_thr=2, ar_thr=100, area_thr=0.1, eps=1e-16): # box1(4,n), box2(4,n)
|
||||
# Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio
|
||||
w1, h1 = box1[2] - box1[0], box1[3] - box1[1]
|
||||
w2, h2 = box2[2] - box2[0], box2[3] - box2[1]
|
||||
ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps)) # aspect ratio
|
||||
return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr) # candidates
|
||||
|
||||
|
||||
def classify_albumentations(
|
||||
augment=True,
|
||||
size=224,
|
||||
scale=(0.08, 1.0),
|
||||
ratio=(0.75, 1.0 / 0.75), # 0.75, 1.33
|
||||
hflip=0.5,
|
||||
vflip=0.0,
|
||||
jitter=0.4,
|
||||
mean=IMAGENET_MEAN,
|
||||
std=IMAGENET_STD,
|
||||
auto_aug=False):
|
||||
# YOLOv5 classification Albumentations (optional, only used if package is installed)
|
||||
prefix = colorstr('albumentations: ')
|
||||
try:
|
||||
import albumentations as A
|
||||
from albumentations.pytorch import ToTensorV2
|
||||
check_version(A.__version__, '1.0.3', hard=True) # version requirement
|
||||
if augment: # Resize and crop
|
||||
T = [A.RandomResizedCrop(height=size, width=size, scale=scale, ratio=ratio)]
|
||||
if auto_aug:
|
||||
# TODO: implement AugMix, AutoAug & RandAug in albumentation
|
||||
LOGGER.info(f'{prefix}auto augmentations are currently not supported')
|
||||
else:
|
||||
if hflip > 0:
|
||||
T += [A.HorizontalFlip(p=hflip)]
|
||||
if vflip > 0:
|
||||
T += [A.VerticalFlip(p=vflip)]
|
||||
if jitter > 0:
|
||||
jitter = float(jitter)
|
||||
T += [A.ColorJitter(jitter, jitter, jitter, 0)] # brightness, contrast, satuaration, 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
|
||||
LOGGER.info(prefix + ', '.join(f'{x}'.replace('always_apply=False, ', '') for x in T if x.p))
|
||||
return A.Compose(T)
|
||||
|
||||
except ImportError: # package not installed, skip
|
||||
LOGGER.warning(f'{prefix}⚠️ not found, install with `pip install albumentations` (recommended)')
|
||||
except Exception as e:
|
||||
LOGGER.info(f'{prefix}{e}')
|
||||
|
||||
|
||||
def classify_transforms(size=224):
|
||||
"""Transforms to apply if albumentations not installed."""
|
||||
assert isinstance(size, int), f'ERROR: classify_transforms size {size} must be integer, not (list, tuple)'
|
||||
# T.Compose([T.ToTensor(), T.Resize(size), T.CenterCrop(size), T.Normalize(IMAGENET_MEAN, IMAGENET_STD)])
|
||||
return T.Compose([CenterCrop(size), ToTensor(), T.Normalize(IMAGENET_MEAN, IMAGENET_STD)])
|
||||
|
||||
|
||||
class LetterBox:
|
||||
# YOLOv5 LetterBox class for image preprocessing, i.e. T.Compose([LetterBox(size), ToTensor()])
|
||||
def __init__(self, size=(640, 640), auto=False, stride=32):
|
||||
"""Resizes and crops an image to a specified size for YOLOv5 preprocessing."""
|
||||
super().__init__()
|
||||
self.h, self.w = (size, size) if isinstance(size, int) else size
|
||||
self.auto = auto # pass max size integer, automatically solve for short side using stride
|
||||
self.stride = stride # used with auto
|
||||
|
||||
def __call__(self, im): # im = np.array HWC
|
||||
imh, imw = im.shape[:2]
|
||||
r = min(self.h / imh, self.w / imw) # ratio of new/old
|
||||
h, w = round(imh * r), round(imw * r) # resized image
|
||||
hs, ws = (math.ceil(x / self.stride) * self.stride for x in (h, w)) if self.auto else self.h, self.w
|
||||
top, left = round((hs - h) / 2 - 0.1), round((ws - w) / 2 - 0.1)
|
||||
im_out = np.full((self.h, self.w, 3), 114, dtype=im.dtype)
|
||||
im_out[top:top + h, left:left + w] = cv2.resize(im, (w, h), interpolation=cv2.INTER_LINEAR)
|
||||
return im_out
|
||||
|
||||
|
||||
class CenterCrop:
|
||||
# YOLOv5 CenterCrop class for image preprocessing, i.e. T.Compose([CenterCrop(size), ToTensor()])
|
||||
def __init__(self, size=640):
|
||||
"""Converts input image into tensor for YOLOv5 processing."""
|
||||
super().__init__()
|
||||
self.h, self.w = (size, size) if isinstance(size, int) else size
|
||||
|
||||
def __call__(self, im): # im = np.array HWC
|
||||
imh, imw = im.shape[:2]
|
||||
m = min(imh, imw) # min dimension
|
||||
top, left = (imh - m) // 2, (imw - m) // 2
|
||||
return cv2.resize(im[top:top + m, left:left + m], (self.w, self.h), interpolation=cv2.INTER_LINEAR)
|
||||
|
||||
|
||||
class ToTensor:
|
||||
# YOLOv5 ToTensor class for image preprocessing, i.e. T.Compose([LetterBox(size), ToTensor()])
|
||||
def __init__(self, half=False):
|
||||
"""Initialize ToTensor class for YOLOv5 image preprocessing."""
|
||||
super().__init__()
|
||||
self.half = half
|
||||
|
||||
def __call__(self, im): # im = np.array HWC in BGR order
|
||||
im = np.ascontiguousarray(im.transpose((2, 0, 1))[::-1]) # HWC to CHW -> BGR to RGB -> contiguous
|
||||
im = torch.from_numpy(im) # to torch
|
||||
im = im.half() if self.half else im.float() # uint8 to fp16/32
|
||||
im /= 255.0 # 0-255 to 0.0-1.0
|
||||
return im
|
||||
File diff suppressed because it is too large
Load Diff
@ -4,6 +4,7 @@ import contextlib
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import random
|
||||
import subprocess
|
||||
import time
|
||||
import zipfile
|
||||
@ -522,3 +523,35 @@ def zip_directory(dir, use_zipfile_library=True):
|
||||
else:
|
||||
import shutil
|
||||
shutil.make_archive(dir, 'zip', dir)
|
||||
|
||||
|
||||
def autosplit(path=DATASETS_DIR / 'coco128/images', weights=(0.9, 0.1, 0.0), annotated_only=False):
|
||||
"""
|
||||
Autosplit a dataset into train/val/test splits and save the resulting splits into autosplit_*.txt files.
|
||||
|
||||
Args:
|
||||
path (Path, optional): Path to images directory. Defaults to DATASETS_DIR / 'coco128/images'.
|
||||
weights (list | tuple, optional): Train, validation, and test split fractions. Defaults to (0.9, 0.1, 0.0).
|
||||
annotated_only (bool, optional): If True, only images with an associated txt file are used. Defaults to False.
|
||||
|
||||
Usage:
|
||||
from utils.dataloaders import autosplit
|
||||
autosplit()
|
||||
"""
|
||||
|
||||
path = Path(path) # images dir
|
||||
files = sorted(x for x in path.rglob('*.*') if x.suffix[1:].lower() in IMG_FORMATS) # image files only
|
||||
n = len(files) # number of files
|
||||
random.seed(0) # for reproducibility
|
||||
indices = random.choices([0, 1, 2], weights=weights, k=n) # assign each image to a split
|
||||
|
||||
txt = ['autosplit_train.txt', 'autosplit_val.txt', 'autosplit_test.txt'] # 3 txt files
|
||||
for x in txt:
|
||||
if (path.parent / x).exists():
|
||||
(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):
|
||||
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
|
||||
|
||||
@ -244,7 +244,7 @@ class BaseTrainer:
|
||||
metric_keys = self.validator.metrics.keys + self.label_loss_items(prefix='val')
|
||||
self.metrics = dict(zip(metric_keys, [0] * len(metric_keys))) # TODO: init metrics for plot_results()?
|
||||
self.ema = ModelEMA(self.model)
|
||||
if self.args.plots and not self.args.v5loader:
|
||||
if self.args.plots:
|
||||
self.plot_training_labels()
|
||||
|
||||
# Optimizer
|
||||
|
||||
@ -6,9 +6,8 @@ import numpy as np
|
||||
from ultralytics.nn.tasks import DetectionModel
|
||||
from ultralytics.yolo import v8
|
||||
from ultralytics.yolo.data import build_dataloader, build_yolo_dataset
|
||||
from ultralytics.yolo.data.dataloaders.v5loader import create_dataloader
|
||||
from ultralytics.yolo.engine.trainer import BaseTrainer
|
||||
from ultralytics.yolo.utils import DEFAULT_CFG, LOGGER, RANK, colorstr
|
||||
from ultralytics.yolo.utils import DEFAULT_CFG, LOGGER, RANK
|
||||
from ultralytics.yolo.utils.plotting import plot_images, plot_labels, plot_results
|
||||
from ultralytics.yolo.utils.torch_utils import de_parallel, torch_distributed_zero_first
|
||||
|
||||
@ -17,7 +16,8 @@ from ultralytics.yolo.utils.torch_utils import de_parallel, torch_distributed_ze
|
||||
class DetectionTrainer(BaseTrainer):
|
||||
|
||||
def build_dataset(self, img_path, mode='train', batch=None):
|
||||
"""Build YOLO Dataset
|
||||
"""
|
||||
Build YOLO Dataset.
|
||||
|
||||
Args:
|
||||
img_path (str): Path to the folder containing images.
|
||||
@ -28,27 +28,7 @@ class DetectionTrainer(BaseTrainer):
|
||||
return build_yolo_dataset(self.args, img_path, batch, self.data, mode=mode, rect=mode == 'val', stride=gs)
|
||||
|
||||
def get_dataloader(self, dataset_path, batch_size=16, rank=0, mode='train'):
|
||||
"""TODO: manage splits differently."""
|
||||
# Calculate stride - check if model is initialized
|
||||
if self.args.v5loader:
|
||||
LOGGER.warning("WARNING ⚠️ 'v5loader' feature is deprecated and will be removed soon. You can train using "
|
||||
'the default YOLOv8 dataloader instead, no argument is needed.')
|
||||
gs = max(int(de_parallel(self.model).stride.max() if self.model else 0), 32)
|
||||
return create_dataloader(path=dataset_path,
|
||||
imgsz=self.args.imgsz,
|
||||
batch_size=batch_size,
|
||||
stride=gs,
|
||||
hyp=vars(self.args),
|
||||
augment=mode == 'train',
|
||||
cache=self.args.cache,
|
||||
pad=0 if mode == 'train' else 0.5,
|
||||
rect=self.args.rect or mode == 'val',
|
||||
rank=rank,
|
||||
workers=self.args.workers,
|
||||
close_mosaic=self.args.close_mosaic != 0,
|
||||
prefix=colorstr(f'{mode}: '),
|
||||
shuffle=mode == 'train',
|
||||
seed=self.args.seed)[0]
|
||||
"""Construct and return dataloader."""
|
||||
assert mode in ['train', 'val']
|
||||
with torch_distributed_zero_first(rank): # init dataset *.cache only once if DDP
|
||||
dataset = self.build_dataset(dataset_path, mode, batch_size)
|
||||
|
||||
@ -7,9 +7,8 @@ import numpy as np
|
||||
import torch
|
||||
|
||||
from ultralytics.yolo.data import build_dataloader, build_yolo_dataset
|
||||
from ultralytics.yolo.data.dataloaders.v5loader import create_dataloader
|
||||
from ultralytics.yolo.engine.validator import BaseValidator
|
||||
from ultralytics.yolo.utils import DEFAULT_CFG, LOGGER, colorstr, ops
|
||||
from ultralytics.yolo.utils import DEFAULT_CFG, LOGGER, ops
|
||||
from ultralytics.yolo.utils.checks import check_requirements
|
||||
from ultralytics.yolo.utils.metrics import ConfusionMatrix, DetMetrics, box_iou
|
||||
from ultralytics.yolo.utils.plotting import output_to_target, plot_images
|
||||
@ -186,28 +185,9 @@ class DetectionValidator(BaseValidator):
|
||||
return build_yolo_dataset(self.args, img_path, batch, self.data, mode=mode, stride=gs)
|
||||
|
||||
def get_dataloader(self, dataset_path, batch_size):
|
||||
"""TODO: manage splits differently."""
|
||||
# Calculate stride - check if model is initialized
|
||||
if self.args.v5loader:
|
||||
LOGGER.warning("WARNING ⚠️ 'v5loader' feature is deprecated and will be removed soon. You can train using "
|
||||
'the default YOLOv8 dataloader instead, no argument is needed.')
|
||||
gs = max(int(de_parallel(self.model).stride if self.model else 0), 32)
|
||||
return create_dataloader(path=dataset_path,
|
||||
imgsz=self.args.imgsz,
|
||||
batch_size=batch_size,
|
||||
stride=gs,
|
||||
hyp=vars(self.args),
|
||||
cache=False,
|
||||
pad=0.5,
|
||||
rect=self.args.rect,
|
||||
workers=self.args.workers,
|
||||
prefix=colorstr(f'{self.args.mode}: '),
|
||||
shuffle=False,
|
||||
seed=self.args.seed)[0]
|
||||
|
||||
"""Construct and return dataloader."""
|
||||
dataset = self.build_dataset(dataset_path, batch=batch_size, mode='val')
|
||||
dataloader = build_dataloader(dataset, batch_size, self.args.workers, shuffle=False, rank=-1)
|
||||
return dataloader
|
||||
return build_dataloader(dataset, batch_size, self.args.workers, shuffle=False, rank=-1) # return dataloader
|
||||
|
||||
def plot_val_samples(self, batch, ni):
|
||||
"""Plot validation image samples."""
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user