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
|
"""
Converts ROIs to face vector
"""
import click
from app.settings import types
from app.utils import click_utils
from app.settings import app_cfg as cfg
@click.command()
@click.option('-o', '--output', 'opt_fp_out', default=None,
help='Override enum output filename CSV')
@click.option('-m', '--media', 'opt_dir_media', default=None,
help='Override enum media directory')
@click.option('--data_store', 'opt_data_store',
type=cfg.DataStoreVar,
default=click_utils.get_default(types.DataStore.SSD),
show_default=True,
help=click_utils.show_help(types.Dataset))
@click.option('--dataset', 'opt_dataset',
type=cfg.DatasetVar,
required=True,
show_default=True,
help=click_utils.show_help(types.Dataset))
@click.option('--size', 'opt_size',
type=(int, int), default=(300, 300),
help='Output image size')
@click.option('-j', '--jitters', 'opt_jitters', default=cfg.DLIB_FACEREC_JITTERS,
help='Number of jitters')
@click.option('-p', '--padding', 'opt_padding', default=cfg.DLIB_FACEREC_PADDING,
help='Percentage padding')
@click.option('--slice', 'opt_slice', type=(int, int), default=(None, None),
help='Slice list of files')
@click.option('-f', '--force', 'opt_force', is_flag=True,
help='Force overwrite file')
@click.option('-g', '--gpu', 'opt_gpu', default=0,
help='GPU index')
@click.pass_context
def cli(ctx, opt_fp_out, opt_dir_media, opt_data_store, opt_dataset, opt_size,
opt_slice, opt_force, opt_gpu, opt_jitters, opt_padding):
"""Converts face ROIs to vectors"""
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.models.bbox import BBox
from app.models.data_store import DataStore
from app.utils import logger_utils, file_utils, im_utils
from app.processors import face_recognition
# -------------------------------------------------
# init here
log = logger_utils.Logger.getLogger()
# set data_store
data_store = DataStore(opt_data_store, opt_dataset)
# get filepath out
fp_out = data_store.metadata(types.Metadata.FACE_VECTOR) if opt_fp_out is None else opt_fp_out
if not opt_force and Path(fp_out).exists():
log.error('File exists. Use "-f / --force" to overwite')
return
# init face processors
facerec = face_recognition.RecognitionDLIB()
# load data
fp_record = data_store.metadata(types.Metadata.FILE_RECORD)
df_record = pd.read_csv(fp_record).set_index('index')
fp_roi = data_store.metadata(types.Metadata.FACE_ROI)
df_roi = pd.read_csv(fp_roi).set_index('index')
if opt_slice:
df_roi = df_roi[opt_slice[0]:opt_slice[1]]
# -------------------------------------------------
# process here
df_img_groups = df_roi.groupby('record_index')
log.debug('processing {:,} groups'.format(len(df_img_groups)))
vecs = []
for image_index, df_img_group in tqdm(df_img_groups):
# make fp
roi_index = df_img_group.index.values[0]
# log.debug(f'roi_index: {roi_index}, image_index: {image_index}')
ds_file = df_record.loc[roi_index] # locate image meta
#ds_file = df_record.loc['index', image_index] # locate image meta
fp_im = data_store.face_image(str(ds_file.subdir), str(ds_file.fn), str(ds_file.ext))
im = cv.imread(fp_im)
# get bbox
x = df_img_group.x.values[0]
y = df_img_group.y.values[0]
w = df_img_group.w.values[0]
h = df_img_group.h.values[0]
imw = df_img_group.image_width.values[0]
imh = df_img_group.image_height.values[0]
dim = im.shape[:2][::-1]
# get face vector
dim = (imw, imh)
bbox_dim = BBox.from_xywh(x, y, w, h).to_dim(dim) # convert to int real dimensions
# compute vec
# padding=opt_padding not yet implemented in 19.16 but merged in master
vec = facerec.vec(im, bbox_dim, jitters=opt_jitters)
vec_str = ','.join([repr(x) for x in vec]) # convert to string for CSV
vecs.append( {'roi_index': roi_index, 'image_index': image_index, 'vec': vec_str})
# save date
df = pd.DataFrame.from_dict(vecs)
df.index.name = 'index'
file_utils.mkdirs(fp_out)
df.to_csv(fp_out)
|
