File size: 3,710 Bytes
13d1b75
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
{
  "inputs": [
    "images"
  ],
  "modules": {
    "attention_module": {
      "config": {
        "args": {
          "depth": 8,
          "maxT": 25,
          "num_channels": 64,
          "scales": [
            [
              32,
              16,
              64
            ],
            [
              128,
              8,
              32
            ],
            [
              512,
              8,
              32
            ]
          ]
        }
      },
      "type": "DeepTextRecognition.CAMModel"
    },
    "feature_extraction": {
      "config": {
        "args": {
          "compress_layer": false,
          "return_multiscale": true,
          "strides": [
            [
              1,
              1
            ],
            [
              2,
              2
            ],
            [
              1,
              1
            ],
            [
              2,
              2
            ],
            [
              1,
              1
            ],
            [
              1,
              1
            ]
          ]
        }
      },
      "type": "DeepTextRecognition.ResNet45Model"
    },
    "processing": {
      "config": {
        "args": {
          "channels_size": 1,
          "image_size": [
            32,
            128
          ],
          "normalize": [
            0.5,
            0.5
          ],
          "padding": "none",
          "resize_method": "bilinear"
        }
      },
      "type": "DeepTextRecognition.ImageProcessor"
    },
    "text_decoder": {
      "config": {
        "args": {
          "dropout": 0.3,
          "nchannel": 512,
          "nclass": 38
        }
      },
      "type": "DeepTextRecognition.DTDModel"
    },
    "tokenizer": {
      "config": {
        "args": {
          "case_sensitive": false,
          "characters": [
            "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",
            "1",
            "2",
            "3",
            "4",
            "5",
            "6",
            "7",
            "8",
            "9",
            "0"
          ]
        }
      },
      "type": "DeepTextRecognition.DANTokenizer"
    }
  },
  "order": [
    "processing",
    "feature_extraction",
    "attention_module",
    "text_decoder",
    "tokenizer"
  ],
  "outputs": [
    "tokenizer:labels",
    "tokenizer:probabilities"
  ],
  "routing": {
    "attention_module": {
      "inputs": [
        "feature_extraction:extracted_features"
      ],
      "outputs": [
        "attention_module:attention_features"
      ]
    },
    "feature_extraction": {
      "inputs": [
        "processing:processed_images"
      ],
      "outputs": [
        "feature_extraction:extracted_features"
      ]
    },
    "processing": {
      "inputs": [
        "images"
      ],
      "outputs": [
        "processing:processed_images"
      ]
    },
    "text_decoder": {
      "inputs": [
        "feature_extraction:extracted_features",
        "attention_module:attention_features"
      ],
      "outputs": [
        "text_decoder:predictions",
        "text_decoder:lengths"
      ]
    },
    "tokenizer": {
      "inputs": [
        "text_decoder:predictions",
        "text_decoder:lengths"
      ],
      "outputs": [
        "tokenizer:labels",
        "tokenizer:probabilities"
      ]
    }
  }
}