general_json2yolo.py

import contextlib
import json

import cv2
import pandas as pd
from PIL import Image
from collections import defaultdict
from pycocotools import mask

from utils import *


# Convert INFOLKS JSON file into YOLO-format labels ----------------------------
def convert_infolks_json(name, files, img_path):
    # Create folders
    path = make_dirs()

    # Import json
    data = []
    for file in glob.glob(files):
        with open(file) as f:
            jdata = json.load(f)
            jdata['json_file'] = file
            data.append(jdata)

    # Write images and shapes
    name = path + os.sep + name
    file_id, file_name, wh, cat = [], [], [], []
    for x in tqdm(data, desc='Files and Shapes'):
        f = glob.glob(img_path + Path(x['json_file']).stem + '.*')[0]
        file_name.append(f)
        wh.append(exif_size(Image.open(f)))  # (width, height)
        cat.extend(a['classTitle'].lower() for a in x['output']['objects'])  # categories

        # filename
        with open(name + '.txt', 'a') as file:
            file.write('%s\n' % f)

    # Write *.names file
    names = sorted(np.unique(cat))
    # names.pop(names.index('Missing product'))  # remove
    with open(name + '.names', 'a') as file:
        [file.write('%s\n' % a) for a in names]

    # Write labels file
    for i, x in enumerate(tqdm(data, desc='Annotations')):
        label_name = Path(file_name[i]).stem + '.txt'

        with open(path + '/labels/' + label_name, 'a') as file:
            for a in x['output']['objects']:
                # if a['classTitle'] == 'Missing product':
                #    continue  # skip

                category_id = names.index(a['classTitle'].lower())

                # The INFOLKS bounding box format is [x-min, y-min, x-max, y-max]
                box = np.array(a['points']['exterior'], dtype=np.float32).ravel()
                box[[0, 2]] /= wh[i][0]  # normalize x by width
                box[[1, 3]] /= wh[i][1]  # normalize y by height
                box = [box[[0, 2]].mean(), box[[1, 3]].mean(), box[2] - box[0], box[3] - box[1]]  # xywh
                if (box[2] > 0.) and (box[3] > 0.):  # if w > 0 and h > 0
                    file.write('%g %.6f %.6f %.6f %.6f\n' % (category_id, *box))

    # Split data into train, test, and validate files
    split_files(name, file_name)
    write_data_data(name + '.data', nc=len(names))
    print(f'Done. Output saved to {os.getcwd() + os.sep + path}')


# Convert vott JSON file into YOLO-format labels -------------------------------
def convert_vott_json(name, files, img_path):
    # Create folders
    path = make_dirs()
    name = path + os.sep + name

    # Import json
    data = []
    for file in glob.glob(files):
        with open(file) as f:
            jdata = json.load(f)
            jdata['json_file'] = file
            data.append(jdata)

    # Get all categories
    file_name, wh, cat = [], [], []
    for i, x in enumerate(tqdm(data, desc='Files and Shapes')):
        with contextlib.suppress(Exception):
            cat.extend(a['tags'][0] for a in x['regions'])  # categories

    # Write *.names file
    names = sorted(pd.unique(cat))
    with open(name + '.names', 'a') as file:
        [file.write('%s\n' % a) for a in names]

    # Write labels file
    n1, n2 = 0, 0
    missing_images = []
    for i, x in enumerate(tqdm(data, desc='Annotations')):

        f = glob.glob(img_path + x['asset']['name'] + '.jpg')
        if len(f):
            f = f[0]
            file_name.append(f)
            wh = exif_size(Image.open(f))  # (width, height)

            n1 += 1
            if (len(f) > 0) and (wh[0] > 0) and (wh[1] > 0):
                n2 += 1

                # append filename to list
                with open(name + '.txt', 'a') as file:
                    file.write('%s\n' % f)

                # write labelsfile
                label_name = Path(f).stem + '.txt'
                with open(path + '/labels/' + label_name, 'a') as file:
                    for a in x['regions']:
                        category_id = names.index(a['tags'][0])

                        # The INFOLKS bounding box format is [x-min, y-min, x-max, y-max]
                        box = a['boundingBox']
                        box = np.array([box['left'], box['top'], box['width'], box['height']]).ravel()
                        box[[0, 2]] /= wh[0]  # normalize x by width
                        box[[1, 3]] /= wh[1]  # normalize y by height
                        box = [box[0] + box[2] / 2, box[1] + box[3] / 2, box[2], box[3]]  # xywh

                        if (box[2] > 0.) and (box[3] > 0.):  # if w > 0 and h > 0
                            file.write('%g %.6f %.6f %.6f %.6f\n' % (category_id, *box))
        else:
            missing_images.append(x['asset']['name'])

    print('Attempted %g json imports, found %g images, imported %g annotations successfully' % (i, n1, n2))
    if len(missing_images):
        print('WARNING, missing images:', missing_images)

    # Split data into train, test, and validate files
    split_files(name, file_name)
    print(f'Done. Output saved to {os.getcwd() + os.sep + path}')


# Convert ath JSON file into YOLO-format labels --------------------------------
def convert_ath_json(json_dir):  # dir contains json annotations and images
    # Create folders
    dir = make_dirs()  # output directory

    jsons = []
    for dirpath, dirnames, filenames in os.walk(json_dir):
        jsons.extend(
            os.path.join(dirpath, filename)
            for filename in [
                f for f in filenames if f.lower().endswith('.json')
            ]
        )

    # Import json
    n1, n2, n3 = 0, 0, 0
    missing_images, file_name = [], []
    for json_file in sorted(jsons):
        with open(json_file) as f:
            data = json.load(f)

        # # Get classes
        # try:
        #     classes = list(data['_via_attributes']['region']['class']['options'].values())  # classes
        # except:
        #     classes = list(data['_via_attributes']['region']['Class']['options'].values())  # classes

        # # Write *.names file
        # names = pd.unique(classes)  # preserves sort order
        # with open(dir + 'data.names', 'w') as f:
        #     [f.write('%s\n' % a) for a in names]

        # Write labels file
        for x in tqdm(data['_via_img_metadata'].values(), desc=f'Processing {json_file}'):
            image_file = str(Path(json_file).parent / x['filename'])
            f = glob.glob(image_file)  # image file
            if len(f):
                f = f[0]
                file_name.append(f)
                wh = exif_size(Image.open(f))  # (width, height)

                n1 += 1  # all images
                if len(f) > 0 and wh[0] > 0 and wh[1] > 0:
                    label_file = dir + 'labels/' + Path(f).stem + '.txt'

                    nlabels = 0
                    try:
                        with open(label_file, 'a') as file:  # write labelsfile
                            # try:
                            #     category_id = int(a['region_attributes']['class'])
                            # except:
                            #     category_id = int(a['region_attributes']['Class'])
                            category_id = 0  # single-class

                            for a in x['regions']:
                                # bounding box format is [x-min, y-min, x-max, y-max]
                                box = a['shape_attributes']
                                box = np.array([box['x'], box['y'], box['width'], box['height']],
                                               dtype=np.float32).ravel()
                                box[[0, 2]] /= wh[0]  # normalize x by width
                                box[[1, 3]] /= wh[1]  # normalize y by height
                                box = [box[0] + box[2] / 2, box[1] + box[3] / 2, box[2],
                                       box[3]]  # xywh (left-top to center x-y)

                                if box[2] > 0. and box[3] > 0.:  # if w > 0 and h > 0
                                    file.write('%g %.6f %.6f %.6f %.6f\n' % (category_id, *box))
                                    n3 += 1
                                    nlabels += 1

                        if nlabels == 0:  # remove non-labelled images from dataset
                            os.system(f'rm {label_file}')
                            # print('no labels for %s' % f)
                            continue  # next file

                        # write image
                        img_size = 4096  # resize to maximum
                        img = cv2.imread(f)  # BGR
                        assert img is not None, 'Image Not Found ' + f
                        r = img_size / max(img.shape)  # size ratio
                        if r < 1:  # downsize if necessary
                            h, w, _ = img.shape
                            img = cv2.resize(img, (int(w * r), int(h * r)), interpolation=cv2.INTER_AREA)

                        ifile = dir + 'images/' + Path(f).name
                        if cv2.imwrite(ifile, img):  # if success append image to list
                            with open(dir + 'data.txt', 'a') as file:
                                file.write('%s\n' % ifile)
                            n2 += 1  # correct images

                    except Exception:
                        os.system(f'rm {label_file}')
                        print(f'problem with {f}')

            else:
                missing_images.append(image_file)

    nm = len(missing_images)  # number missing
    print('\nFound %g JSONs with %g labels over %g images. Found %g images, labelled %g images successfully' %
          (len(jsons), n3, n1, n1 - nm, n2))
    if len(missing_images):
        print('WARNING, missing images:', missing_images)

    # Write *.names file
    names = ['knife']  # preserves sort order
    with open(dir + 'data.names', 'w') as f:
        [f.write('%s\n' % a) for a in names]

    # Split data into train, test, and validate files
    split_rows_simple(dir + 'data.txt')
    write_data_data(dir + 'data.data', nc=1)
    print(f'Done. Output saved to {Path(dir).absolute()}')


def convert_coco_json(json_dir='../coco/annotations/', use_segments=False, use_keypoints=False, skip_iscrowd_1=False, rle_to_polygons_holes=False, save_rle_masks=False, cls91to80=False, category_id_starts_from_0=False):
    save_dir = make_dirs()  # output directory
    coco80 = coco91_to_coco80_class()

    # Import json
    for json_file in sorted(Path(json_dir).resolve().glob('*.json')):
        fn = Path(save_dir) / 'labels' / json_file.stem.replace('instances_', '')  # folder name
        fn.mkdir()
        with open(json_file) as f:
            data = json.load(f)

        # Create image dict
        images = {'%g' % x['id']: x for x in data['images']}
        # Create image-annotations dict
        imgToAnns = defaultdict(list)
        for ann in data['annotations']:
            imgToAnns[ann['image_id']].append(ann)

        if use_keypoints:
            show_kpt_shape_flip_idx(data)

        # Write labels file
        for img_id, anns in tqdm(imgToAnns.items(), desc=f'Annotations {json_file}'):
            img = images['%g' % img_id]
            h, w, f = img['height'], img['width'], img['file_name']
            f = f.split('/')[-1]
            
            bboxes = []
            segments = []
            keypoints = []
            for ann in anns:
                if skip_iscrowd_1 and "iscrowd" in ann and ann["iscrowd"]:
                    continue
                # The COCO box format is [top left x, top left y, width, height]
                if 'bbox' not in ann:
                    continue
                elif len(ann['bbox']) == 0:
                    box = bbox_from_keypoints(ann)
                else:
                    box = np.array(ann['bbox'], dtype=np.float64)
                box[:2] += box[2:] / 2  # xy top-left corner to center
                box[[0, 2]] /= w  # normalize x
                box[[1, 3]] /= h  # normalize y
                if box[2] <= 0 or box[3] <= 0:  # if w <= 0 and h <= 0
                    continue

                if category_id_starts_from_0:
                    cls = ann['category_id']
                else:
                    cls = coco80[ann['category_id'] - 1] if cls91to80 else ann['category_id'] - 1  # class
                box = [cls] + box.tolist()
                bboxes.append(box)
                set_coco_segments(use_segments, rle_to_polygons_holes, save_rle_masks, w, h, f, fn, ann, cls, segments)
                set_coco_keypoints(use_keypoints, w, h, f, fn, ann, box, keypoints)

            # Write
            with open((fn / f).with_suffix('.txt'), 'a') as file:
                for i in range(len(bboxes)):
                    count = 0
                    if use_keypoints and len(keypoints[i]) > 0:
                        line = *(keypoints[i]),
                        file.write(('%g ' * len(line)).rstrip() % line + '\n')
                        count += 1
                    if use_segments and len(segments[i]) > 0:
                        line = *(segments[i]),
                        file.write(('%g ' * len(line)).rstrip() % line + '\n')
                        count += 1
                    if count == 0:
                        line = *(bboxes[i]),
                        file.write(('%g ' * len(line)).rstrip() % line + '\n')

def set_coco_segments(use_segments, rle_to_polygons_holes, save_rle_masks, w, h, f, fn, ann, cls, segments):
    if not use_segments:
        return
    if 'segmentation' not in ann:
        segments.append([])
        return
    if len(ann['segmentation']) == 0:
        segments.append([])
        return
    if isinstance(ann['segmentation'], dict):
        file_name = f.split('.')[0]
        file_name = file_name + '_' + str(len(segments)) + '.png'
        mask_path = (fn / file_name)
        ann['segmentation'] = rle2polygon(ann['segmentation'], rle_to_polygons_holes, save_rle_masks, mask_path)
        if len(ann['segmentation']) == 0:
            segments.append([])
            return
    if len(ann['segmentation']) > 1:
        s = merge_multi_segment(ann['segmentation'])
        s = (np.concatenate(s, axis=0) / np.array([w, h])).reshape(-1).tolist()
    else:
        s = [j for i in ann['segmentation'] for j in i]  # all segments concatenated
        s = (np.array(s).reshape(-1, 2) / np.array([w, h])).reshape(-1).tolist()
    s = [cls] + s
    segments.append(s)

def set_coco_keypoints(use_keypoints, w, h, f, fn, ann, box, keypoints):
    if not use_keypoints:
        return
    if 'keypoints' not in ann:
        keypoints.append([])
        return
    if len(ann['keypoints']) == 0:
        keypoints.append([])
        return
    else:
        k = (np.array(ann['keypoints']).reshape(-1, 3) / np.array([w, h, 1])).reshape(-1).tolist()
        k = box + k
        keypoints.append(k)

def bbox_from_keypoints(ann):
    if 'keypoints' in ann:
        k = np.array(ann['keypoints']).reshape(-1, 3)
        x_list, y_list, v_list = zip(*k)
        box = [min(x_list), min(y_list), max(x_list) - min(x_list), max(y_list) - min(y_list)]
        return np.array(box, dtype=np.float64)
    else:
        return [0, 0, 0, 0]

def show_kpt_shape_flip_idx(data):
    if 'categories' not in data:
        return
    for category in data['categories']:
        if 'keypoints' not in category:
            continue
        keypoints = category['keypoints']
        num = len(keypoints)
        print('kpt_shape: [' + str(num) + ', 3]')
        flip_idx = list(range(num))
        for i, name in enumerate(keypoints):
            name = name.lower()
            left_pos = name.find('left')
            if left_pos < 0:
                continue
            name_right = name.replace('left', 'right')
            for j, namej in enumerate(keypoints):
                namej = namej.lower()
                if namej == name_right:
                    flip_idx[i] = j
                    flip_idx[j] = i
                    break
        print('flip_idx: [' + ', '.join(str(x) for x in flip_idx) + ']')


def is_clockwise(contour):
    value = 0
    num = len(contour)
    for i, point in enumerate(contour):
        p1 = contour[i]
        if i < num - 1:
            p2 = contour[i + 1]
        else:
            p2 = contour[0]
        value += (p2[0][0] - p1[0][0]) * (p2[0][1] + p1[0][1])
    return value < 0

def get_merge_point_idx(contour1, contour2):
    idx1 = 0
    idx2 = 0
    distance_min = -1
    for i, p1 in enumerate(contour1):
        for j, p2 in enumerate(contour2):
            distance = pow(p2[0][0] - p1[0][0], 2) + pow(p2[0][1] - p1[0][1], 2)
            if distance_min < 0:
                distance_min = distance
                idx1 = i
                idx2 = j
            elif distance < distance_min:
                distance_min = distance
                idx1 = i
                idx2 = j
    return idx1, idx2

def merge_contours(contour1, contour2, idx1, idx2):
    contour = []
    for i in list(range(0, idx1 + 1)):
        contour.append(contour1[i])
    for i in list(range(idx2, len(contour2))):
        contour.append(contour2[i])
    for i in list(range(0, idx2 + 1)):
        contour.append(contour2[i])
    for i in list(range(idx1, len(contour1))):
        contour.append(contour1[i])
    contour = np.array(contour)
    return contour

def merge_with_parent(contour_parent, contour):
    if not is_clockwise(contour_parent):
        contour_parent = contour_parent[::-1]
    if is_clockwise(contour):
        contour = contour[::-1]
    idx1, idx2 = get_merge_point_idx(contour_parent, contour)
    return merge_contours(contour_parent, contour, idx1, idx2)

def mask2polygon_external(image):
    contours, hierarchies = cv2.findContours(image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_TC89_KCOS)
    if len(contours) == 0:
        return []
    contours_approx = []
    for contour in contours:
        epsilon = 0.001 * cv2.arcLength(contour, True)
        contour_approx = cv2.approxPolyDP(contour, epsilon, True)
        contours_approx.append(contour_approx)
    polygons = []
    for contour in contours_approx:
        if len(contour) >= 3:
            polygon = contour.flatten().tolist()
            polygons.append(polygon)
    return polygons 

def mask2polygon_holes(image):
    contours, hierarchies = cv2.findContours(image, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_TC89_KCOS)
    if len(contours) == 0:
        return []
    contours_approx = []
    for contour in contours:
        epsilon = 0.001 * cv2.arcLength(contour, True)
        contour_approx = cv2.approxPolyDP(contour, epsilon, True)
        contours_approx.append(contour_approx)
    contours_parent = []
    for i, contour in enumerate(contours_approx):
        parent_idx = hierarchies[0][i][3]
        if parent_idx < 0 and len(contour) >= 3:
            contours_parent.append(contour)
        else:
            contours_parent.append([])
    for i, contour in enumerate(contours_approx):
        parent_idx = hierarchies[0][i][3]
        if parent_idx >= 0 and len(contour) >= 3:
            contour_parent = contours_parent[parent_idx]
            if len(contour_parent) == 0:
                continue
            contours_parent[parent_idx] = merge_with_parent(contour_parent, contour)
    contours_parent_tmp = []
    for contour in contours_parent:
        if len(contour) == 0:
            continue
        contours_parent_tmp.append(contour)
    polygons = []
    for contour in contours_parent_tmp:
        polygon = contour.flatten().tolist()
        polygons.append(polygon)
    return polygons 

def rle2polygon(segmentation, rle_to_polygons_holes, save_rle_masks, mask_path):
    if isinstance(segmentation["counts"], list):
        segmentation = mask.frPyObjects(segmentation, *segmentation["size"])
    m = mask.decode(segmentation) 
    m[m > 0] = 255
    if save_rle_masks:
        import PIL.Image
        pil_image = PIL.Image.fromarray(m)
        pil_image.save(mask_path)
    if rle_to_polygons_holes:
        polygons = mask2polygon_holes(m)
    else:
        polygons = mask2polygon_external(m)
    return polygons

def min_index(arr1, arr2):
    """Find a pair of indexes with the shortest distance. 
    Args:
        arr1: (N, 2).
        arr2: (M, 2).
    Return:
        a pair of indexes(tuple).
    """
    dis = ((arr1[:, None, :] - arr2[None, :, :]) ** 2).sum(-1)
    return np.unravel_index(np.argmin(dis, axis=None), dis.shape)


def merge_multi_segment(segments):
    """Merge multi segments to one list.
    Find the coordinates with min distance between each segment,
    then connect these coordinates with one thin line to merge all 
    segments into one.

    Args:
        segments(List(List)): original segmentations in coco's json file.
            like [segmentation1, segmentation2,...], 
            each segmentation is a list of coordinates.
    """
    s = []
    segments = [np.array(i).reshape(-1, 2) for i in segments]
    idx_list = [[] for _ in range(len(segments))]

    # record the indexes with min distance between each segment
    for i in range(1, len(segments)):
        idx1, idx2 = min_index(segments[i - 1], segments[i])
        idx_list[i - 1].append(idx1)
        idx_list[i].append(idx2)

    # use two round to connect all the segments
    for k in range(2):
        # forward connection
        if k == 0:
            for i, idx in enumerate(idx_list):
                # middle segments have two indexes
                # reverse the index of middle segments
                if len(idx) == 2 and idx[0] > idx[1]:
                    idx = idx[::-1]
                    segments[i] = segments[i][::-1, :]

                segments[i] = np.roll(segments[i], -idx[0], axis=0)
                segments[i] = np.concatenate([segments[i], segments[i][:1]])
                # deal with the first segment and the last one
                if i in [0, len(idx_list) - 1]:
                    s.append(segments[i])
                else:
                    idx = [0, idx[1] - idx[0]]
                    s.append(segments[i][idx[0]:idx[1] + 1])

        else:
            for i in range(len(idx_list) - 1, -1, -1):
                if i not in [0, len(idx_list) - 1]:
                    idx = idx_list[i]
                    nidx = abs(idx[1] - idx[0])
                    s.append(segments[i][nidx:])
    return s


def delete_dsstore(path='../datasets'):
    # Delete apple .DS_store files
    from pathlib import Path
    files = list(Path(path).rglob('.DS_store'))
    print(files)
    for f in files:
        f.unlink()


if __name__ == '__main__':
    source = 'COCO'

    if source == 'COCO':
        convert_coco_json('../datasets/coco/annotations',  # directory with *.json
                          use_segments=True,
                          use_keypoints=True,
                          skip_iscrowd_1=False,
                          rle_to_polygons_holes=False,
                          save_rle_masks=False,
                          cls91to80=False,
                          category_id_starts_from_0=False)

    elif source == 'infolks':  # Infolks https://infolks.info/
        convert_infolks_json(name='out',
                             files='../data/sm4/json/*.json',
                             img_path='../data/sm4/images/')

    elif source == 'vott':  # VoTT https://github.com/microsoft/VoTT
        convert_vott_json(name='data',
                          files='../../Downloads/athena_day/20190715/*.json',
                          img_path='../../Downloads/athena_day/20190715/')  # images folder

    elif source == 'ath':  # ath format
        convert_ath_json(json_dir='../../Downloads/athena/')  # images folder

    # zip results
    # os.system('zip -r ../coco.zip ../coco')