Hugging Face's logo

Spaces:
Riksarkivet
/
htr_demo
Running on T4

App Files Community
7
htr_demo
File size: 12,902 Bytes 
5ebeb73
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
 
default_scope = "mmocr"
env_cfg = dict(
    cudnn_benchmark=True, mp_cfg=dict(mp_start_method="fork", opencv_num_threads=0), dist_cfg=dict(backend="nccl")
)
randomness = dict(seed=None)
default_hooks = dict(
    timer=dict(type="IterTimerHook"),
    logger=dict(type="LoggerHook", interval=100),
    param_scheduler=dict(type="ParamSchedulerHook"),
    checkpoint=dict(type="CheckpointHook", interval=1),
    sampler_seed=dict(type="DistSamplerSeedHook"),
    sync_buffer=dict(type="SyncBuffersHook"),
    visualization=dict(type="VisualizationHook", interval=1, enable=False, show=False, draw_gt=False, draw_pred=False),
)
log_level = "INFO"
log_processor = dict(type="LogProcessor", window_size=10, by_epoch=True)
load_from = (
    "/ceph/hpc/home/euerikl/projects/hf_openmmlab_models/models/checkpoints/1700_1800_combined_satrn/epoch_5.pth"
)
resume = False
val_evaluator = dict(
    type="Evaluator",
    metrics=[
        dict(
            type="WordMetric",
            mode=["exact", "ignore_case", "ignore_case_symbol"],
            valid_symbol="[^A-Z^a-z^0-9^一-龥^å^ä^ö^Å^Ä^Ö]",
        ),
        dict(type="CharMetric", valid_symbol="[^A-Z^a-z^0-9^一-龥^å^ä^ö^Å^Ä^Ö]"),
        dict(type="OneMinusNEDMetric", valid_symbol="[^A-Z^a-z^0-9^一-龥^å^ä^ö^Å^Ä^Ö]"),
    ],
)
test_evaluator = dict(
    type="Evaluator",
    metrics=[
        dict(
            type="WordMetric",
            mode=["exact", "ignore_case", "ignore_case_symbol"],
            valid_symbol="[^A-Z^a-z^0-9^一-龥^å^ä^ö^Å^Ä^Ö]",
        ),
        dict(type="CharMetric", valid_symbol="[^A-Z^a-z^0-9^一-龥^å^ä^ö^Å^Ä^Ö]"),
        dict(type="OneMinusNEDMetric", valid_symbol="[^A-Z^a-z^0-9^一-龥^å^ä^ö^Å^Ä^Ö]"),
    ],
)
vis_backends = [dict(type="LocalVisBackend")]
visualizer = dict(type="TextRecogLocalVisualizer", name="visualizer", vis_backends=[dict(type="TensorboardVisBackend")])
optim_wrapper = dict(type="OptimWrapper", optimizer=dict(type="Adam", lr=0.0003))
train_cfg = dict(type="EpochBasedTrainLoop", max_epochs=5, val_interval=1)
val_cfg = dict(type="ValLoop")
test_cfg = dict(type="TestLoop")
param_scheduler = [dict(type="MultiStepLR", milestones=[3, 4], end=5)]
file_client_args = dict(backend="disk")
dictionary = dict(
    type="Dictionary",
    dict_file="./models/SATRN/dict1700.txt",
    with_padding=True,
    with_unknown=True,
    same_start_end=True,
    with_start=True,
    with_end=True,
)
model = dict(
    type="SATRN",
    backbone=dict(type="ShallowCNN", input_channels=3, hidden_dim=512),
    encoder=dict(
        type="SATRNEncoder",
        n_layers=12,
        n_head=8,
        d_k=64,
        d_v=64,
        d_model=512,
        n_position=100,
        d_inner=2048,
        dropout=0.1,
    ),
    decoder=dict(
        type="NRTRDecoder",
        n_layers=6,
        d_embedding=512,
        n_head=8,
        d_model=512,
        d_inner=2048,
        d_k=64,
        d_v=64,
        module_loss=dict(type="CEModuleLoss", flatten=True, ignore_first_char=True),
        dictionary=dict(
            type="Dictionary",
            dict_file="./models/SATRN/dict1700.txt",
            with_padding=True,
            with_unknown=True,
            same_start_end=True,
            with_start=True,
            with_end=True,
        ),
        max_seq_len=100,
        postprocessor=dict(type="AttentionPostprocessor"),
    ),
    data_preprocessor=dict(
        type="TextRecogDataPreprocessor", mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375]
    ),
)
train_pipeline = [
    dict(type="LoadImageFromFile", file_client_args=dict(backend="disk"), ignore_empty=True, min_size=2),
    dict(type="LoadOCRAnnotations", with_text=True),
    dict(type="Resize", scale=(400, 64), keep_ratio=False),
    dict(type="PackTextRecogInputs", meta_keys=("img_path", "ori_shape", "img_shape", "valid_ratio")),
]
test_pipeline = [
    dict(type="LoadImageFromFile", file_client_args=dict(backend="disk")),
    dict(type="Resize", scale=(400, 64), keep_ratio=False),
    dict(type="LoadOCRAnnotations", with_text=True),
    dict(type="PackTextRecogInputs", meta_keys=("img_path", "ori_shape", "img_shape", "valid_ratio")),
]
HTR_1700_combined_train = dict(
    type="RecogTextDataset",
    parser_cfg=dict(type="LineJsonParser", keys=["filename", "text"]),
    data_root="/ceph/hpc/scratch/user/euerikl/data/HTR_1700_clean",
    ann_file="/ceph/hpc/home/euerikl/projects/hf_openmmlab_models/data/processed/1700_HTR_shuffled_train.jsonl",
    test_mode=False,
    pipeline=None,
)
HTR_1700_combined_test = dict(
    type="RecogTextDataset",
    parser_cfg=dict(type="LineJsonParser", keys=["filename", "text"]),
    data_root="/ceph/hpc/scratch/user/euerikl/data/HTR_1700_clean",
    ann_file="/ceph/hpc/home/euerikl/projects/hf_openmmlab_models/data/processed/1700_HTR_shuffled_val.jsonl",
    test_mode=True,
    pipeline=None,
)
pr_cr_combined_train = dict(
    type="RecogTextDataset",
    parser_cfg=dict(type="LineStrParser", keys=["filename", "text"], separator="|"),
    data_root="/ceph/hpc/scratch/user/euerikl/data/line_images",
    ann_file="/ceph/hpc/home/euerikl/projects/htr_1800/gt_files/combined_train.txt",
    test_mode=False,
    pipeline=None,
)
pr_cr_combined_test = dict(
    type="RecogTextDataset",
    parser_cfg=dict(type="LineStrParser", keys=["filename", "text"], separator="|"),
    data_root="/ceph/hpc/scratch/user/euerikl/data/line_images",
    ann_file="/ceph/hpc/home/euerikl/projects/htr_1800/gt_files/combined_eval.txt",
    test_mode=True,
    pipeline=None,
)
out_of_domain_1700_all_test = dict(
    type="RecogTextDataset",
    parser_cfg=dict(type="LineJsonParser", keys=["filename", "text"]),
    data_root="/ceph/hpc/scratch/user/euerikl/data/HTR_1700_testsets_clean",
    ann_file="/ceph/hpc/home/euerikl/projects/hf_openmmlab_models/data/processed/1700_testsets_gt/1700_HTR_testsets_all.jsonl",
    test_mode=True,
    pipeline=None,
)
train_list = [
    dict(
        type="RecogTextDataset",
        parser_cfg=dict(type="LineJsonParser", keys=["filename", "text"]),
        data_root="/ceph/hpc/scratch/user/euerikl/data/HTR_1700_clean",
        ann_file="/ceph/hpc/home/euerikl/projects/hf_openmmlab_models/data/processed/1700_HTR_shuffled_train.jsonl",
        test_mode=False,
        pipeline=None,
    ),
    dict(
        type="RecogTextDataset",
        parser_cfg=dict(type="LineStrParser", keys=["filename", "text"], separator="|"),
        data_root="/ceph/hpc/scratch/user/euerikl/data/line_images",
        ann_file="/ceph/hpc/home/euerikl/projects/htr_1800/gt_files/combined_train.txt",
        test_mode=False,
        pipeline=None,
    ),
]
test_list = [
    dict(
        type="RecogTextDataset",
        parser_cfg=dict(type="LineJsonParser", keys=["filename", "text"]),
        data_root="/ceph/hpc/scratch/user/euerikl/data/HTR_1700_testsets_clean",
        ann_file="/ceph/hpc/home/euerikl/projects/hf_openmmlab_models/data/processed/1700_testsets_gt/1700_HTR_testsets_all.jsonl",
        test_mode=True,
        pipeline=None,
    )
]
train_dataset = dict(
    type="ConcatDataset",
    datasets=[
        dict(
            type="RecogTextDataset",
            parser_cfg=dict(type="LineJsonParser", keys=["filename", "text"]),
            data_root="/ceph/hpc/scratch/user/euerikl/data/HTR_1700_clean",
            ann_file="/ceph/hpc/home/euerikl/projects/hf_openmmlab_models/data/processed/1700_HTR_shuffled_train.jsonl",
            test_mode=False,
            pipeline=None,
        ),
        dict(
            type="RecogTextDataset",
            parser_cfg=dict(type="LineStrParser", keys=["filename", "text"], separator="|"),
            data_root="/ceph/hpc/scratch/user/euerikl/data/line_images",
            ann_file="/ceph/hpc/home/euerikl/projects/htr_1800/gt_files/combined_train.txt",
            test_mode=False,
            pipeline=None,
        ),
    ],
    pipeline=[
        dict(type="LoadImageFromFile", file_client_args=dict(backend="disk"), ignore_empty=True, min_size=2),
        dict(type="LoadOCRAnnotations", with_text=True),
        dict(type="Resize", scale=(400, 64), keep_ratio=False),
        dict(type="PackTextRecogInputs", meta_keys=("img_path", "ori_shape", "img_shape", "valid_ratio")),
    ],
)
test_dataset = dict(
    type="ConcatDataset",
    datasets=[
        dict(
            type="RecogTextDataset",
            parser_cfg=dict(type="LineJsonParser", keys=["filename", "text"]),
            data_root="/ceph/hpc/scratch/user/euerikl/data/HTR_1700_testsets_clean",
            ann_file="/ceph/hpc/home/euerikl/projects/hf_openmmlab_models/data/processed/1700_testsets_gt/1700_HTR_testsets_all.jsonl",
            test_mode=True,
            pipeline=None,
        )
    ],
    pipeline=[
        dict(type="LoadImageFromFile", file_client_args=dict(backend="disk")),
        dict(type="Resize", scale=(400, 64), keep_ratio=False),
        dict(type="LoadOCRAnnotations", with_text=True),
        dict(type="PackTextRecogInputs", meta_keys=("img_path", "ori_shape", "img_shape", "valid_ratio")),
    ],
)
train_dataloader = dict(
    batch_size=8,
    num_workers=1,
    persistent_workers=True,
    sampler=dict(type="DefaultSampler", shuffle=True),
    dataset=dict(
        type="ConcatDataset",
        datasets=[
            dict(
                type="RecogTextDataset",
                parser_cfg=dict(type="LineJsonParser", keys=["filename", "text"]),
                data_root="/ceph/hpc/scratch/user/euerikl/data/HTR_1700_clean",
                ann_file="/ceph/hpc/home/euerikl/projects/hf_openmmlab_models/data/processed/1700_HTR_shuffled_train.jsonl",
                test_mode=False,
                pipeline=None,
            ),
            dict(
                type="RecogTextDataset",
                parser_cfg=dict(type="LineStrParser", keys=["filename", "text"], separator="|"),
                data_root="/ceph/hpc/scratch/user/euerikl/data/line_images",
                ann_file="/ceph/hpc/home/euerikl/projects/htr_1800/gt_files/combined_train.txt",
                test_mode=False,
                pipeline=None,
            ),
        ],
        pipeline=[
            dict(type="LoadImageFromFile", file_client_args=dict(backend="disk"), ignore_empty=True, min_size=2),
            dict(type="LoadOCRAnnotations", with_text=True),
            dict(type="Resize", scale=(400, 64), keep_ratio=False),
            dict(type="PackTextRecogInputs", meta_keys=("img_path", "ori_shape", "img_shape", "valid_ratio")),
        ],
    ),
)
test_dataloader = dict(
    batch_size=8,
    num_workers=1,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type="DefaultSampler", shuffle=False),
    dataset=dict(
        type="ConcatDataset",
        datasets=[
            dict(
                type="RecogTextDataset",
                parser_cfg=dict(type="LineJsonParser", keys=["filename", "text"]),
                data_root="/ceph/hpc/scratch/user/euerikl/data/HTR_1700_testsets_clean",
                ann_file="/ceph/hpc/home/euerikl/projects/hf_openmmlab_models/data/processed/1700_testsets_gt/1700_HTR_testsets_all.jsonl",
                test_mode=True,
                pipeline=None,
            )
        ],
        pipeline=[
            dict(type="LoadImageFromFile", file_client_args=dict(backend="disk")),
            dict(type="Resize", scale=(400, 64), keep_ratio=False),
            dict(type="LoadOCRAnnotations", with_text=True),
            dict(type="PackTextRecogInputs", meta_keys=("img_path", "ori_shape", "img_shape", "valid_ratio")),
        ],
    ),
)
val_dataloader = dict(
    batch_size=8,
    num_workers=1,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type="DefaultSampler", shuffle=False),
    dataset=dict(
        type="ConcatDataset",
        datasets=[
            dict(
                type="RecogTextDataset",
                parser_cfg=dict(type="LineJsonParser", keys=["filename", "text"]),
                data_root="/ceph/hpc/scratch/user/euerikl/data/HTR_1700_testsets_clean",
                ann_file="/ceph/hpc/home/euerikl/projects/hf_openmmlab_models/data/processed/1700_testsets_gt/1700_HTR_testsets_all.jsonl",
                test_mode=True,
                pipeline=None,
            )
        ],
        pipeline=[
            dict(type="LoadImageFromFile", file_client_args=dict(backend="disk")),
            dict(type="Resize", scale=(400, 64), keep_ratio=False),
            dict(type="LoadOCRAnnotations", with_text=True),
            dict(type="PackTextRecogInputs", meta_keys=("img_path", "ori_shape", "img_shape", "valid_ratio")),
        ],
    ),
)
gpu_ids = range(0, 4)
cudnn_benchmark = True
work_dir = "/ceph/hpc/home/euerikl/projects/hf_openmmlab_models/models/checkpoints/1700_1800_combined_satrn"
checkpoint_config = dict(interval=1)
auto_scale_lr = dict(base_batch_size=32)
launcher = "pytorch"