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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
|
"""
Crop images to prepare for training
"""
import click
# from PIL import Image, ImageOps, ImageFilter, ImageDraw
from app.settings import types
from app.utils import click_utils
from app.settings import app_cfg as cfg
color_filters = {'color': 1, 'gray': 2, 'all': 3}
@click.command()
@click.option('-i', '--input', 'opt_fp_in', required=True,
help='Input CSV (eg image_files.csv)')
@click.option('-m', '--media', 'opt_dir_media', required=True,
help='Input media directory')
@click.option('-o', '--output', 'opt_fp_out', required=True,
help='Output CSV')
@click.option('--size', 'opt_size',
type=(int, int), default=(300, 300),
help='Output image size')
@click.option('-t', '--detector-type', 'opt_detector_type',
type=cfg.FaceDetectNetVar,
default=click_utils.get_default(types.FaceDetectNet.DLIB_CNN),
help=click_utils.show_help(types.FaceDetectNet))
@click.option('-g', '--gpu', 'opt_gpu', default=0,
help='GPU index')
@click.option('--conf', 'opt_conf_thresh', default=0.85, type=click.FloatRange(0,1),
help='Confidence minimum threshold')
@click.option('-p', '--pyramids', 'opt_pyramids', default=0, type=click.IntRange(0,4),
help='Number pyramids to upscale for DLIB detectors')
@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None),
help='Slice list of files')
@click.option('--display/--no-display', 'opt_display', is_flag=True, default=False,
help='Display detections to debug')
@click.option('-f', '--force', 'opt_force', is_flag=True,
help='Force overwrite file')
@click.option('--color', 'opt_color_filter',
type=click.Choice(color_filters.keys()), default='all',
help='Filter to keep color or grayscale images (color = keep color')
@click.option('--largest', 'opt_largest', is_flag=True,
help='Only keep largest face')
@click.pass_context
def cli(ctx, opt_fp_in, opt_dir_media, opt_fp_out, opt_size, opt_detector_type,
opt_gpu, opt_conf_thresh, opt_pyramids, opt_slice, opt_display, opt_force, opt_color_filter,
opt_largest):
"""Converts frames with faces to CSV of ROIs"""
import sys
import os
from os.path import join
from pathlib import Path
from glob import glob
from tqdm import tqdm
import numpy as np
import dlib # must keep a local reference for dlib
import cv2 as cv
import pandas as pd
from app.utils import logger_utils, file_utils, im_utils
from app.processors import face_detector
# -------------------------------------------------
# init here
log = logger_utils.Logger.getLogger()
if not opt_force and Path(opt_fp_out).exists():
log.error('File exists. Use "-f / --force" to overwite')
return
if opt_detector_type == types.FaceDetectNet.CVDNN:
detector = face_detector.DetectorCVDNN()
elif opt_detector_type == types.FaceDetectNet.DLIB_CNN:
detector = face_detector.DetectorDLIBCNN(opt_gpu)
elif opt_detector_type == types.FaceDetectNet.DLIB_HOG:
detector = face_detector.DetectorDLIBHOG()
elif opt_detector_type == types.FaceDetectNet.MTCNN:
detector = face_detector.DetectorMTCNN()
elif opt_detector_type == types.FaceDetectNet.HAAR:
log.error('{} not yet implemented'.format(opt_detector_type.name))
return
# -------------------------------------------------
# process here
color_filter = color_filters[opt_color_filter]
# get list of files to process
df_files = pd.read_csv(opt_fp_in).set_index('index')
if opt_slice:
df_files = df_files[opt_slice[0]:opt_slice[1]]
log.debug('processing {:,} files'.format(len(df_files)))
data = []
for df_file in tqdm(df_files.itertuples(), total=len(df_files)):
fp_im = join(opt_dir_media, df_file.subdir, '{}.{}'.format(df_file.fn, df_file.ext))
im = cv.imread(fp_im)
# filter out color or grayscale iamges
if color_filter != color_filters['all']:
try:
is_gray = im_utils.is_grayscale(im)
if is_gray and color_filter != color_filters['gray']:
log.debug('Skipping grayscale image: {}'.format(fp_im))
continue
except Exception as e:
log.error('Could not check grayscale: {}'.format(fp_im))
continue
try:
bboxes = detector.detect(im, opt_size=opt_size, opt_pyramids=opt_pyramids, opt_largest=opt_largest)
except Exception as e:
log.error('could not detect: {}'.format(fp_im))
log.error('{}'.format(e))
continue
for bbox in bboxes:
roi = {
'image_index': int(df_file.Index),
'x': bbox.x,
'y': bbox.y,
'w': bbox.w,
'h': bbox.h,
'image_width': im.shape[1],
'image_height': im.shape[0]}
data.append(roi)
# debug display
if opt_display and len(bboxes):
bbox_dim = bbox.to_dim(im.shape[:2][::-1]) # w,h
im_md = im_utils.resize(im, width=min(1200, opt_size[0]))
for bbox in bboxes:
bbox_dim = bbox.to_dim(im_md.shape[:2][::-1])
cv.rectangle(im_md, bbox_dim.pt_tl, bbox_dim.pt_br, (0,255,0), 3)
cv.imshow('', im_md)
while True:
k = cv.waitKey(1) & 0xFF
if k == 27 or k == ord('q'): # ESC
cv.destroyAllWindows()
sys.exit()
elif k != 255:
# any key to continue
break
# save date
file_utils.mkdirs(opt_fp_out)
df = pd.DataFrame.from_dict(data)
df.index.name = 'index'
df.to_csv(opt_fp_out)
|
