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
|
from pathlib import Path
import text_recognizer.metadata.shared as shared
RAW_DATA_DIRNAME = shared.DATA_DIRNAME / "raw" / "emnist"
METADATA_FILENAME = RAW_DATA_DIRNAME / "metadata.toml"
DL_DATA_DIRNAME = shared.DATA_DIRNAME / "downloaded" / "emnist"
PROCESSED_DATA_DIRNAME = shared.DATA_DIRNAME / "processed" / "emnist"
PROCESSED_DATA_FILENAME = PROCESSED_DATA_DIRNAME / "byclass.h5"
ESSENTIALS_FILENAME = (
Path(__file__).parents[1].resolve() / "data" / "emnist_essentials.json"
)
SEED = 4711
NUM_SPECIAL_TOKENS = 4
SAMPLE_TO_BALANCE = True
INPUT_SHAPE = (28, 28)
DIMS = (1, *INPUT_SHAPE) # Extra dimension added by ToTensor()
OUTPUT_DIMS = (1,)
MAPPING = [
"<B>",
"<S>",
"<E>",
"<P>",
"0",
"1",
"2",
"3",
"4",
"5",
"6",
"7",
"8",
"9",
"A",
"B",
"C",
"D",
"E",
"F",
"G",
"H",
"I",
"J",
"K",
"L",
"M",
"N",
"O",
"P",
"Q",
"R",
"S",
"T",
"U",
"V",
"W",
"X",
"Y",
"Z",
"a",
"b",
"c",
"d",
"e",
"f",
"g",
"h",
"i",
"j",
"k",
"l",
"m",
"n",
"o",
"p",
"q",
"r",
"s",
"t",
"u",
"v",
"w",
"x",
"y",
"z",
" ",
"!",
'"',
"#",
"&",
"'",
"(",
")",
"*",
"+",
",",
"-",
".",
"/",
":",
";",
"?",
]
|
