File size: 8,281 Bytes
a89d9fd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import os
import sys

__dir__ = os.path.dirname(os.path.abspath(__file__))
sys.path.append(__dir__)
sys.path.insert(0, os.path.abspath(os.path.join(__dir__, '..')))

import yaml
import paddle
import paddle.distributed as dist

from ppocr.data import build_dataloader
from ppocr.modeling.architectures import build_model
from ppocr.losses import build_loss
from ppocr.optimizer import build_optimizer
from ppocr.postprocess import build_post_process
from ppocr.metrics import build_metric
from ppocr.utils.save_load import load_model
from ppocr.utils.utility import set_seed
from ppocr.modeling.architectures import apply_to_static
import tools.program as program

dist.get_world_size()


def main(config, device, logger, vdl_writer):
    # init dist environment
    if config['Global']['distributed']:
        dist.init_parallel_env()

    global_config = config['Global']

    # build dataloader
    train_dataloader = build_dataloader(config, 'Train', device, logger)
    if len(train_dataloader) == 0:
        logger.error(
            "No Images in train dataset, please ensure\n" +
            "\t1. The images num in the train label_file_list should be larger than or equal with batch size.\n"
            +
            "\t2. The annotation file and path in the configuration file are provided normally."
        )
        return

    if config['Eval']:
        valid_dataloader = build_dataloader(config, 'Eval', device, logger)
    else:
        valid_dataloader = None

    # build post process
    post_process_class = build_post_process(config['PostProcess'],
                                            global_config)

    # build model
    # for rec algorithm
    if hasattr(post_process_class, 'character'):
        char_num = len(getattr(post_process_class, 'character'))
        if config['Architecture']["algorithm"] in ["Distillation",
                                                   ]:  # distillation model
            for key in config['Architecture']["Models"]:
                if config['Architecture']['Models'][key]['Head'][
                        'name'] == 'MultiHead':  # for multi head
                    if config['PostProcess'][
                            'name'] == 'DistillationSARLabelDecode':
                        char_num = char_num - 2
                    # update SARLoss params
                    assert list(config['Loss']['loss_config_list'][-1].keys())[
                        0] == 'DistillationSARLoss'
                    config['Loss']['loss_config_list'][-1][
                        'DistillationSARLoss']['ignore_index'] = char_num + 1
                    out_channels_list = {}
                    out_channels_list['CTCLabelDecode'] = char_num
                    out_channels_list['SARLabelDecode'] = char_num + 2
                    config['Architecture']['Models'][key]['Head'][
                        'out_channels_list'] = out_channels_list
                else:
                    config['Architecture']["Models"][key]["Head"][
                        'out_channels'] = char_num
        elif config['Architecture']['Head'][
                'name'] == 'MultiHead':  # for multi head
            if config['PostProcess']['name'] == 'SARLabelDecode':
                char_num = char_num - 2
            # update SARLoss params
            assert list(config['Loss']['loss_config_list'][1].keys())[
                0] == 'SARLoss'
            if config['Loss']['loss_config_list'][1]['SARLoss'] is None:
                config['Loss']['loss_config_list'][1]['SARLoss'] = {
                    'ignore_index': char_num + 1
                }
            else:
                config['Loss']['loss_config_list'][1]['SARLoss'][
                    'ignore_index'] = char_num + 1
            out_channels_list = {}
            out_channels_list['CTCLabelDecode'] = char_num
            out_channels_list['SARLabelDecode'] = char_num + 2
            config['Architecture']['Head'][
                'out_channels_list'] = out_channels_list
        else:  # base rec model
            config['Architecture']["Head"]['out_channels'] = char_num

        if config['PostProcess']['name'] == 'SARLabelDecode':  # for SAR model
            config['Loss']['ignore_index'] = char_num - 1

    model = build_model(config['Architecture'])

    use_sync_bn = config["Global"].get("use_sync_bn", False)
    if use_sync_bn:
        model = paddle.nn.SyncBatchNorm.convert_sync_batchnorm(model)
        logger.info('convert_sync_batchnorm')

    model = apply_to_static(model, config, logger)

    # build loss
    loss_class = build_loss(config['Loss'])

    # build optim
    optimizer, lr_scheduler = build_optimizer(
        config['Optimizer'],
        epochs=config['Global']['epoch_num'],
        step_each_epoch=len(train_dataloader),
        model=model)

    # build metric
    eval_class = build_metric(config['Metric'])

    logger.info('train dataloader has {} iters'.format(len(train_dataloader)))
    if valid_dataloader is not None:
        logger.info('valid dataloader has {} iters'.format(
            len(valid_dataloader)))

    use_amp = config["Global"].get("use_amp", False)
    amp_level = config["Global"].get("amp_level", 'O2')
    amp_custom_black_list = config['Global'].get('amp_custom_black_list', [])
    if use_amp:
        AMP_RELATED_FLAGS_SETTING = {'FLAGS_max_inplace_grad_add': 8, }
        if paddle.is_compiled_with_cuda():
            AMP_RELATED_FLAGS_SETTING.update({
                'FLAGS_cudnn_batchnorm_spatial_persistent': 1
            })
        paddle.fluid.set_flags(AMP_RELATED_FLAGS_SETTING)
        scale_loss = config["Global"].get("scale_loss", 1.0)
        use_dynamic_loss_scaling = config["Global"].get(
            "use_dynamic_loss_scaling", False)
        scaler = paddle.amp.GradScaler(
            init_loss_scaling=scale_loss,
            use_dynamic_loss_scaling=use_dynamic_loss_scaling)
        if amp_level == "O2":
            model, optimizer = paddle.amp.decorate(
                models=model,
                optimizers=optimizer,
                level=amp_level,
                master_weight=True)
    else:
        scaler = None

    # load pretrain model
    pre_best_model_dict = load_model(config, model, optimizer,
                                     config['Architecture']["model_type"])

    if config['Global']['distributed']:
        model = paddle.DataParallel(model)
    # start train
    program.train(config, train_dataloader, valid_dataloader, device, model,
                  loss_class, optimizer, lr_scheduler, post_process_class,
                  eval_class, pre_best_model_dict, logger, vdl_writer, scaler,
                  amp_level, amp_custom_black_list)


def test_reader(config, device, logger):
    loader = build_dataloader(config, 'Train', device, logger)
    import time
    starttime = time.time()
    count = 0
    try:
        for data in loader():
            count += 1
            if count % 1 == 0:
                batch_time = time.time() - starttime
                starttime = time.time()
                logger.info("reader: {}, {}, {}".format(
                    count, len(data[0]), batch_time))
    except Exception as e:
        logger.info(e)
    logger.info("finish reader: {}, Success!".format(count))


if __name__ == '__main__':
    config, device, logger, vdl_writer = program.preprocess(is_train=True)
    seed = config['Global']['seed'] if 'seed' in config['Global'] else 1024
    set_seed(seed)
    main(config, device, logger, vdl_writer)
    # test_reader(config, device, logger)