-
Notifications
You must be signed in to change notification settings - Fork 0
/
app.py
166 lines (146 loc) · 4.88 KB
/
app.py
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
157
158
159
160
161
162
163
164
165
166
import dash
import base64
import numpy as np
import pandas as pd
import dash_core_components as dcc
import dash_html_components as html
import dash_bootstrap_components as dbc
from dash.dependencies import Input, Output, State
from model_utils import Embedding
from utils import similarity_matrix, sort_matrix
from utils import read_files, new_df, save_df
external_stylesheets = [
'https://codepen.io/chriddyp/pen/bWLwgP.css', dbc.themes.DARKLY]
SESSION_ID = 0
app = dash.Dash(__name__, external_stylesheets=external_stylesheets)
app.title = "DIF"
card1 = dbc.Card(
[
dbc.CardImg(id='img1', top=True),
dbc.CardBody([
dbc.Row(html.P(id='filename-1'),
justify="center"),
dbc.Button('DELETE',
color="danger",
size='lg',
id="button1",
n_clicks=0,)
]),
],
style={"width": "auto"},
)
card2 = dbc.Card(
[
dbc.CardImg(id='img2', top=True),
dbc.CardBody([
dbc.Row(html.P(id='filename-2'),
justify="center"),
dbc.Button('DELETE',
color="danger",
size='lg',
id="button2",
n_clicks=0,)
]),
],
style={"width": "auto"},
)
app.layout = html.Div(children=[
html.Div(children="Duplicate Image Finder ",
id="headline"),
html.Br(),
dbc.Row([dbc.Input(
id="input_path",
type="text",
bs_size="lg",
placeholder="Paste dataset folder path ",
debounce=True,)
],
justify="center",
id='input_path_div'),
html.Br(),
html.Br(),
dcc.Loading(
id="loader",
children=[html.Div(id="loading-div")],
type="dot",
),
html.Br(),
dbc.Row(
[dbc.Col(card1, id='col-card-1', width=4),
dbc.Col(card2, id='col-card-2', width=4)
],
justify="center",
id='display_layout'
)
])
@ app.callback([Output('img1', 'src'),
Output('img2', 'src'),
Output('filename-1', 'children'),
Output('filename-2', 'children'), ],
[Input('loading-div', 'children'),
Input('button1', 'n_clicks'),
Input('button2', 'n_clicks')])
def display_image(children, nc1, nc2):
global SESSION_ID
changed_id = [p['prop_id'] for p in dash.callback_context.triggered][0]
print("changed_id", changed_id)
print("clicks", children)
print(f"cccc {nc1,nc2}")
if children != []:
# Reading files
index_pair = np.load('index_pair.npy')
files_path = pd.read_csv('./files.csv')
# Checking which button is clicked and update Session id
update_session(index_pair, files_path, changed_id)
# Reading images and filename
image1, image2, filename1, filename2 = encoded_images(
index_pair, files_path)
# Saving updated files datafrmae
save_df(files_path)
return image1, image2, filename1, filename2
return "", "", "", ""
def update_session(index_pair, files_df, changed_id):
global SESSION_ID
idx1, idx2 = index_pair[SESSION_ID]
if 'button1' in changed_id:
files_df.is_deleted.iloc[idx1] = 1
SESSION_ID += 1
elif 'button2' in changed_id:
files_df.is_deleted.iloc[idx2] = 1
SESSION_ID += 1
def encoded_images(index_pair, files_df):
global SESSION_ID
idx1, idx2 = index_pair[SESSION_ID]
if files_df.is_deleted.iloc[idx1] == 0 and files_df.is_deleted.iloc[idx2] == 0:
file1, file2 = files_df.files.iloc[idx1], files_df.files.iloc[idx2]
# Reading Images and encoding them as base64
enc_img1 = base64.b64encode(open(file1, 'rb').read())
enc_img2 = base64.b64encode(open(file2, 'rb').read())
enc_images = [
f"data:image/png;base64,{enc_img1.decode()}",
f"data:image/png;base64,{enc_img2.decode()}"]
# Sending file names
filenames = [file1.split('/')[-1], file2.split('/')[-1]]
return enc_images+filenames
else:
SESSION_ID += 1
return encoded_images(index_pair, files_df)
return ['', '', '', '']
@ app.callback(Output('loading-div', 'children'),
[Input('input_path', 'value')],
[State('loading-div', 'children')])
def get_path(path, children):
files = read_files(path)
if path:
children.append(html.P(f"files found : {len(files)}"))
embedding = Embedding()
embs = np.array(embedding.embeddings(files))
matrix = similarity_matrix(embs, embs)
index_pair = sort_matrix(matrix)
np.save('index_pair.npy', index_pair)
df = new_df(files)
save_df(df, './files.csv')
return children
return []
if __name__ == '__main__':
app.run_server(debug=True, host="0.0.0.0")