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
|
import os
import glob
import time
import pandas as pd
from sqlalchemy import create_engine, Table, Column, String, Integer, DateTime, Float
from sqlalchemy.orm import sessionmaker
from sqlalchemy.ext.declarative import declarative_base
from app.utils.file_utils import load_recipe, load_csv_safe
from app.settings import app_cfg as cfg
connection_url = "mysql+mysqldb://{}:{}@{}/{}".format(
os.getenv("DB_USER"),
os.getenv("DB_PASS"),
os.getenv("DB_HOST"),
os.getenv("DB_NAME")
)
datasets = {}
loaded = False
def list_datasets():
return [dataset.describe() for dataset in datasets.values()]
def get_dataset(name):
return datasets[name] if name in datasets else None
def get_table(name, table_name):
dataset = get_dataset(name)
return dataset.get_table(table_name) if dataset else None
def load_sql_datasets(replace=False, base_model=None):
global datasets, loaded
if loaded:
return datasets
engine = create_engine(connection_url) if replace else None
for path in glob.iglob(os.path.join(cfg.DIR_FAISS_METADATA, "*")):
dataset = load_sql_dataset(path, replace, engine, base_model)
datasets[dataset.name] = dataset
loaded = True
return datasets
def load_sql_dataset(path, replace=False, engine=None, base_model=None):
name = os.path.basename(path)
dataset = SqlDataset(name, base_model=base_model)
for fn in glob.iglob(os.path.join(path, "*.csv")):
key = os.path.basename(fn).replace(".csv", "")
table = dataset.get_table(key)
if table is None:
continue
if replace:
print('loading dataset {}'.format(fn))
df = pd.read_csv(fn)
# fix columns that are named "index", a sql reserved word
df.columns = table.__table__.columns.keys()
df.to_sql(name=table.__tablename__, con=engine, if_exists='replace', index=False)
return dataset
class SqlDataset:
"""
Bridge between the facial information CSVs connected to the datasets, and MySQL
- each dataset should have files that can be loaded into these database models
- names will be fixed to work in SQL (index -> id)
- we can then have more generic models for fetching this info after doing a FAISS query
"""
def __init__(self, name, engine=None, base_model=None):
self.name = name
self.tables = {}
if base_model is None:
self.engine = create_engine(connection_url)
base_model = declarative_base(engine)
self.base_model = base_model
def describe(self):
return {
'name': self.name,
'tables': list(self.tables.keys()),
}
def get_table(self, type):
if type in self.tables:
return self.tables[type]
elif type == 'uuids':
self.tables[type] = self.uuid_table()
elif type == 'roi':
self.tables[type] = self.roi_table()
elif type == 'identity_meta':
self.tables[type] = self.identity_table()
elif type == 'pose':
self.tables[type] = self.pose_table()
else:
return None
return self.tables[type]
# ==> uuids.csv <==
# index,uuid
# 0,f03fd921-2d56-4e83-8115-f658d6a72287
def uuid_table(self):
class UUID(self.base_model):
__tablename__ = self.name + "_uuid"
id = Column(Integer, primary_key=True)
uuid = Column(String(36), nullable=False)
return UUID
# ==> roi.csv <==
# index,h,image_height,image_index,image_width,w,x,y
# 0,0.33000000000000007,250,0,250,0.32999999999999996,0.33666666666666667,0.35
def roi_table(self):
class ROI(self.base_model):
__tablename__ = self.name + "_roi"
id = Column(Integer, primary_key=True)
h = Column(Float, nullable=False)
image_height = Column(Integer, nullable=False)
image_index = Column(Integer, nullable=False)
image_width = Column(Integer, nullable=False)
w = Column(Float, nullable=False)
x = Column(Float, nullable=False)
y = Column(Float, nullable=False)
return ROI
# ==> identity.csv <==
# index,fullname,description,gender,images,image_index
# 0,A. J. Cook,Canadian actress,f,1,0
def identity_table(self):
class Identity(self.base_model):
__tablename__ = self.name + "_identity"
id = Column(Integer, primary_key=True)
fullname = Column(String(36), nullable=False)
description = Column(String(36), nullable=False)
gender = Column(String(1), nullable=False)
images = Column(Integer, nullable=False)
image_id = Column(Integer, nullable=False)
return Identity
# ==> pose.csv <==
# index,image_index,pitch,roll,yaw
# 0,0,11.16264458441435,10.415885631337728,22.99719032415318
def pose_table(self):
class Pose(self.base_model):
__tablename__ = self.name + "_pose"
id = Column(Integer, primary_key=True)
image_id = Column(Integer, primary_key=True)
pitch = Column(Float, nullable=False)
roll = Column(Float, nullable=False)
yaw = Column(Float, nullable=False)
return Pose
# Session = sessionmaker(bind=engine)
# session = Session()
|
