yolov7的dataset代码详解

yolov7的数据增强中采用了很多yolov5没有用过的增强，比如mosaic、mosaic9、mixup、copy_paste、paste_in等，这些数据增强很占显存，训练的时候可以把一些数据增强关了，我把mosaic9注释了，以下是yolov7的dataset代码详解。

# Dataset utils and dataloaders

import glob
import logging
import math
import os
import random
import shutil
import time
from itertools import repeat
from multiprocessing.pool import ThreadPool
from pathlib import Path
from threading import Thread

import cv2
import numpy as np
import torch
import torch.nn.functional as F
from PIL import Image, ExifTags
from torch.utils.data import Dataset
from tqdm import tqdm

import pickle
from copy import deepcopy
#from pycocotools import mask as maskUtils
from torchvision.utils import save_image
from torchvision.ops import roi_pool, roi_align, ps_roi_pool, ps_roi_align

from utils.general import check_requirements, xyxy2xywh, xywh2xyxy, xywhn2xyxy, xyn2xy, segment2box, segments2boxes, \
    resample_segments, clean_str
from utils.torch_utils import torch_distributed_zero_first

# Parameters
help_url = 'https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data'
img_formats = ['bmp', 'jpg', 'jpeg', 'png', 'tif', 'tiff', 'dng', 'webp', 'mpo']  # acceptable image suffixes
vid_formats = ['mov', 'avi', 'mp4', 'mpg', 'mpeg', 'm4v', 'wmv', 'mkv']  # acceptable video suffixes
logger = logging.getLogger(__name__)

# Get orientation exif tag
for orientation in ExifTags.TAGS.keys():
    if ExifTags.TAGS[orientation] == 'Orientation':
        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 exif_size(img):
    # Returns exif-corrected PIL size
    s = img.size  # (width, height)
    try:
        rotation = dict(img._getexif().items())[orientation]
        if rotation == 6:  # rotation 270
            s = (s[1], s[0])
        elif rotation == 8:  # rotation 90
            s = (s[1], s[0])
    except:
        pass

    return s


def create_dataloader(path, imgsz, batch_size, stride, opt, hyp=None, augment=False, cache=False, pad=0.0, rect=False,
                      rank=-1, world_size=1, workers=8, image_weights=False, quad=False, prefix=''):
    # Make sure only the first process in DDP process the dataset first, and the following others can use the cache
    with torch_distributed_zero_first(rank):
        dataset = LoadImagesAndLabels(path, imgsz, batch_size,
                                      augment=augment,  # augment images
                                      hyp=hyp,  # augmentation hyperparameters
                                      rect=rect,  # rectangular training
                                      cache_images=cache,
                                      single_cls=opt.single_cls,
                                      stride=int(stride),
                                      pad=pad,
                                      image_weights=image_weights,
                                      prefix=prefix)

    batch_size = min(batch_size, len(dataset))
    nw = min([os.cpu_count() // world_size, batch_size if batch_size > 1 else 0, workers])  # number of workers
    sampler = torch.utils.data.distributed.DistributedSampler(dataset) if rank != -1 else None
    loader = torch.utils.data.DataLoader if image_weights else InfiniteDataLoader
    # Use torch.utils.data.DataLoader() if dataset.properties will update during training else InfiniteDataLoader()
    dataloader = loader(dataset,
                        batch_size=batch_size,
                        num_workers=nw,
                        sampler=sampler,
                        pin_memory=True,
                        collate_fn=LoadImagesAndLabels.collate_fn4 if quad else LoadImagesAndLabels.collate_fn)
    return dataloader, dataset


class InfiniteDataLoader(torch.utils.data.dataloader.DataLoader):
    """ Dataloader that reuses workers

    Uses same syntax as vanilla DataLoader
    """

    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
        object.__setattr__(self, 'batch_sampler', _RepeatSampler(self.batch_sampler))
        self.iterator = super().__iter__()

    def __len__(self):
        return len(self.batch_sampler.sampler)

    def __iter__(self):
        for i in range(len(self)):
            yield next(self.iterator)


class _RepeatSampler(object):
    """ Sampler that repeats forever

    Args:
        sampler (Sampler)
    """

    def __init__(self, sampler):
        self.sampler = sampler

    def __iter__(self):
        while True:
            yield from iter(self.sampler)


class LoadImages:  # for inference
    def __init__(self, path, img_size=640, stride=32):
        p = str(Path(path).absolute())  # os-agnostic absolute path
        if '*' in p:
            files = sorted(glob.glob(p, recursive=True))  # glob
        elif os.path.isdir(p):
            files = sorted(glob.glob(os.path.join(p, '*.*')))  # dir
        elif os.path.isfile(p):
            files = [p]  # files
        else:
            raise Exception(f'ERROR: {p} does not exist')

        images = [x for x in files if x.split('.')[-1].lower() in img_formats]
        videos = [x for x in files if x.split('.')[-1].lower() in vid_formats]
        ni, nv = len(images), len(videos)

        self.img_size = img_size
        self.stride = stride
        self.files = images + videos
        self.nf = ni + nv  # number of files
        self.video_flag = [False] * ni + [True] * nv
        self.mode = 'image'
        if any(videos):
            self.new_video(videos[0])  # new video
        else:
            self.cap = None
        assert self.nf > 0, f'No images or videos found in {p}. ' \
                            f'Supported formats are:\nimages: {img_formats}\nvideos: {vid_formats}'

    def __iter__(self):
        self.count = 0
        return self

    def __next__(self):
        if self.count == self.nf:
            raise StopIteration
        path = self.files[self.count]

        if self.video_flag[self.count]:
            # Read video
            self.mode = 'video'
            ret_val, img0 = self.cap.read()
            if not ret_val:
                self.count += 1
                self.cap.release()
                if self.count == self.nf:  # last video
                    raise StopIteration
                else:
                    path = self.files[self.count]
                    self.new_video(path)
                    ret_val, img0 = self.cap.read()

            self.frame += 1
            print(f'video {self.count + 1}/{self.nf} ({self.frame}/{self.nframes}) {path}: ', end='')

        else:
            # Read image
            self.count += 1
            img0 = cv2.imread(path)  # BGR
            assert img0 is not None, 'Image Not Found ' + path
            #print(f'image {self.count}/{self.nf} {path}: ', end='')

        # Padded resize
        img = letterbox(img0, self.img_size, stride=self.stride)[0]

        # Convert
        img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
        img = np.ascontiguousarray(img)

        return path, img, img0, self.cap

    def new_video(self, path):
        self.frame = 0
        self.cap = cv2.VideoCapture(path)
        self.nframes = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT))

    def __len__(self):
        return self.nf  # number of files


class LoadWebcam:  # for inference
    def __init__(self, pipe='0', img_size=640, stride=32):
        self.img_size = img_size
        self.stride = stride

        if pipe.isnumeric():
            pipe = eval(pipe)  # local camera
        # pipe = 'rtsp://192.168.1.64/1'  # IP camera
        # pipe = 'rtsp://username:password@192.168.1.64/1'  # IP camera with login
        # pipe = 'http://wmccpinetop.axiscam.net/mjpg/video.mjpg'  # IP golf camera

        self.pipe = pipe
        self.cap = cv2.VideoCapture(pipe)  # video capture object
        self.cap.set(cv2.CAP_PROP_BUFFERSIZE, 3)  # set buffer size

    def __iter__(self):
        self.count = -1
        return self

    def __next__(self):
        self.count += 1
        if cv2.waitKey(1) == ord('q'):  # q to quit
            self.cap.release()
            cv2.destroyAllWindows()
            raise StopIteration

        # Read frame
        if self.pipe == 0:  # local camera
            ret_val, img0 = self.cap.read()
            img0 = cv2.flip(img0, 1)  # flip left-right
        else:  # IP camera
            n = 0
            while True:
                n += 1
                self.cap.grab()
                if n % 30 == 0:  # skip frames
                    ret_val, img0 = self.cap.retrieve()
                    if ret_val:
                        break

        # Print
        assert ret_val, f'Camera Error {self.pipe}'
        img_path = 'webcam.jpg'
        print(f'webcam {self.count}: ', end='')

        # Padded resize
        img = letterbox(img0, self.img_size, stride=self.stride)[0]

        # Convert
        img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
        img = np.ascontiguousarray(img)

        return img_path, img, img0, None

    def __len__(self):
        return 0


class LoadStreams:  # multiple IP or RTSP cameras
    def __init__(self, sources='streams.txt', img_size=640, stride=32):
        self.mode = 'stream'
        self.img_size = img_size
        self.stride = stride

        if os.path.isfile(sources):
            with open(sources, 'r') as f:
                sources = [x.strip() for x in f.read().strip().splitlines() if len(x.strip())]
        else:
            sources = [sources]

        n = len(sources)
        self.imgs = [None] * n
        self.sources = [clean_str(x) for x in sources]  # clean source names for later
        for i, s in enumerate(sources):
            # Start the thread to read frames from the video stream
            print(f'{i + 1}/{n}: {s}... ', end='')
            url = eval(s) if s.isnumeric() else s
            if 'youtube.com/' in str(url) or 'youtu.be/' in str(url):  # if source is YouTube video
                check_requirements(('pafy', 'youtube_dl'))
                import pafy
                url = pafy.new(url).getbest(preftype="mp4").url
            cap = cv2.VideoCapture(url)
            assert cap.isOpened(), f'Failed to open {s}'
            w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
            h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
            self.fps = cap.get(cv2.CAP_PROP_FPS) % 100

            _, self.imgs[i] = cap.read()  # guarantee first frame
            thread = Thread(target=self.update, args=([i, cap]), daemon=True)
            print(f' success ({w}x{h} at {self.fps:.2f} FPS).')
            thread.start()
        print('')  # newline

        # check for common shapes
        s = np.stack([letterbox(x, self.img_size, stride=self.stride)[0].shape for x in self.imgs], 0)  # shapes
        self.rect = np.unique(s, axis=0).shape[0] == 1  # rect inference if all shapes equal
        if not self.rect:
            print('WARNING: Different stream shapes detected. For optimal performance supply similarly-shaped streams.')

    def update(self, index, cap):
        # Read next stream frame in a daemon thread
        n = 0
        while cap.isOpened():
            n += 1
            # _, self.imgs[index] = cap.read()
            cap.grab()
            if n == 4:  # read every 4th frame
                success, im