-
-
Save davesie/0535698482c48b97904993772f8a3367 to your computer and use it in GitHub Desktop.
Transform Tsinghua-Tencent 100K Dataset Annotations to COCO Format
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
''' | |
Transform Tsinghua-Tencent 100K Dataset Annotations to COCO Format | |
Source: | |
https://gist.github.com/zhaoweizhong/7ca1f4d4fdcb0aa198732a0e7cc9b908#file-tt100k2coco-py | |
''' | |
import json | |
import argparse | |
def load_json(file_name): | |
file = open(file_name, 'r').read() | |
return json.loads(file) | |
def parse(data, data_type, output_name): | |
# File Format | |
result = { | |
"info": { | |
"description": "TT100K Dataset COCO Format", | |
"url": "https://github.com/zhaoweizhong", | |
"version": "1.0", | |
"year": 2020, | |
"contributor": "Zhaowei Zhong", | |
"date_created": "2020/01/04" | |
}, | |
"licenses": [ | |
{ | |
"url": " ", | |
"id": 1, | |
"name": " " | |
} | |
], | |
"images": [], | |
"annotations": [], | |
"categories": [] | |
} | |
# Categories | |
categories = ["pl80", "w9", "p6", "ph4.2", "i8", "w14", "w33", "pa13", "im", "pl90", "w58", "il70", "p5", "pm55", | |
"pl60", "ip", "p11", "pdd", "wc", "i2r", "w30", "pmr", "p23", "pl15", "pm10", "pss", "w1", "p4", | |
"w38", "w50", "w34", "pw3.5", "iz", "w39", "w11", "p1n", "pr70", "pd", "pnl", "pg", "ph5.3", "w66", | |
"il80", "pb", "pbm", "pm5", "w24", "w67", "w49", "pm40", "ph4", "w45", "i4", "w37", "ph2.6", "pl70", | |
"ph5.5", "i14", "i11", "p7", "p29", "pne", "pr60", "pm13", "ph4.5", "p12", "p3", "w40", "pl5", "w13", | |
"pr10", "p14", "i4l", "pr30", "pw4.2", "w16", "p17", "ph3", "i9", "w15", "w35", "pa8", "pt", "pr45", | |
"w17", "pl30", "pcs", "pctl", "pr50", "ph4.4", "pm46", "pm35", "i15", "pa12", "pclr", "i1", "pcd", | |
"pbp", "pcr", "w28", "ps", "pm8", "w18", "w2", "w52", "ph2.9", "ph1.8", "pe", "p20", "w36", "p10", | |
"pn", "pa14", "w54", "ph3.2", "p2", "ph2.5", "w62", "w55", "pw3", "pw4.5", "i12", "ph4.3", "phclr", | |
"i10", "pr5", "i13", "w10", "p26", "w26", "p8", "w5", "w42", "il50", "p13", "pr40", "p25", "w41", | |
"pl20", "ph4.8", "pnlc", "ph3.3", "w29", "ph2.1", "w53", "pm30", "p24", "p21", "pl40", "w27", "pmb", | |
"pc", "i6", "pr20", "p18", "ph3.8", "pm50", "pm25", "i2", "w22", "w47", "w56", "pl120", "ph2.8", "i7", | |
"w12", "pm1.5", "pm2.5", "w32", "pm15", "ph5", "w19", "pw3.2", "pw2.5", "pl10", "il60", "w57", "w48", | |
"w60", "pl100", "pr80", "p16", "pl110", "w59", "w64", "w20", "ph2", "p9", "il100", "w31", "w65", | |
"ph2.4", "pr100", "p19", "ph3.5", "pa10", "pcl", "pl35", "p15", "w7", "pa6", "phcs", "w43", "p28", | |
"w6", "w3", "w25", "pl25", "il110", "p1", "w46", "pn-2", "w51", "w44", "w63", "w23", "pm20", "w8", | |
"pmblr", "w4", "i5", "il90", "w21", "p27", "pl50", "pl65", "w61", "ph2.2", "pm2", "i3", "pa18", "pw4"] | |
i = 1 | |
for category in categories: | |
result['categories'].append({ | |
"id": i, | |
"name": category | |
}) | |
i = i + 1 | |
# Images | |
for img in data['imgs']: | |
if data_type == 'all': | |
result['images'].append({ | |
"license": 1, | |
"file_name": data['imgs'][img]['path'][len(data_type) + 1:], | |
"height": 2048, | |
"width": 2048, | |
"id": data['imgs'][img]['id'] | |
}) | |
elif str(data['imgs'][img]['path']).find(data_type) != -1: | |
result['images'].append({ | |
"license": 1, | |
"file_name": data['imgs'][img]['path'][len(data_type) + 1:], | |
"height": 2048, | |
"width": 2048, | |
"id": data['imgs'][img]['id'] | |
}) | |
# Annotations | |
i = 0 | |
for img in data['imgs']: | |
if data_type == 'all': | |
for box in data['imgs'][img]['objects']: | |
result['annotations'].append({ | |
"segmentation": [], | |
"area": (box['bbox']['xmax'] - box['bbox']['xmin']) * (box['bbox']['ymax'] - box['bbox']['ymin']), | |
"iscrowd": 0, | |
"image_id": data['imgs'][img]['id'], | |
"bbox": [ | |
box['bbox']['xmin'], | |
box['bbox']['ymin'], | |
box['bbox']['xmax'] - box['bbox']['xmin'], | |
box['bbox']['ymax'] - box['bbox']['ymin'] | |
], | |
"category_id": categories.index(box['category']) + 1, | |
"id": i | |
}) | |
if ('ellipse_org' in box): | |
for xy in box['ellipse_org']: | |
result['annotations'][i]['segmentation'][0].append(xy[0]) | |
result['annotations'][i]['segmentation'][0].append(xy[1]) | |
elif 'polygon' in box: | |
for xy in box['polygon']: | |
result['annotations'][i]['segmentation'][0].append(xy[0]) | |
result['annotations'][i]['segmentation'][0].append(xy[1]) | |
i = i + 1 | |
elif str(data['imgs'][img]['path']).find(data_type) != -1: | |
for box in data['imgs'][img]['objects']: | |
result['annotations'].append({ | |
"segmentation": [], | |
"area": (box['bbox']['xmax'] - box['bbox']['xmin']) * (box['bbox']['ymax'] - box['bbox']['ymin']), | |
"iscrowd": 0, | |
"image_id": data['imgs'][img]['id'], | |
"bbox": [ | |
box['bbox']['xmin'], | |
box['bbox']['ymin'], | |
box['bbox']['xmax'] - box['bbox']['xmin'], | |
box['bbox']['ymax'] - box['bbox']['ymin'] | |
], | |
"category_id": categories.index(box['category']) + 1, | |
"id": i | |
}) | |
if ('ellipse_org' in box): | |
for xy in box['ellipse_org']: | |
result['annotations'][i]['segmentation'][0].append(xy[0]) | |
result['annotations'][i]['segmentation'][0].append(xy[1]) | |
elif 'polygon' in box: | |
for xy in box['polygon']: | |
result['annotations'][i]['segmentation'][0].append(xy[0]) | |
result['annotations'][i]['segmentation'][0].append(xy[1]) | |
i = i + 1 | |
with open(output_name, "w") as f: | |
json.dump(result, f) | |
if __name__ == '__main__': | |
print('--- START ---') | |
parser = argparse.ArgumentParser() | |
parser.add_argument('-t', '--data_type', type=str, default='train') | |
parser.add_argument('-f', '--file_name', type=str, default='data.json') | |
parser.add_argument('-o', '--output_name', type=str, default='output.json') | |
args = parser.parse_args() | |
data_type = args.data_type | |
file_name = args.file_name | |
output_name = args.output_name | |
data = load_json(file_name) | |
parse(data, data_type, output_name) | |
print('--- DONE ---') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment