飞桨常规赛：中文场景文字识别- 12月第8名方案

# 从gitee上下载PaddleOCR代码，也可以从GitHub链接下载!git clone https://gitee.com/paddlepaddle/PaddleOCR.git --depth=1# 升级pip!pip install -U pip 
# 安装依赖%cd ~/PaddleOCR
%pip install -r requirements.txt

%cd ~/PaddleOCR/
!tree   -L 1

#  解压缩数据集%cd ~
!unzip -qa data/data62842/train_images.zip -d data/data62842/
!unzip -qa data/data62843/test_images.zip -d data/data62843/

# 使用命令查看训练数据文件夹下数据量是否是5万张!cd ~/data/data62842/train_images  &&  ls -l | grep "^-" | wc -l

# 使用命令查看test数据文件夹下数据量是否是1万张!cd ~/data/data62843/test_images  &&  ls -l | grep "^-" | wc -l

# 读取数据列表文件import pandas as pd
%cd ~
data_label=pd.read_csv('data/data62842/train_label.csv', encoding='gb2312')
data_label.head()

# 对数据列表文件进行划分%cd ~/data/data62842/print(data_label.shape)
train=data_label[:45000]
val=data_label[45000:]
train.to_csv('train.txt',sep='\t',header=None,index=None)
val.to_csv('val.txt',sep='\t',header=None,index=None)

# 查看数量print(train.shape)print(val.shape)

!head val.txt

!head train.txt

Architecture:
  model_type: rec
  algorithm: CRNN
  Transform:
  Backbone:
    name: MobileNetV3
    scale: 0.5
    model_name: small
    small_stride: [1, 2, 2, 2]  Neck:
    name: SequenceEncoder
    encoder_type: rnn
    hidden_size: 48
  Head:
    name: CTCHead
    fc_decay: 0.00001

Train:  dataset:    name: SimpleDataSet    data_dir: /home/aistudio/data/data62842/train_images    label_file_list: ["/home/aistudio/data/data62842/train.txt"]
...
...Eval:  dataset:    name: SimpleDataSet    data_dir: /home/aistudio/data/data62842/train_images    label_file_list: ["/home/aistudio/data/data62842/val.txt"]

Global:
  use_gpu: false             # true 使用GPU
  .....
  cal_metric_during_train: False   # true 打开评估

Train.loader.num_workers:4Eval.loader.num_workers: 4

Global:
  use_gpu: true
  epoch_num: 500
  log_smooth_window: 20
  print_batch_step: 10
  save_model_dir: ./output/rec_chinese_lite_v2.0
  save_epoch_step: 3
  # evaluation is run every 5000 iterations after the 4000th iteration
  eval_batch_step: [0, 2000]  cal_metric_during_train: True
  pretrained_model: ./ch_ppocr_mobile_v2.0_rec_pre/best_accuracy
  checkpoints: 
  save_inference_dir:
  use_visualdl: True
  infer_img: doc/imgs_words/ch/word_1.jpg
  # for data or label process
  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
  max_text_length: 25
  infer_mode: False
  use_space_char: True
  save_res_path: ./output/rec/predicts_chinese_lite_v2.0.txtOptimizer:
  name: Adam
  beta1: 0.9
  beta2: 0.999
  lr:
    name: Cosine
    learning_rate: 0.001
    warmup_epoch: 5
  regularizer:
    name: 'L2'
    factor: 0.00001Architecture:
  model_type: rec
  algorithm: CRNN
  Transform:
  Backbone:
    name: MobileNetV3
    scale: 0.5
    model_name: small
    small_stride: [1, 2, 2, 2]  Neck:
    name: SequenceEncoder
    encoder_type: rnn
    hidden_size: 48
  Head:
    name: CTCHead
    fc_decay: 0.00001Loss:
  name: CTCLossPostProcess:
  name: CTCLabelDecodeMetric:
  name: RecMetric
  main_indicator: accTrain:
  dataset:
    name: SimpleDataSet
    data_dir: /home/aistudio/data/data62842/train_images
    label_file_list: ["/home/aistudio/data/data62842/train.txt"]    transforms:
      - DecodeImage: # load image
          img_mode: BGR
          channel_first: False
      - RecAug: 
      - CTCLabelEncode: # Class handling label
      - RecResizeImg:
          image_shape: [3, 32, 320]      - KeepKeys:
          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
  loader:
    shuffle: True
    batch_size_per_card: 256
    drop_last: True
    num_workers: 8Eval:
  dataset:
    name: SimpleDataSet
    data_dir: /home/aistudio/data/data62842/train_images
    label_file_list: ["/home/aistudio/data/data62842/val.txt"]    transforms:
      - DecodeImage: # load image
          img_mode: BGR
          channel_first: False
      - CTCLabelEncode: # Class handling label
      - RecResizeImg:
          image_shape: [3, 32, 320]      - KeepKeys:
          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
  loader:
    shuffle: False
    drop_last: False
    batch_size_per_card: 256
    num_workers: 8

# 覆盖配置!cp -f  ~/rec_chinese_lite_train_v2.0.yml ~/PaddleOCR/configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml

%cd ~/PaddleOCR/# mobile模型# !wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar# !tar -xf ch_ppocr_mobile_v2.0_rec_pre.tar# server模型!wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar
!tar -xf ch_ppocr_server_v2.0_rec_pre.tar

%cd ~/PaddleOCR/# mobile模型# !python tools/train.py -c ./configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.checkpoints=./output/rec_chinese_lite_v2.0/latest# server模型!python tools/train.py -c ./configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml

[2021/12/30 23:26:54] root INFO: epoch: [68/500], iter: 9930, lr: 0.000962, loss: 5.635038, acc: 0.521482, norm_edit_dis: 0.745346, reader_cost: 0.01405 s, batch_cost: 0.26990 s, samples: 2560, ips: 948.50786[2021/12/30 23:27:11] root INFO: epoch: [68/500], iter: 9940, lr: 0.000962, loss: 5.653114, acc: 0.509764, norm_edit_dis: 0.740487, reader_cost: 0.01402 s, batch_cost: 0.26862 s, samples: 2560, ips: 953.03473[2021/12/30 23:27:26] root INFO: epoch: [68/500], iter: 9950, lr: 0.000962, loss: 5.411234, acc: 0.515623, norm_edit_dis: 0.748549, reader_cost: 0.00091 s, batch_cost: 0.26371 s, samples: 2560, ips: 970.76457[2021/12/30 23:27:40] root INFO: epoch: [68/500], iter: 9960, lr: 0.000962, loss: 5.588465, acc: 0.525389, norm_edit_dis: 0.755345, reader_cost: 0.00684 s, batch_cost: 0.25901 s, samples: 2560, ips: 988.38445[2021/12/30 23:27:48] root INFO: epoch: [68/500], iter: 9970, lr: 0.000961, loss: 5.789876, acc: 0.513670, norm_edit_dis: 0.740609, reader_cost: 0.00095 s, batch_cost: 0.15022 s, samples: 2560, ips: 1704.17763[2021/12/30 23:27:51] root INFO: epoch: [68/500], iter: 9974, lr: 0.000961, loss: 5.787237, acc: 0.511717, norm_edit_dis: 0.747102, reader_cost: 0.00018 s, batch_cost: 0.05935 s, samples: 1024, ips: 1725.41448[2021/12/30 23:27:51] root INFO: save model in ./output/rec_chinese_lite_v2.0/latest[2021/12/30 23:27:51] root INFO: Initialize indexs of datasets:['/home/aistudio/data/data62842/train.txt'][2021/12/30 23:28:21] root INFO: epoch: [69/500], iter: 9980, lr: 0.000961, loss: 5.801509, acc: 0.517576, norm_edit_dis: 0.749756, reader_cost: 1.10431 s, batch_cost: 1.37585 s, samples: 1536, ips: 111.64048[2021/12/30 23:28:40] root INFO: epoch: [69/500], iter: 9990, lr: 0.000961, loss: 5.548770, acc: 0.533201, norm_edit_dis: 0.762078, reader_cost: 0.00839 s, batch_cost: 0.32035 s, samples: 2560, ips: 799.11578[2021/12/30 23:28:56] root INFO: epoch: [69/500], iter: 10000, lr: 0.000961, loss: 5.449094, acc: 0.537107, norm_edit_dis: 0.762517, reader_cost: 0.00507 s, batch_cost: 0.25845 s, samples: 2560, ips: 990.51517eval model:: 100%|██████████████████████████████| 20/20 [00:15<00:00,  1.98it/s]
[2021/12/30 23:29:12] root INFO: cur metric, acc: 0.4641999071600186, norm_edit_dis: 0.6980459628854201, fps: 4204.853978632389[2021/12/30 23:29:12] root INFO: best metric, acc: 0.48179990364001923, start_epoch: 12, norm_edit_dis: 0.7096561279006699, fps: 4618.199275059127, best_epoch: 46

# GPU 评估， Global.checkpoints 为待测权重%cd ~/PaddleOCR/# mobile模型# !python  -m paddle.distributed.launch tools/eval.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml \#     -o Global.checkpoints=./output/rec_chinese_lite_v2.0/latest# server模型!python  -m paddle.distributed.launch tools/eval.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml \
    -o Global.checkpoints=./output/rec_chinese_common_v2.0/best_accuracy.pdparams

 with open(save_res_path, "w") as fout:
 	#添加列头
 	fout.write('new_name' + "\t" + 'value' +'\n')
        for file in get_image_file_list(config['Global']['infer_img']):
            logger.info("infer_img: {}".format(file))
            with open(file, 'rb') as f:
                img = f.read()
                data = {'image': img}
            batch = transform(data, ops)
            if config['Architecture']['algorithm'] == "SRN":
                encoder_word_pos_list = np.expand_dims(batch[1], axis=0)
                gsrm_word_pos_list = np.expand_dims(batch[2], axis=0)
                gsrm_slf_attn_bias1_list = np.expand_dims(batch[3], axis=0)
                gsrm_slf_attn_bias2_list = np.expand_dims(batch[4], axis=0)

                others = [
                    paddle.to_tensor(encoder_word_pos_list),
                    paddle.to_tensor(gsrm_word_pos_list),
                    paddle.to_tensor(gsrm_slf_attn_bias1_list),
                    paddle.to_tensor(gsrm_slf_attn_bias2_list)
                ]
            if config['Architecture']['algorithm'] == "SAR":
                valid_ratio = np.expand_dims(batch[-1], axis=0)
                img_metas = [paddle.to_tensor(valid_ratio)]

            images = np.expand_dims(batch[0], axis=0)
            images = paddle.to_tensor(images)
            if config['Architecture']['algorithm'] == "SRN":
                preds = model(images, others)
            elif config['Architecture']['algorithm'] == "SAR":
                preds = model(images, img_metas)
            else:
                preds = model(images)
            post_result = post_process_class(preds)
            info = None
            if isinstance(post_result, dict):
                rec_info = dict()
                for key in post_result:
                    if len(post_result[key][0]) >= 2:
                        rec_info[key] = {                            "label": post_result[key][0][0],                            "score": float(post_result[key][0][1]),
                        }
                info = json.dumps(rec_info)
            else:
                if len(post_result[0]) >= 2:
                    info = post_result[0][0] + "\t" + str(post_result[0][1])

            if info is not None:
                logger.info("\t result: {}".format(info))
                # fout.write(file + "\t" + info)
                # 格式化输出
                fout.write(file + "\t" + post_result[0][0] +'\n')
    logger.info("success!")

%cd ~/PaddleOCR/# mobile模型# !python tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml \#     -o Global.infer_img="/home/aistudio/data/data62843/test_images" \#     Global.pretrained_model="./output/rec_chinese_lite_v2.0/best_accuracy"# server模型!python tools/infer_rec.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml \
    -o Global.infer_img="/home/aistudio/data/data62843/test_images" \
    Global.checkpoints=./output/rec_chinese_common_v2.0/best_accuracy

[2021/12/30 23:53:50] root INFO: 	 result: 萧记果点	0.66611135[2021/12/30 23:53:50] root INFO: infer_img: /home/aistudio/data/data62843/test_images/9995.jpg
[2021/12/30 23:53:50] root INFO: 	 result: 福	0.1693737[2021/12/30 23:53:50] root INFO: infer_img: /home/aistudio/data/data62843/test_images/9996.jpg
[2021/12/30 23:53:50] root INFO: 	 result: 279	0.97771764[2021/12/30 23:53:50] root INFO: infer_img: /home/aistudio/data/data62843/test_images/9997.jpg
[2021/12/30 23:53:50] root INFO: 	 result: 公牛装饰开关	0.9916236[2021/12/30 23:53:50] root INFO: infer_img: /home/aistudio/data/data62843/test_images/9998.jpg
[2021/12/30 23:53:50] root INFO: 	 result: 专酒	0.118371546[2021/12/30 23:53:50] root INFO: infer_img: /home/aistudio/data/data62843/test_images/9999.jpg
[2021/12/30 23:53:50] root INFO: 	 result: 东之家	0.871051[2021/12/30 23:53:50] root INFO: success!
...
...

# 静态模型导出%cd ~/PaddleOCR/# mobile模型# !python tools/export_model.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.pretrained_model=./output/rec_chinese_lite_v2.0/best_accuracy.pdparams  Global.save_inference_dir=./inference/rec_inference/# server模型!python tools/export_model.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_common_v2.0.yml -o Global.pretrained_model=./output/rec_chinese_common_train_v2.0/best_accuracy.pdparams  Global.save_inference_dir=./inference/rec_inference/

%cd ~/PaddleOCR/
!du -sh ./inference/rec_inference/

# 使用导出静态模型预测%cd ~/PaddleOCR/
!python3.7 tools/infer/predict_rec.py  --rec_model_dir=./inference/rec_inference/  --image_dir="/home/aistudio/data/A榜测试数据集/TestAImages"

[2021/12/30 13:20:08] root INFO: Predicts of /home/aistudio/data/A榜测试数据集/TestAImages/TestA_000001.jpg:('MJ', 0.2357887)
[2021/12/30 13:20:08] root INFO: Predicts of /home/aistudio/data/A榜测试数据集/TestAImages/TestA_000002.jpg:('中门', 0.7167614)
[2021/12/30 13:20:08] root INFO: Predicts of /home/aistudio/data/A榜测试数据集/TestAImages/TestA_000003.jpg:('黄焖鸡米饭', 0.7325407)
[2021/12/30 13:20:08] root INFO: Predicts of /home/aistudio/data/A榜测试数据集/TestAImages/TestA_000004.jpg:('加行', 0.06699998)
[2021/12/30 13:20:08] root INFO: Predicts of /home/aistudio/data/A榜测试数据集/TestAImages/TestA_000005.jpg:('学商烤面航', 0.40579563)
[2021/12/30 13:20:08] root INFO: Predicts of /home/aistudio/data/A榜测试数据集/TestAImages/TestA_000006.jpg:('绿村装机 滋光彩机 CP口出国', 0.38243735)
[2021/12/30 13:20:08] root INFO: Predicts of /home/aistudio/data/A榜测试数据集/TestAImages/TestA_000007.jpg:('有酸锁 四好吃', 0.38957664)
[2021/12/30 13:20:08] root INFO: Predicts of /home/aistudio/data/A榜测试数据集/TestAImages/TestA_000008.jpg:('婚汽中海', 0.36037388)
[2021/12/30 13:20:08] root INFO: Predicts of /home/aistudio/data/A榜测试数据集/TestAImages/TestA_000009.jpg:('L', 0.25453746)
[2021/12/30 13:20:08] root INFO: Predicts of /home/aistudio/data/A榜测试数据集/TestAImages/TestA_000010.jpg:('清女装', 0.79736567)
[2021/12/30 13:20:08] root INFO: Predicts of /home/aistudio/data/A榜测试数据集/TestAImages/TestA_000011.jpg:('幼小数学视食', 0.50577885)
...
...

%cd ~
!head PaddleOCR/output/rec/predicts_chinese_common_v2.0.txt