Hugging Face's logo

Raghavan
/
fast_base_tt_800_finetune_ic17mlt

Transformers
PyTorch
Safetensors
Inference Endpoints
Model card Files Community
Raghavan commited on
Commit
b0a4e4e
•
1 Parent(s): 4427f1b

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +440 -0
  2. preprocessor_config.json +32 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,440 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "FASTForImageCaptioning"
4
+ ],
5
+ "backbone_act_func": "relu",
6
+ "backbone_bias": false,
7
+ "backbone_dilation": 1,
8
+ "backbone_dropout_rate": 0,
9
+ "backbone_groups": 1,
10
+ "backbone_has_shuffle": false,
11
+ "backbone_in_channels": 3,
12
+ "backbone_kernel_size": 3,
13
+ "backbone_ops_order": "weight_bn_act",
14
+ "backbone_out_channels": 64,
15
+ "backbone_stage1_dilation": [
16
+ 1,
17
+ 1,
18
+ 1,
19
+ 1,
20
+ 1,
21
+ 1,
22
+ 1,
23
+ 1,
24
+ 1,
25
+ 1
26
+ ],
27
+ "backbone_stage1_groups": [
28
+ 1,
29
+ 1,
30
+ 1,
31
+ 1,
32
+ 1,
33
+ 1,
34
+ 1,
35
+ 1,
36
+ 1,
37
+ 1
38
+ ],
39
+ "backbone_stage1_in_channels": [
40
+ 64,
41
+ 64,
42
+ 64,
43
+ 64,
44
+ 64,
45
+ 64,
46
+ 64,
47
+ 64,
48
+ 64,
49
+ 64
50
+ ],
51
+ "backbone_stage1_kernel_size": [
52
+ [
53
+ 3,
54
+ 3
55
+ ],
56
+ [
57
+ 3,
58
+ 3
59
+ ],
60
+ [
61
+ 3,
62
+ 1
63
+ ],
64
+ [
65
+ 3,
66
+ 3
67
+ ],
68
+ [
69
+ 3,
70
+ 1
71
+ ],
72
+ [
73
+ 3,
74
+ 3
75
+ ],
76
+ [
77
+ 3,
78
+ 3
79
+ ],
80
+ [
81
+ 1,
82
+ 3
83
+ ],
84
+ [
85
+ 3,
86
+ 3
87
+ ],
88
+ [
89
+ 3,
90
+ 3
91
+ ]
92
+ ],
93
+ "backbone_stage1_out_channels": [
94
+ 64,
95
+ 64,
96
+ 64,
97
+ 64,
98
+ 64,
99
+ 64,
100
+ 64,
101
+ 64,
102
+ 64,
103
+ 64
104
+ ],
105
+ "backbone_stage1_stride": [
106
+ 1,
107
+ 2,
108
+ 1,
109
+ 1,
110
+ 1,
111
+ 1,
112
+ 1,
113
+ 1,
114
+ 1,
115
+ 1
116
+ ],
117
+ "backbone_stage2_dilation": [
118
+ 1,
119
+ 1,
120
+ 1,
121
+ 1,
122
+ 1,
123
+ 1,
124
+ 1,
125
+ 1,
126
+ 1,
127
+ 1
128
+ ],
129
+ "backbone_stage2_groups": [
130
+ 1,
131
+ 1,
132
+ 1,
133
+ 1,
134
+ 1,
135
+ 1,
136
+ 1,
137
+ 1,
138
+ 1,
139
+ 1
140
+ ],
141
+ "backbone_stage2_in_channels": [
142
+ 64,
143
+ 128,
144
+ 128,
145
+ 128,
146
+ 128,
147
+ 128,
148
+ 128,
149
+ 128,
150
+ 128,
151
+ 128
152
+ ],
153
+ "backbone_stage2_kernel_size": [
154
+ [
155
+ 3,
156
+ 3
157
+ ],
158
+ [
159
+ 1,
160
+ 3
161
+ ],
162
+ [
163
+ 3,
164
+ 3
165
+ ],
166
+ [
167
+ 3,
168
+ 1
169
+ ],
170
+ [
171
+ 3,
172
+ 3
173
+ ],
174
+ [
175
+ 3,
176
+ 3
177
+ ],
178
+ [
179
+ 3,
180
+ 1
181
+ ],
182
+ [
183
+ 3,
184
+ 1
185
+ ],
186
+ [
187
+ 3,
188
+ 3
189
+ ],
190
+ [
191
+ 3,
192
+ 3
193
+ ]
194
+ ],
195
+ "backbone_stage2_out_channels": [
196
+ 128,
197
+ 128,
198
+ 128,
199
+ 128,
200
+ 128,
201
+ 128,
202
+ 128,
203
+ 128,
204
+ 128,
205
+ 128
206
+ ],
207
+ "backbone_stage2_stride": [
208
+ 2,
209
+ 1,
210
+ 1,
211
+ 1,
212
+ 1,
213
+ 1,
214
+ 1,
215
+ 1,
216
+ 1,
217
+ 1
218
+ ],
219
+ "backbone_stage3_dilation": [
220
+ 1,
221
+ 1,
222
+ 1,
223
+ 1,
224
+ 1,
225
+ 1,
226
+ 1,
227
+ 1
228
+ ],
229
+ "backbone_stage3_groups": [
230
+ 1,
231
+ 1,
232
+ 1,
233
+ 1,
234
+ 1,
235
+ 1,
236
+ 1,
237
+ 1
238
+ ],
239
+ "backbone_stage3_in_channels": [
240
+ 128,
241
+ 256,
242
+ 256,
243
+ 256,
244
+ 256,
245
+ 256,
246
+ 256,
247
+ 256
248
+ ],
249
+ "backbone_stage3_kernel_size": [
250
+ [
251
+ 3,
252
+ 3
253
+ ],
254
+ [
255
+ 3,
256
+ 3
257
+ ],
258
+ [
259
+ 3,
260
+ 3
261
+ ],
262
+ [
263
+ 1,
264
+ 3
265
+ ],
266
+ [
267
+ 3,
268
+ 3
269
+ ],
270
+ [
271
+ 3,
272
+ 1
273
+ ],
274
+ [
275
+ 3,
276
+ 3
277
+ ],
278
+ [
279
+ 3,
280
+ 1
281
+ ]
282
+ ],
283
+ "backbone_stage3_out_channels": [
284
+ 256,
285
+ 256,
286
+ 256,
287
+ 256,
288
+ 256,
289
+ 256,
290
+ 256,
291
+ 256
292
+ ],
293
+ "backbone_stage3_stride": [
294
+ 2,
295
+ 1,
296
+ 1,
297
+ 1,
298
+ 1,
299
+ 1,
300
+ 1,
301
+ 1
302
+ ],
303
+ "backbone_stage4_dilation": [
304
+ 1,
305
+ 1,
306
+ 1,
307
+ 1,
308
+ 1
309
+ ],
310
+ "backbone_stage4_groups": [
311
+ 1,
312
+ 1,
313
+ 1,
314
+ 1,
315
+ 1
316
+ ],
317
+ "backbone_stage4_in_channels": [
318
+ 256,
319
+ 512,
320
+ 512,
321
+ 512,
322
+ 512
323
+ ],
324
+ "backbone_stage4_kernel_size": [
325
+ [
326
+ 3,
327
+ 3
328
+ ],
329
+ [
330
+ 1,
331
+ 3
332
+ ],
333
+ [
334
+ 3,
335
+ 1
336
+ ],
337
+ [
338
+ 3,
339
+ 1
340
+ ],
341
+ [
342
+ 1,
343
+ 3
344
+ ]
345
+ ],
346
+ "backbone_stage4_out_channels": [
347
+ 512,
348
+ 512,
349
+ 512,
350
+ 512,
351
+ 512
352
+ ],
353
+ "backbone_stage4_stride": [
354
+ 2,
355
+ 1,
356
+ 1,
357
+ 1,
358
+ 1
359
+ ],
360
+ "backbone_stride": 2,
361
+ "backbone_use_bn": true,
362
+ "bbox_type": 300,
363
+ "head_conv_dilation": 1,
364
+ "head_conv_groups": 1,
365
+ "head_conv_in_channels": 512,
366
+ "head_conv_kernel_size": [
367
+ 3,
368
+ 3
369
+ ],
370
+ "head_conv_out_channels": 128,
371
+ "head_conv_stride": 1,
372
+ "head_dropout_ratio": 0.1,
373
+ "head_final_act_func": null,
374
+ "head_final_bias": false,
375
+ "head_final_dilation": 1,
376
+ "head_final_dropout_rate": 0,
377
+ "head_final_groups": 1,
378
+ "head_final_has_shuffle": false,
379
+ "head_final_in_channels": 128,
380
+ "head_final_kernel_size": 1,
381
+ "head_final_ops_order": "weight",
382
+ "head_final_out_channels": 5,
383
+ "head_final_stride": 1,
384
+ "head_final_use_bn": false,
385
+ "head_pooling_size": 11,
386
+ "initializer_range": 0.02,
387
+ "loss_bg": false,
388
+ "min_area": 300,
389
+ "min_score": 300,
390
+ "neck_dilation": [
391
+ 1,
392
+ 1,
393
+ 1,
394
+ 1
395
+ ],
396
+ "neck_groups": [
397
+ 1,
398
+ 1,
399
+ 1,
400
+ 1
401
+ ],
402
+ "neck_in_channels": [
403
+ 64,
404
+ 128,
405
+ 256,
406
+ 512
407
+ ],
408
+ "neck_kernel_size": [
409
+ [
410
+ 3,
411
+ 3
412
+ ],
413
+ [
414
+ 3,
415
+ 3
416
+ ],
417
+ [
418
+ 3,
419
+ 3
420
+ ],
421
+ [
422
+ 3,
423
+ 3
424
+ ]
425
+ ],
426
+ "neck_out_channels": [
427
+ 128,
428
+ 128,
429
+ 128,
430
+ 128
431
+ ],
432
+ "neck_stride": [
433
+ 1,
434
+ 1,
435
+ 1,
436
+ 1
437
+ ],
438
+ "torch_dtype": "float32",
439
+ "transformers_version": "4.34.0.dev0"
440
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bbox_type": 300,
3
+ "crop_size": {
4
+ "height": 224,
5
+ "width": 224
6
+ },
7
+ "do_center_crop": false,
8
+ "do_normalize": true,
9
+ "do_reduce_labels": false,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "image_mean": [
13
+ 0.485,
14
+ 0.456,
15
+ 0.406
16
+ ],
17
+ "image_processor_type": "FastImageProcessor",
18
+ "image_std": [
19
+ 0.229,
20
+ 0.224,
21
+ 0.225
22
+ ],
23
+ "min_area": 300,
24
+ "min_score": 300,
25
+ "pooling_size": 11,
26
+ "resample": 3,
27
+ "rescale_factor": 0.00392156862745098,
28
+ "size": {
29
+ "height": 640,
30
+ "width": 640
31
+ }
32
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc50c180ba7740cf2348171bf0aff3a7a851b98c1485c64a7997043d6a7fb311
3
+ size 65786529