Hugging Face's logo

Bekhouche
/
TPS-ResNet-BiLSTM-CTC-STR

Transformers
Safetensors
Model card Files
xet
Community
Bekhouche commited on
Commit
4211c12
·
verified ·
1 Parent(s): 868d244

Upload Pipeline

Browse files
Files changed (2) hide show
  1. config.json +235 -235
  2. model.safetensors +2 -2
config.json CHANGED
@@ -1,235 +1,235 @@
1
- {
2
- "inputs": [
3
- "images"
4
- ],
5
- "modules": {
6
- "avg_pool": {
7
- "config": {
8
- "args": {
9
- "output_size": [
10
- null,
11
- 1
12
- ]
13
- }
14
- },
15
- "type": "torch.nn.AdaptiveAvgPool2d"
16
- },
17
- "feature_extraction": {
18
- "config": {
19
- "args": {
20
- "input_channel": 1,
21
- "output_channel": 512,
22
- "variant": "DTRB"
23
- }
24
- },
25
- "type": "DeepTextRecognition.ResNetModel"
26
- },
27
- "permute": {
28
- "config": {
29
- "args": {
30
- "dims": [
31
- 0,
32
- 3,
33
- 1,
34
- 2
35
- ]
36
- }
37
- },
38
- "type": "torch.permute"
39
- },
40
- "prediction": {
41
- "config": {
42
- "args": {
43
- "in_features": 256,
44
- "out_features": 37
45
- }
46
- },
47
- "type": "torch.nn.Linear"
48
- },
49
- "processing": {
50
- "config": {
51
- "args": {
52
- "channels_size": 1,
53
- "image_size": [
54
- 32,
55
- 100
56
- ],
57
- "padding": "left"
58
- }
59
- },
60
- "type": "DeepTextRecognition.ImageProcessor"
61
- },
62
- "sequence_modeling": {
63
- "config": {
64
- "args": {
65
- "hidden_sizes": [
66
- 256,
67
- 256
68
- ],
69
- "input_size": 512,
70
- "output_size": 256
71
- }
72
- },
73
- "type": "DeepTextRecognition.BiLSTMModel"
74
- },
75
- "squeeze": {
76
- "config": {
77
- "args": {
78
- "dim": 3
79
- }
80
- },
81
- "type": "torch.squeeze"
82
- },
83
- "tokenizer": {
84
- "config": {
85
- "args": {
86
- "characters": [
87
- "0",
88
- "1",
89
- "2",
90
- "3",
91
- "4",
92
- "5",
93
- "6",
94
- "7",
95
- "8",
96
- "9",
97
- "a",
98
- "b",
99
- "c",
100
- "d",
101
- "e",
102
- "f",
103
- "g",
104
- "h",
105
- "i",
106
- "j",
107
- "k",
108
- "l",
109
- "m",
110
- "n",
111
- "o",
112
- "p",
113
- "q",
114
- "r",
115
- "s",
116
- "t",
117
- "u",
118
- "v",
119
- "w",
120
- "x",
121
- "y",
122
- "z"
123
- ],
124
- "max_length": 25
125
- }
126
- },
127
- "type": "DeepTextRecognition.CTCTokenizer"
128
- },
129
- "transformation": {
130
- "config": {
131
- "args": {
132
- "F": 20,
133
- "I_channel_num": 1,
134
- "I_r_size": [
135
- 32,
136
- 100
137
- ],
138
- "I_size": [
139
- 32,
140
- 100
141
- ]
142
- }
143
- },
144
- "type": "DeepTextRecognition.TPSModel"
145
- }
146
- },
147
- "order": [
148
- "processing",
149
- "transformation",
150
- "feature_extraction",
151
- "permute",
152
- "avg_pool",
153
- "squeeze",
154
- "sequence_modeling",
155
- "prediction",
156
- "tokenizer"
157
- ],
158
- "outputs": [
159
- "tokenizer:labels"
160
- ],
161
- "routing": {
162
- "avg_pool": {
163
- "inputs": [
164
- "permute:permuted_features"
165
- ],
166
- "outputs": [
167
- "avg_pool:pooled_features"
168
- ]
169
- },
170
- "feature_extraction": {
171
- "inputs": [
172
- "transformation:transformed_images"
173
- ],
174
- "outputs": [
175
- "feature_extraction:extracted_features"
176
- ]
177
- },
178
- "permute": {
179
- "inputs": [
180
- "feature_extraction:extracted_features"
181
- ],
182
- "outputs": [
183
- "permute:permuted_features"
184
- ]
185
- },
186
- "prediction": {
187
- "inputs": [
188
- "sequence_modeling:modeled_features"
189
- ],
190
- "outputs": [
191
- "prediction:predictions"
192
- ]
193
- },
194
- "processing": {
195
- "inputs": [
196
- "images"
197
- ],
198
- "outputs": [
199
- "processing:processed_images"
200
- ]
201
- },
202
- "sequence_modeling": {
203
- "inputs": [
204
- "squeeze:squeezed_features"
205
- ],
206
- "outputs": [
207
- "sequence_modeling:modeled_features"
208
- ]
209
- },
210
- "squeeze": {
211
- "inputs": [
212
- "avg_pool:pooled_features"
213
- ],
214
- "outputs": [
215
- "squeeze:squeezed_features"
216
- ]
217
- },
218
- "tokenizer": {
219
- "inputs": [
220
- "prediction:predictions"
221
- ],
222
- "outputs": [
223
- "tokenizer:labels"
224
- ]
225
- },
226
- "transformation": {
227
- "inputs": [
228
- "processing:processed_images"
229
- ],
230
- "outputs": [
231
- "transformation:transformed_images"
232
- ]
233
- }
234
- }
235
- }
 
1
+ {
2
+ "inputs": [
3
+ "images"
4
+ ],
5
+ "modules": {
6
+ "avg_pool": {
7
+ "config": {
8
+ "args": {
9
+ "output_size": [
10
+ null,
11
+ 1
12
+ ]
13
+ }
14
+ },
15
+ "type": "DeepTextRecognition.AdaptiveAvgPoolModule"
16
+ },
17
+ "feature_extraction": {
18
+ "config": {
19
+ "args": {
20
+ "input_channel": 1,
21
+ "output_channel": 512,
22
+ "variant": "DTRB"
23
+ }
24
+ },
25
+ "type": "DeepTextRecognition.ResNetModel"
26
+ },
27
+ "permute": {
28
+ "config": {
29
+ "args": {
30
+ "dims": [
31
+ 0,
32
+ 3,
33
+ 1,
34
+ 2
35
+ ]
36
+ }
37
+ },
38
+ "type": "DeepTextRecognition.PermuteModule"
39
+ },
40
+ "prediction": {
41
+ "config": {
42
+ "args": {
43
+ "in_features": 256,
44
+ "out_features": 37
45
+ }
46
+ },
47
+ "type": "torch.nn.Linear"
48
+ },
49
+ "processing": {
50
+ "config": {
51
+ "args": {
52
+ "channels_size": 1,
53
+ "image_size": [
54
+ 32,
55
+ 100
56
+ ],
57
+ "padding": "left"
58
+ }
59
+ },
60
+ "type": "DeepTextRecognition.ImageProcessor"
61
+ },
62
+ "sequence_modeling": {
63
+ "config": {
64
+ "args": {
65
+ "hidden_sizes": [
66
+ 256,
67
+ 256
68
+ ],
69
+ "input_size": 512,
70
+ "output_size": 256
71
+ }
72
+ },
73
+ "type": "DeepTextRecognition.BiLSTMModel"
74
+ },
75
+ "squeeze": {
76
+ "config": {
77
+ "args": {
78
+ "dim": 3
79
+ }
80
+ },
81
+ "type": "DeepTextRecognition.SqueezeModule"
82
+ },
83
+ "tokenizer": {
84
+ "config": {
85
+ "args": {
86
+ "characters": [
87
+ "0",
88
+ "1",
89
+ "2",
90
+ "3",
91
+ "4",
92
+ "5",
93
+ "6",
94
+ "7",
95
+ "8",
96
+ "9",
97
+ "a",
98
+ "b",
99
+ "c",
100
+ "d",
101
+ "e",
102
+ "f",
103
+ "g",
104
+ "h",
105
+ "i",
106
+ "j",
107
+ "k",
108
+ "l",
109
+ "m",
110
+ "n",
111
+ "o",
112
+ "p",
113
+ "q",
114
+ "r",
115
+ "s",
116
+ "t",
117
+ "u",
118
+ "v",
119
+ "w",
120
+ "x",
121
+ "y",
122
+ "z"
123
+ ],
124
+ "max_length": 25
125
+ }
126
+ },
127
+ "type": "DeepTextRecognition.CTCTokenizer"
128
+ },
129
+ "transformation": {
130
+ "config": {
131
+ "args": {
132
+ "F": 20,
133
+ "I_channel_num": 1,
134
+ "I_r_size": [
135
+ 32,
136
+ 100
137
+ ],
138
+ "I_size": [
139
+ 32,
140
+ 100
141
+ ]
142
+ }
143
+ },
144
+ "type": "DeepTextRecognition.TPSModel"
145
+ }
146
+ },
147
+ "order": [
148
+ "processing",
149
+ "transformation",
150
+ "feature_extraction",
151
+ "permute",
152
+ "avg_pool",
153
+ "squeeze",
154
+ "sequence_modeling",
155
+ "prediction",
156
+ "tokenizer"
157
+ ],
158
+ "outputs": [
159
+ "tokenizer:labels"
160
+ ],
161
+ "routing": {
162
+ "avg_pool": {
163
+ "inputs": [
164
+ "permute:permuted_features"
165
+ ],
166
+ "outputs": [
167
+ "avg_pool:pooled_features"
168
+ ]
169
+ },
170
+ "feature_extraction": {
171
+ "inputs": [
172
+ "transformation:transformed_images"
173
+ ],
174
+ "outputs": [
175
+ "feature_extraction:extracted_features"
176
+ ]
177
+ },
178
+ "permute": {
179
+ "inputs": [
180
+ "feature_extraction:extracted_features"
181
+ ],
182
+ "outputs": [
183
+ "permute:permuted_features"
184
+ ]
185
+ },
186
+ "prediction": {
187
+ "inputs": [
188
+ "sequence_modeling:modeled_features"
189
+ ],
190
+ "outputs": [
191
+ "prediction:predictions"
192
+ ]
193
+ },
194
+ "processing": {
195
+ "inputs": [
196
+ "images"
197
+ ],
198
+ "outputs": [
199
+ "processing:processed_images"
200
+ ]
201
+ },
202
+ "sequence_modeling": {
203
+ "inputs": [
204
+ "squeeze:squeezed_features"
205
+ ],
206
+ "outputs": [
207
+ "sequence_modeling:modeled_features"
208
+ ]
209
+ },
210
+ "squeeze": {
211
+ "inputs": [
212
+ "avg_pool:pooled_features"
213
+ ],
214
+ "outputs": [
215
+ "squeeze:squeezed_features"
216
+ ]
217
+ },
218
+ "tokenizer": {
219
+ "inputs": [
220
+ "prediction:predictions"
221
+ ],
222
+ "outputs": [
223
+ "tokenizer:labels"
224
+ ]
225
+ },
226
+ "transformation": {
227
+ "inputs": [
228
+ "processing:processed_images"
229
+ ],
230
+ "outputs": [
231
+ "transformation:transformed_images"
232
+ ]
233
+ }
234
+ }
235
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1190060ddab41d6e380e55b9b7f04a30ef5df9f7be51fb3176b4393d572c9bb
3
- size 195866432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f03a7e38a48e115d7de35b1dfddf330d0ee8476541175f6a11800094c290210b
3
+ size 195868384