Spaces:
Sleeping
Sleeping
File size: 6,081 Bytes
d4b77ac |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 |
# --------------------------------------------------------
# SiamMask
# Licensed under The MIT License
# Written by Qiang Wang (wangqiang2015 at ia.ac.cn)
# --------------------------------------------------------
from os.path import join, isdir
from os import mkdir, makedirs
import cv2
import numpy as np
import glob
import xml.etree.ElementTree as ET
from concurrent import futures
import time
import sys
# Print iterations progress (thanks StackOverflow)
def printProgress(iteration, total, prefix='', suffix='', decimals=1, barLength=100):
"""
Call in a loop to create terminal progress bar
@params:
iteration - Required : current iteration (Int)
total - Required : total iterations (Int)
prefix - Optional : prefix string (Str)
suffix - Optional : suffix string (Str)
decimals - Optional : positive number of decimals in percent complete (Int)
barLength - Optional : character length of bar (Int)
"""
formatStr = "{0:." + str(decimals) + "f}"
percents = formatStr.format(100 * (iteration / float(total)))
filledLength = int(round(barLength * iteration / float(total)))
bar = '' * filledLength + '-' * (barLength - filledLength)
sys.stdout.write('\r%s |%s| %s%s %s' % (prefix, bar, percents, '%', suffix)),
if iteration == total:
sys.stdout.write('\x1b[2K\r')
sys.stdout.flush()
def crop_hwc(image, bbox, out_sz, padding=(0, 0, 0)):
a = (out_sz - 1) / (bbox[2] - bbox[0])
b = (out_sz - 1) / (bbox[3] - bbox[1])
c = -a * bbox[0]
d = -b * bbox[1]
mapping = np.array([[a, 0, c],
[0, b, d]]).astype(np.float)
crop = cv2.warpAffine(image, mapping, (out_sz, out_sz), borderMode=cv2.BORDER_CONSTANT, borderValue=padding)
return crop
def pos_s_2_bbox(pos, s):
return [pos[0] - s / 2, pos[1] - s / 2, pos[0] + s / 2, pos[1] + s / 2]
def crop_like_SiamFC(image, bbox, context_amount=0.5, exemplar_size=127, instanc_size=255, padding=(0, 0, 0)):
target_pos = [(bbox[2] + bbox[0]) / 2., (bbox[3] + bbox[1]) / 2.]
target_size = [bbox[2] - bbox[0], bbox[3] - bbox[1]]
wc_z = target_size[1] + context_amount * sum(target_size)
hc_z = target_size[0] + context_amount * sum(target_size)
s_z = np.sqrt(wc_z * hc_z)
scale_z = exemplar_size / s_z
d_search = (instanc_size - exemplar_size) / 2
pad = d_search / scale_z
s_x = s_z + 2 * pad
z = crop_hwc(image, pos_s_2_bbox(target_pos, s_z), exemplar_size, padding)
x = crop_hwc(image, pos_s_2_bbox(target_pos, s_x), instanc_size, padding)
return z, x
def crop_like_SiamFCx(image, bbox, context_amount=0.5, exemplar_size=127, instanc_size=255, padding=(0, 0, 0)):
target_pos = [(bbox[2] + bbox[0]) / 2., (bbox[3] + bbox[1]) / 2.]
target_size = [bbox[2] - bbox[0], bbox[3] - bbox[1]]
wc_z = target_size[1] + context_amount * sum(target_size)
hc_z = target_size[0] + context_amount * sum(target_size)
s_z = np.sqrt(wc_z * hc_z)
scale_z = exemplar_size / s_z
d_search = (instanc_size - exemplar_size) / 2
pad = d_search / scale_z
s_x = s_z + 2 * pad
x = crop_hwc(image, pos_s_2_bbox(target_pos, s_x), instanc_size, padding)
return x
def crop_xml(xml, sub_set_crop_path, instanc_size=511):
xmltree = ET.parse(xml)
objects = xmltree.findall('object')
frame_crop_base_path = join(sub_set_crop_path, xml.split('/')[-1].split('.')[0])
if not isdir(frame_crop_base_path): makedirs(frame_crop_base_path)
img_path = xml.replace('xml', 'JPEG').replace('Annotations', 'Data')
im = cv2.imread(img_path)
avg_chans = np.mean(im, axis=(0, 1))
for id, object_iter in enumerate(objects):
bndbox = object_iter.find('bndbox')
bbox = [int(bndbox.find('xmin').text), int(bndbox.find('ymin').text),
int(bndbox.find('xmax').text), int(bndbox.find('ymax').text)]
# z, x = crop_like_SiamFC(im, bbox, instanc_size=instanc_size, padding=avg_chans)
# x = crop_like_SiamFCx(im, bbox, instanc_size=instanc_size, padding=avg_chans)
# cv2.imwrite(join(frame_crop_base_path, '{:06d}.{:02d}.z.jpg'.format(0, id)), z)
x = crop_like_SiamFCx(im, bbox, instanc_size=instanc_size, padding=avg_chans)
cv2.imwrite(join(frame_crop_base_path, '{:06d}.{:02d}.x.jpg'.format(0, id)), x)
def main(instanc_size=511, num_threads=24):
crop_path = './crop{:d}'.format(instanc_size)
if not isdir(crop_path): mkdir(crop_path)
VID_base_path = './ILSVRC2015'
ann_base_path = join(VID_base_path, 'Annotations/DET/train/')
sub_sets = ('ILSVRC2013_train', 'ILSVRC2013_train_extra0', 'ILSVRC2013_train_extra1', 'ILSVRC2013_train_extra2', 'ILSVRC2013_train_extra3', 'ILSVRC2013_train_extra4', 'ILSVRC2013_train_extra5', 'ILSVRC2013_train_extra6', 'ILSVRC2013_train_extra7', 'ILSVRC2013_train_extra8', 'ILSVRC2013_train_extra9', 'ILSVRC2013_train_extra10', 'ILSVRC2014_train_0000', 'ILSVRC2014_train_0001','ILSVRC2014_train_0002','ILSVRC2014_train_0003','ILSVRC2014_train_0004','ILSVRC2014_train_0005','ILSVRC2014_train_0006')
for sub_set in sub_sets:
sub_set_base_path = join(ann_base_path, sub_set)
if 'ILSVRC2013_train' == sub_set:
xmls = sorted(glob.glob(join(sub_set_base_path, '*', '*.xml')))
else:
xmls = sorted(glob.glob(join(sub_set_base_path, '*.xml')))
n_imgs = len(xmls)
sub_set_crop_path = join(crop_path, sub_set)
with futures.ProcessPoolExecutor(max_workers=num_threads) as executor:
fs = [executor.submit(crop_xml, xml, sub_set_crop_path, instanc_size) for xml in xmls]
for i, f in enumerate(futures.as_completed(fs)):
printProgress(i, n_imgs, prefix=sub_set, suffix='Done ', barLength=80)
if __name__ == '__main__':
since = time.time()
main(int(sys.argv[1]), int(sys.argv[2]))
time_elapsed = time.time() - since
print('Total complete in {:.0f}m {:.0f}s'.format(
time_elapsed // 60, time_elapsed % 60))
|