Hugging Face's logo

Bekhouche
/
TPS-ResNet-BiLSTM-Attn-STR

Transformers
Safetensors
Model card Files
xet
Community
Bekhouche commited on
Commit
39f8461
·
verified ·
1 Parent(s): b2384cc

Upload Pipeline

Browse files
Files changed (2) hide show
  1. config.json +236 -254
  2. model.safetensors +2 -2
config.json CHANGED
@@ -1,254 +1,236 @@
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
- "max": {
28
- "config": {
29
- "args": {
30
- "dim": 2
31
- }
32
- },
33
- "type": "torch.max"
34
- },
35
- "permute": {
36
- "config": {
37
- "args": {
38
- "dims": [
39
- 0,
40
- 3,
41
- 1,
42
- 2
43
- ]
44
- }
45
- },
46
- "type": "torch.permute"
47
- },
48
- "prediction": {
49
- "config": {
50
- "args": {
51
- "hidden_size": 256,
52
- "input_size": 256,
53
- "num_classes": 38
54
- }
55
- },
56
- "type": "DeepTextRecognition.AttentionModel"
57
- },
58
- "processing": {
59
- "config": {
60
- "args": {
61
- "channels_size": 1,
62
- "image_size": [
63
- 32,
64
- 100
65
- ],
66
- "padding": "left"
67
- }
68
- },
69
- "type": "DeepTextRecognition.ImageProcessor"
70
- },
71
- "sequence_modeling": {
72
- "config": {
73
- "args": {
74
- "hidden_sizes": [
75
- 256,
76
- 256
77
- ],
78
- "input_size": 512,
79
- "output_size": 256
80
- }
81
- },
82
- "type": "DeepTextRecognition.BiLSTMModel"
83
- },
84
- "squeeze": {
85
- "config": {
86
- "args": {
87
- "dim": 3
88
- }
89
- },
90
- "type": "torch.squeeze"
91
- },
92
- "tokenizer": {
93
- "config": {
94
- "args": {
95
- "characters": [
96
- "0",
97
- "1",
98
- "2",
99
- "3",
100
- "4",
101
- "5",
102
- "6",
103
- "7",
104
- "8",
105
- "9",
106
- "a",
107
- "b",
108
- "c",
109
- "d",
110
- "e",
111
- "f",
112
- "g",
113
- "h",
114
- "i",
115
- "j",
116
- "k",
117
- "l",
118
- "m",
119
- "n",
120
- "o",
121
- "p",
122
- "q",
123
- "r",
124
- "s",
125
- "t",
126
- "u",
127
- "v",
128
- "w",
129
- "x",
130
- "y",
131
- "z"
132
- ],
133
- "max_length": 25
134
- }
135
- },
136
- "type": "DeepTextRecognition.AttentionTokenizer"
137
- },
138
- "transformation": {
139
- "config": {
140
- "args": {
141
- "F": 20,
142
- "I_channel_num": 1,
143
- "I_r_size": [
144
- 32,
145
- 100
146
- ],
147
- "I_size": [
148
- 32,
149
- 100
150
- ]
151
- }
152
- },
153
- "type": "DeepTextRecognition.TPSModel"
154
- }
155
- },
156
- "order": [
157
- "processing",
158
- "transformation",
159
- "feature_extraction",
160
- "permute",
161
- "avg_pool",
162
- "squeeze",
163
- "sequence_modeling",
164
- "prediction",
165
- "max",
166
- "tokenizer"
167
- ],
168
- "outputs": [
169
- "tokenizer:labels"
170
- ],
171
- "routing": {
172
- "avg_pool": {
173
- "inputs": [
174
- "permute:permuted_features"
175
- ],
176
- "outputs": [
177
- "avg_pool:pooled_features"
178
- ]
179
- },
180
- "feature_extraction": {
181
- "inputs": [
182
- "transformation:transformed_images"
183
- ],
184
- "outputs": [
185
- "feature_extraction:extracted_features"
186
- ]
187
- },
188
- "max": {
189
- "inputs": [
190
- "prediction:predictions"
191
- ],
192
- "outputs": [
193
- "max:none",
194
- "max:predictions"
195
- ]
196
- },
197
- "permute": {
198
- "inputs": [
199
- "feature_extraction:extracted_features"
200
- ],
201
- "outputs": [
202
- "permute:permuted_features"
203
- ]
204
- },
205
- "prediction": {
206
- "inputs": [
207
- "sequence_modeling:modeled_features"
208
- ],
209
- "outputs": [
210
- "prediction:predictions"
211
- ]
212
- },
213
- "processing": {
214
- "inputs": [
215
- "images"
216
- ],
217
- "outputs": [
218
- "processing:processed_images"
219
- ]
220
- },
221
- "sequence_modeling": {
222
- "inputs": [
223
- "squeeze:squeezed_features"
224
- ],
225
- "outputs": [
226
- "sequence_modeling:modeled_features"
227
- ]
228
- },
229
- "squeeze": {
230
- "inputs": [
231
- "avg_pool:pooled_features"
232
- ],
233
- "outputs": [
234
- "squeeze:squeezed_features"
235
- ]
236
- },
237
- "tokenizer": {
238
- "inputs": [
239
- "max:predictions"
240
- ],
241
- "outputs": [
242
- "tokenizer:labels"
243
- ]
244
- },
245
- "transformation": {
246
- "inputs": [
247
- "processing:processed_images"
248
- ],
249
- "outputs": [
250
- "transformation:transformed_images"
251
- ]
252
- }
253
- }
254
- }
 
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
+ "hidden_size": 256,
44
+ "input_size": 256,
45
+ "num_classes": 38
46
+ }
47
+ },
48
+ "type": "DeepTextRecognition.TextRecognitionAttentionModel"
49
+ },
50
+ "processing": {
51
+ "config": {
52
+ "args": {
53
+ "channels_size": 1,
54
+ "image_size": [
55
+ 32,
56
+ 100
57
+ ],
58
+ "padding": "left"
59
+ }
60
+ },
61
+ "type": "DeepTextRecognition.ImageProcessor"
62
+ },
63
+ "sequence_modeling": {
64
+ "config": {
65
+ "args": {
66
+ "hidden_sizes": [
67
+ 256,
68
+ 256
69
+ ],
70
+ "input_size": 512,
71
+ "output_size": 256
72
+ }
73
+ },
74
+ "type": "DeepTextRecognition.BiLSTMModel"
75
+ },
76
+ "squeeze": {
77
+ "config": {
78
+ "args": {
79
+ "dim": 3
80
+ }
81
+ },
82
+ "type": "DeepTextRecognition.SqueezeModule"
83
+ },
84
+ "tokenizer": {
85
+ "config": {
86
+ "args": {
87
+ "characters": [
88
+ "0",
89
+ "1",
90
+ "2",
91
+ "3",
92
+ "4",
93
+ "5",
94
+ "6",
95
+ "7",
96
+ "8",
97
+ "9",
98
+ "a",
99
+ "b",
100
+ "c",
101
+ "d",
102
+ "e",
103
+ "f",
104
+ "g",
105
+ "h",
106
+ "i",
107
+ "j",
108
+ "k",
109
+ "l",
110
+ "m",
111
+ "n",
112
+ "o",
113
+ "p",
114
+ "q",
115
+ "r",
116
+ "s",
117
+ "t",
118
+ "u",
119
+ "v",
120
+ "w",
121
+ "x",
122
+ "y",
123
+ "z"
124
+ ],
125
+ "max_length": 25
126
+ }
127
+ },
128
+ "type": "DeepTextRecognition.AttentionTokenizer"
129
+ },
130
+ "transformation": {
131
+ "config": {
132
+ "args": {
133
+ "F": 20,
134
+ "I_channel_num": 1,
135
+ "I_r_size": [
136
+ 32,
137
+ 100
138
+ ],
139
+ "I_size": [
140
+ 32,
141
+ 100
142
+ ]
143
+ }
144
+ },
145
+ "type": "DeepTextRecognition.TPSModel"
146
+ }
147
+ },
148
+ "order": [
149
+ "processing",
150
+ "transformation",
151
+ "feature_extraction",
152
+ "permute",
153
+ "avg_pool",
154
+ "squeeze",
155
+ "sequence_modeling",
156
+ "prediction",
157
+ "tokenizer"
158
+ ],
159
+ "outputs": [
160
+ "tokenizer:labels"
161
+ ],
162
+ "routing": {
163
+ "avg_pool": {
164
+ "inputs": [
165
+ "permute:permuted_features"
166
+ ],
167
+ "outputs": [
168
+ "avg_pool:pooled_features"
169
+ ]
170
+ },
171
+ "feature_extraction": {
172
+ "inputs": [
173
+ "transformation:transformed_images"
174
+ ],
175
+ "outputs": [
176
+ "feature_extraction:extracted_features"
177
+ ]
178
+ },
179
+ "permute": {
180
+ "inputs": [
181
+ "feature_extraction:extracted_features"
182
+ ],
183
+ "outputs": [
184
+ "permute:permuted_features"
185
+ ]
186
+ },
187
+ "prediction": {
188
+ "inputs": [
189
+ "sequence_modeling:modeled_features"
190
+ ],
191
+ "outputs": [
192
+ "prediction:predictions"
193
+ ]
194
+ },
195
+ "processing": {
196
+ "inputs": [
197
+ "images"
198
+ ],
199
+ "outputs": [
200
+ "processing:processed_images"
201
+ ]
202
+ },
203
+ "sequence_modeling": {
204
+ "inputs": [
205
+ "squeeze:squeezed_features"
206
+ ],
207
+ "outputs": [
208
+ "sequence_modeling:modeled_features"
209
+ ]
210
+ },
211
+ "squeeze": {
212
+ "inputs": [
213
+ "avg_pool:pooled_features"
214
+ ],
215
+ "outputs": [
216
+ "squeeze:squeezed_features"
217
+ ]
218
+ },
219
+ "tokenizer": {
220
+ "inputs": [
221
+ "prediction:predictions"
222
+ ],
223
+ "outputs": [
224
+ "tokenizer:labels"
225
+ ]
226
+ },
227
+ "transformation": {
228
+ "inputs": [
229
+ "processing:processed_images"
230
+ ],
231
+ "outputs": [
232
+ "transformation:transformed_images"
233
+ ]
234
+ }
235
+ }
236
+ }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7e8c504090d5988d78aa47de37297c860cf183f98190f22ae2c64451f527ede
3
- size 198655756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9d06a0bcfdd11cdeb8ca6dcf671c71487f7a416c32d9d57fbc6c347af097d87
3
+ size 198657772