CompactCNN/DAGM_data_prep.py at master · msminhas93/CompactCNN · GitHub

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
#!/usr/bin/env python
# coding: utf-8


import os
import shutil
import csv
import cv2
import numpy as np
import argparse

parser = argparse.ArgumentParser()
parser.add_argument("datasetdir")
parser.add_argument("dagmfolder")
args = parser.parse_args()


datasetdir = args.datasetdir # replace this with the dataset directory
dagmfolder = args.dagmfolder # replace this with the dagm folder


if not os.path.isdir(datasetdir):
    os.mkdir(datasetdir)

if not os.path.isdir(dagmfolder):
    raise ValueError('Not a Valid Path')

os.chdir(datasetdir)
os.mkdir('./DAGM_classification')
os.mkdir('./DAGM_segmentation')


os.chdir(os.path.join(datasetdir,'DAGM_classification'))
for i in range(1,11):
    os.mkdir(f'./Class{i}')
    for subset in ['Train','Test']:
        os.mkdir(f'./Class{i}/{subset}')
        for category in ['Defect','NonDefect']:
            os.mkdir(f'./Class{i}/{subset}/{category}')


for i in range(1,11):
    print(f'Class {i}')
    for subset in ['Train','Test']:
        with open(os.path.join(dagmfolder,f'Class{i}/{subset}/Label/Labels.txt'), newline='\n') as csvfile:
            filereader = csv.reader(csvfile, delimiter='\t', quotechar='|')
            next(filereader,None)
            for row in filereader:
                if int(row[1])==1:
                    shutil.copy(os.path.join(dagmfolder,f'Class{i}/{subset}/{row[2]}'),f'./Class{i}/{subset}/Defect')
                else:
                    shutil.copy(os.path.join(dagmfolder,f'Class{i}/{subset}/{row[2]}'),f'./Class{i}/{subset}/NonDefect')


for i in range(1,11):
    for subset in ['Train','Test']:
        for category in ['Defect','NonDefect']:
            val = len(os.listdir(os.path.join(datasetdir,f'DAGM_classification/Class{i}/{subset}/{category}')))
            print(f'Class{i} {subset} {category}: {val}')


os.chdir(os.path.join(datasetdir,'DAGM_segmentation'))
for i in range(1,11):
    os.mkdir(f'./Class{i}/')
    for subset in ['Train','Test']:
        os.mkdir(f'./Class{i}/{subset}')
        for fol in ['Image','Mask']:
            os.mkdir(f'./Class{i}/{subset}/{fol}')


for i in range(1,11):
    print(f'Class {i}')
    for subset in ['Train','Test']:
        print(f'Copying {subset}')
        with open(os.path.join(dagmfolder,f'Class{i}/{subset}/Label/Labels.txt'), newline='\n') as csvfile:
            filereader = csv.reader(csvfile, delimiter='\t', quotechar='|')
            next(filereader,None)
            for row in filereader:
                shutil.copy(os.path.join(dagmfolder,f'Class{i}/{subset}/{row[2]}'),f'./Class{i}/{subset}/Image')
                if int(row[1])==1: #defect
                    shutil.copy(os.path.join(dagmfolder,f'Class{i}/{subset}/Label/{row[4]}'),f'./Class{i}/{subset}/Mask')
                else:
                    cv2.imwrite(f'./Class{i}/{subset}/Mask/{row[0]}_label.PNG',np.zeros((512,512),dtype=np.uint8))


for i in range(1,11):
    for subset in ['Train','Test']:
        for fol in ['Image','Mask']:
            val = len(os.listdir(os.path.join(datasetdir,f'DAGM_segmentation/Class{i}/{subset}/{fol}')))
            print(f'Class{i} {subset} {fol}: {val}')