yolov5/utils/datasets.py

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Dataloaders and dataset utils
"""

import glob
import hashlib
import json
import math
import os
import random
import shutil
import time
from itertools import repeat
from multiprocessing.pool import Pool, ThreadPool
from pathlib import Path
from threading import Thread
from zipfile import ZipFile

import cv2
import numpy as np
import torch
import torch.nn.functional as F
import yaml
from PIL import ExifTags, Image, ImageOps
from tqdm import tqdm

from .augmentations import letterbox
from .general import (xyn2xy, xywh2xyxy, xywhn2xyxy)

# Parameters
HELP_URL = 'https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data'
IMG_FORMATS = ['bmp', 'dng', 'jpeg', 'jpg', 'mpo', 'png', 'tif', 'tiff', 'webp']  # include image suffixes
VID_FORMATS = ['asf', 'avi', 'gif', 'm4v', 'mkv', 'mov', 'mp4', 'mpeg', 'mpg', 'wmv']  # include video suffixes

# Get orientation exif tag
for orientation in ExifTags.TAGS.keys():
    if ExifTags.TAGS[orientation] == 'Orientation':
        break


def get_hash(paths):
    # Returns a single hash value of a list of paths (files or dirs)
    size = sum(os.path.getsize(p) for p in paths if os.path.exists(p))  # sizes
    h = hashlib.md5(str(size).encode())  # hash sizes
    h.update(''.join(paths).encode())  # hash paths
    return h.hexdigest()  # return hash


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 exif_transpose(image):
    """
    Transpose a PIL image accordingly if it has an EXIF Orientation tag.
    Inplace version of https://github.com/python-pillow/Pillow/blob/master/src/PIL/ImageOps.py exif_transpose()

    :param image: The image to transpose.
    :return: An image.
    """
    exif = image.getexif()
    orientation = exif.get(0x0112, 1)  # default 1
    if orientation > 1:
        method = {2: Image.FLIP_LEFT_RIGHT,
                  3: Image.ROTATE_180,
                  4: Image.FLIP_TOP_BOTTOM,
                  5: Image.TRANSPOSE,
                  6: Image.ROTATE_270,
                  7: Image.TRANSVERSE,
                  8: Image.ROTATE_90,
                  }.get(orientation)
        if method is not None:
            image = image.transpose(method)
            del exif[0x0112]
            image.info["exif"] = exif.tobytes()
    return image


def pil_to_cv(pil_img, img_size=320, stride=32, auto=True):
    np_img = np.array(pil_img)
    
    img0 = cv2.cvtColor(np_img, cv2.COLOR_RGB2BGR)

    img = letterbox(img0, img_size, stride=stride, auto=auto)[0]
    img = img.transpose((2, 0, 1))[::-1]  # HWC to CHW, BGR to RGB
    img = np.ascontiguousarray(img)

    return img, img0


class LoadImages:
    # YOLOv5 image/video dataloader, i.e. `python detect.py --source image.jpg/vid.mp4`
    def __init__(self, path, img_size=640, stride=32, auto=True):
        p = str(Path(path).resolve())  # 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'
        self.auto = auto
        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()
            while 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
            s = f'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: '

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

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

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

        return path, img, img0, self.cap, s

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

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


def img2label_paths(img_paths):
    # Define label paths as a function of image paths
    sa, sb = os.sep + 'images' + os.sep, os.sep + 'labels' + os.sep  # /images/, /labels/ substrings
    return [sb.join(x.rsplit(sa, 1)).rsplit('.', 1)[0] + '.txt' for x in img_paths]


# Ancillary functions --------------------------------------------------------------------------------------------------
def load_image(self, i):
    # loads 1 image from dataset index 'i', returns im, original hw, resized hw
    im = self.imgs[i]
    if im is None:  # not cached in ram
        npy = self.img_npy[i]
        if npy and npy.exists():  # load npy
            im = np.load(npy)
        else:  # read image
            path = self.img_files[i]
            im = cv2.imread(path)  # BGR
            assert im is not None, f'Image Not Found {path}'
        h0, w0 = im.shape[:2]  # orig hw
        r = self.img_size / max(h0, w0)  # ratio
        if r != 1:  # if sizes are not equal
            im = cv2.resize(im, (int(w0 * r), int(h0 * r)),
                            interpolation=cv2.INTER_AREA if r < 1 and not self.augment else cv2.INTER_LINEAR)
        return im, (h0, w0), im.shape[:2]  # im, hw_original, hw_resized
    else:
        return self.imgs[i], self.img_hw0[i], self.img_hw[i]  # im, hw_original, hw_resized


def load_mosaic(self, index):
    # YOLOv5 4-mosaic loader. Loads 1 image + 3 random images into a 4-image mosaic
    labels4, segments4 = [], []
    s = self.img_size
    yc, xc = (int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border)  # mosaic center x, y
    indices = [index] + random.choices(self.indices, k=3)  # 3 additional image indices
    random.shuffle(indices)
    for i, index in enumerate(indices):
        # Load image
        img, _, (h, w) = load_image(self, index)

        # place img in img4
        if i == 0:  # top left
            img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
            x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc  # xmin, ymin, xmax, ymax (large image)
            x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h  # xmin, ymin, xmax, ymax (small image)
        elif i == 1:  # top right
            x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
            x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
        elif i == 2:  # bottom left
            x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
            x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h)
        elif i == 3:  # bottom right
            x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)
            x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)

        img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b]  # img4[ymin:ymax, xmin:xmax]
        padw = x1a - x1b
        padh = y1a - y1b

        # Labels
        labels, segments = self.labels[index].copy(), self.segments[index].copy()
        if labels.size:
            labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padw, padh)  # normalized xywh to pixel xyxy format
            segments = [xyn2xy(x, w, h, padw, padh) for x in segments]
        labels4.append(labels)
        segments4.extend(segments)

    # Concat/clip labels
    labels4 = np.concatenate(labels4, 0)
    for x in (labels4[:, 1:], *segments4):
        np.clip(x, 0, 2 * s, out=x)  # clip when using random_perspective()
    # img4, labels4 = replicate(img4, labels4)  # replicate

    return img4, labels4


def load_mosaic9(self, index):
    # YOLOv5 9-mosaic loader. Loads 1 image + 8 random images into a 9-image mosaic
    labels9, segments9 = [], []
    s = self.img_size
    indices = [index] + random.choices(self.indices, k=8)  # 8 additional image indices
    random.shuffle(indices)
    for i, index in enumerate(indices):
        # Load image
        img, _, (h, w) = load_image(self, index)

        # place img in img9
        if i == 0:  # center
            img9 = np.full((s * 3, s * 3, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
            h0, w0 = h, w
            c = s, s, s + w, s + h  # xmin, ymin, xmax, ymax (base) coordinates
        elif i == 1:  # top
            c = s, s - h, s + w, s
        elif i == 2:  # top right
            c = s + wp, s - h, s + wp + w, s
        elif i == 3:  # right
            c = s + w0, s, s + w0 + w, s + h
        elif i == 4:  # bottom right
            c = s + w0, s + hp, s + w0 + w, s + hp + h
        elif i == 5:  # bottom
            c = s + w0 - w, s + h0, s + w0, s + h0 + h
        elif i == 6:  # bottom left
            c = s + w0 - wp - w, s + h0, s + w0 - wp, s + h0 + h
        elif i == 7:  # left
            c = s - w, s + h0 - h, s, s + h0
        elif i == 8:  # top left
            c = s - w, s + h0 - hp - h, s, s + h0 - hp

        padx, pady = c[:2]
        x1, y1, x2, y2 = (max(x, 0) for x in c)  # allocate coords

        # Labels
        labels, segments = self.labels[index].copy(), self.segments[index].copy()
        if labels.size:
            labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padx, pady)  # normalized xywh to pixel xyxy format
            segments = [xyn2xy(x, w, h, padx, pady) for x in segments]
        labels9.append(labels)
        segments9.extend(segments)

        # Image
        img9[y1:y2, x1:x2] = img[y1 - pady:, x1 - padx:]  # img9[ymin:ymax, xmin:xmax]
        hp, wp = h, w  # height, width previous

    # Offset
    yc, xc = (int(random.uniform(0, s)) for _ in self.mosaic_border)  # mosaic center x, y
    img9 = img9[yc:yc + 2 * s, xc:xc + 2 * s]

    # Concat/clip labels
    labels9 = np.concatenate(labels9, 0)
    labels9[:, [1, 3]] -= xc
    labels9[:, [2, 4]] -= yc
    c = np.array([xc, yc])  # centers
    segments9 = [x - c for x in segments9]

    for x in (labels9[:, 1:], *segments9):
        np.clip(x, 0, 2 * s, out=x)  # clip when using random_perspective()
    # img9, labels9 = replicate(img9, labels9)  # replicate


    return img9, labels9


def create_folder(path='./new'):
    # Create folder
    if os.path.exists(path):
        shutil.rmtree(path)  # delete output folder
    os.makedirs(path)  # make new output folder


def flatten_recursive(path='../datasets/coco128'):
    # Flatten a recursive directory by bringing all files to top level
    new_path = Path(path + '_flat')
    create_folder(new_path)
    for file in tqdm(glob.glob(str(Path(path)) + '/**/*.*', recursive=True)):
        shutil.copyfile(file, new_path / Path(file).name)


def extract_boxes(path='../datasets/coco128'):  # from utils.datasets import *; extract_boxes()
    # Convert detection dataset into classification dataset, with one directory per class
    path = Path(path)  # images dir
    shutil.rmtree(path / 'classifier') if (path / 'classifier').is_dir() else None  # remove existing
    files = list(path.rglob('*.*'))
    n = len(files)  # number of files
    for im_file in tqdm(files, total=n):
        if im_file.suffix[1:] in IMG_FORMATS:
            # image
            im = cv2.imread(str(im_file))[..., ::-1]  # BGR to RGB
            h, w = im.shape[:2]

            # labels
            lb_file = Path(img2label_paths([str(im_file)])[0])
            if Path(lb_file).exists():
                with open(lb_file) as f:
                    lb = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32)  # labels

                for j, x in enumerate(lb):
                    c = int(x[0])  # class
                    f = (path / 'classifier') / f'{c}' / f'{path.stem}_{im_file.stem}_{j}.jpg'  # new filename
                    if not f.parent.is_dir():
                        f.parent.mkdir(parents=True)

                    b = x[1:] * [w, h, w, h]  # box
                    # b[2:] = b[2:].max()  # rectangle to square
                    b[2:] = b[2:] * 1.2 + 3  # pad
                    b = xywh2xyxy(b.reshape(-1, 4)).ravel().astype(np.int)

                    b[[0, 2]] = np.clip(b[[0, 2]], 0, w)  # clip boxes outside of image
                    b[[1, 3]] = np.clip(b[[1, 3]], 0, h)
                    assert cv2.imwrite(str(f), im[b[1]:b[3], b[0]:b[2]]), f'box failure in {f}'


def autosplit(path='../datasets/coco128/images', weights=(0.9, 0.1, 0.0), annotated_only=False):
    """ Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files
    Usage: from utils.datasets import *; autosplit()
    Arguments
        path:            Path to images directory
        weights:         Train, val, test weights (list, tuple)
        annotated_only:  Only use images with an annotated txt file
    """
    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
    [(path.parent / x).unlink(missing_ok=True) for x in txt]  # remove existing

    print(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('./' + img.relative_to(path.parent).as_posix() + '\n')  # add image to txt file