AIWIN Handwritten OCR Recognition Contest based on PaddleOCR

AIWIN Handwritten OCR Recognition Contest based on PaddleOCR

1. Background

Ailab.aiwin.org.cn/competition…

The bank’s daily business involves the identification and entry of all kinds of vouchers, such as id card entry, check entry, statement entry and so on. In the past, the input method is mainly manual input, with low efficiency and high labor cost. In recent years, OCR technology is gradually replacing the traditional manual input method with its characteristics of automatic execution and less human intervention. But OCR technology, there are some problems in practical application, document of all kinds of fields of recognition, handwriting due to their different large fonts, of no fixed, semantic relevance is low, credentials background interference and so on reasons, lead to OCR recognition accuracy is not high, need a lot of artificial correction, the daily bank entry caused a certain influence.

2. Task

In this competition, handwritten image slice data set will be provided. The data set will be obtained from real business scenes through slice desensitization, and the participating teams will obtain corresponding recognition results through recognition technology. That is:

Input: Handwritten image slice data set

Output: Corresponding identification result

The competition questions are divided into two independent tasks in the competition schedule. Training sets, test sets and modeling environments under different conditions are set respectively, which are summarized as follows:

• Task 1: Provide an open downloadable training set and test set, allowing offline or online modeling of Notebook environment and Terminal container environment (offline), and output identification results to complete the contest.
• Task 2: Provide undownloadable training set, which requires online modeling through the Terminal container environment (offline) and submitting the model. The system inputs the test set (that is, invisible to the players) and outputs the recognition results to complete the competition.

3. Basic information of data

	Task a	Task 2
Training set (including verification set, please divide by yourself)	Eight thousand images, including two kinds of information, year and amount	30,000 images, including bank name, year, month, date, amount of 5 kinds of information.
The test set	Two thousand images	Set AB list: A list: 5,000 images B: 5,000 images

The original handwritten images are divided into three categories, respectively involving bank name, year, month and date, and amount, as shown below:

There may be a certain amount of interference information mixed in the corresponding image slices. The examples are as follows:

Two, environment Settings

PaddleOCR github.com/paddlepaddl… It is the most powerful OCR tool library in the universe, out of the box, fast.

# Download the PaddleOCR code from Gitee or from the GitHub link! git clone https://gitee.com/paddlepaddle/PaddleOCR.git --depth=1
Copy the code

Cloning into 'PaddleOCR'... remote: Enumerating objects: 1229, done.[K remote: Counting objects: 100% (1229/1229), done.[K remote: Compressing objects: 100% (1098/1098), done.[K remote: Total 1229 (delta 202), reused 707 (delta 80), pack-reused 0[K Receiving objects: 100% (1229/1229) and 100.43 MiB | 5.50 MiB/s, done. Resolving deltas: 100% (202/202), done. Checking connectivity... done.Copy the code

# upgrade PIP! pip install -U pip# install dependencies
%cd ~/PaddleOCR
%pip install -r requirements.txt
Copy the code

Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple Collecting pip [?25l Downloading https://pypi.tuna.tsinghua.edu.cn/packages/a4/6d/6463d49a933f547439d6b5b98b46af8742cc03ae83543e4d7688c2420f8b/pip-21.3.1 - py3 - none - any WHL (1.7 MB) [K | █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ | 1.7 MB 55.4 MB/s eta 0:00:01 [? 25 hinstalling collected Packages: PIP Found Existing Installation: PIP 19.2.3 Uninstalling PIP 19.2.3: Successfully uninstalled pip-19.2.3 Successfully installed pip-21.3.1 /home/aistudio/PaddleOCR Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple Collecting shapely Downloading https://pypi.tuna.tsinghua.edu.cn/packages/ae/20/33ce377bd24d122a4d54e22ae2c445b9b1be8240edb50040b40add950cd9/Shapely-1. 8.0 - cp37 - cp37m - manylinux_2_5_x86_64. Manylinux1_x86_64. WHL (1.1 MB) | █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ | 1.1 MB 7.6 MB/s [?25hCollecting scikit-image Downloading https://pypi.tuna.tsinghua.edu.cn/packages/9a/44/8f8c7f9c9de7fde70587a656d7df7d056e6f05192a74491f7bc074a724d0/scikit_ima Ge - 0.19.1 - cp37 - cp37m - manylinux_2_12_x86_64. Manylinux2010_x86_64, WHL (13.3 MB) | █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ | 13.3 MB 4.0MB /s [?25hCollecting imgaug==0.4.0 Downloading https://pypi.tuna.tsinghua.edu.cn/packages/66/b1/af3142c4a85cba6da9f4ebb5ff4e21e2616309552caca5e8acefe9840622/imgaug-0.4 . 0 - py2. Py3 - none - any. WHL (948 kB) | █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ | 948 kB 14.6 MB/s [? 25 hcollecting pyclipper Downloading https://pypi.tuna.tsinghua.edu.cn/packages/c5/fa/2c294127e4f88967149a68ad5b3e43636e94e3721109572f8f17ab15b772/pyclipper- 1.3.0. Post2 cp37 - cp37m - manylinux_2_5_x86_64. Manylinux1_x86_64, WHL (603 kB) | █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ | 603 kB 67.9 MB/s [?25hCollecting LMDB Downloading https://pypi.tuna.tsinghua.edu.cn/packages/4d/cf/3230b1c9b0bec406abb85a9332ba5805bdd03a1d24025c6bbcfb8ed71539/lmdb-1.3.0 - cp37 - cp37m - manylinux_2_12_x86_64. Manylinux2010_x86_64. WHL (298 kB) | █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ | 298 kB 11.0 MB/s [?25hRequirement already satisfied: TQDM in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from -r requirements.txt (line 6)) (4.36.1) Requirement already satisfied: Numpy in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from -r requirements.txt (line 7)) (1.20.3)  Requirement already satisfied: Visualdl in /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages (from -r requirements.txt (line 8)) (2.2.0) Collecting python - Levenshtein Downloading https://pypi.tuna.tsinghua.edu.cn/packages/2a/dc/97f2b63ef0fa1fd78dcb7195aca577804f6b2b51e712516cc0e902a9a201/python-Lev Enshtein - 0.12.2. Tar. Gz (50 kB) | █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ | 50 kB 23.9 MB/s [? 25 h Preparing metadata (setup. Py) ... [?25ldone [?25hCollecting opencv-contrib-python==4.4.0.46 Downloading https://pypi.tuna.tsinghua.edu.cn/packages/08/51/1e0a206dd5c70fea91084e6f43979dc13e8eb175760cc7a105083ec3eb68/opencv_con Trib_python 4.4.0.46 - cp37 - cp37m - manylinux2014_x86_64. WHL (55.7 MB) | █ ▊ | 3.1 MB 11.7 MB/s eta 0:00:0 done [? 25 h Created wheel for python-Levenshtein: Filename = python_Levenshtein - 0.12.2 cp37 - cp37m - linux_x86_64. WHL size = 171682 sha256=210cbc3beb9de6384f8dfd64ea9c1f7e7d4bd57233af34afe6994b95ae346f01 Stored in directory: /home/aistudio/.cache/pip/wheels/38/b9/a4/3729726160fb103833de468adb5ce019b58543ae41d0b0e446 Successfully built python-Levenshtein Installing collected packages: tifffile, PyWavelets, shapely, scikit-image, lxml, cssutils, cssselect, python-Levenshtein, pyclipper, premailer, opencv-contrib-python, lmdb, Imgaug Successfully installed PyWavelets-1.2.0 cssselect-1.1.0 cssutils-2.3.0 imgaug-0.4.0 lmDB-1.3.0 LXML -4.7.1 Opencv-contrib-python-4.4.0.46 premailer-3.10.0 pyclipper 1.3.0.post2 python-levenshtein 0.12.2 scikit-image-0.19.1 Shapely -1.8.0 TIFFFile -2021.11.2 Note: You may need to restart the kernel to use updated packages.Copy the code

3. Data preparation

The main tasks are:

• Data decompression
• Det data set formatting and data set partitioning
• Rec data set formatting and data set partitioning

# decompression%cd ~ ! Unzip-qoa 2021A_T1_Task1_ Data set Contains training sets and test sets.zip
Copy the code

/home/aistudio
Copy the code

View the data set
from PIL import Image
img=Image.open("Training set/amount/images / 8 bb39447774eb21a01777a9efa890543. JPG")
img
Copy the code

1. Amount data processing

%cd ~
View the data set! Head training set /amount/gt.jsonCopy the code

/ home/aistudio {" 8 bb39426774ee53f017770203bab0bc5. JPG ":" boss hk pick up two yuan spreading the whole ", "eight bb39447760a31c801762283f9dd63cb. JPG" : "Two above one hk $. The whole", "eight bb1943d774eb211017784b7af783c23. JPG" : "above hk $but spreading the whole", "eight bb194277657bb0501768d5379a4262b. JPG" : "Wu bai SAN she yuan 3 Angle of eight points", "eight bb3942b7657bb83017674d349786868. JPG" : "the boss hundred yuan", "eight bb1943d760a31b70176275a31832557. JPG" : "One over two thousand ErBai yuan", "eight bb19437760a2b5f017641f9743b41b4. JPG" : "3 m thousand hundred five yuan spreading Angle of eight points", "eight bb1941c7657bb01017674b446cc2a2e. JPG" : "Two $times or spreading ten yuan lu", "eight bb39441760a31b601764a13149e3008. JPG" : "nine company boss hk five yuan",Copy the code

import glob, codecs, json, os
import numpy as np

amount_jpgs = glob.glob('./ Training set /amount/images/*.jpg')
lines = codecs.open('./ Training set /amount/gt.json', encoding='utf-8').readlines()
lines = ' '.join(lines)
amount_gt = json.loads(lines.replace(',\n}'.'} '))
Copy the code

%cd ~/
# Divide train and eval
Write to the list file
f_train=open("./ training set /amount/train_list.txt".'w')
f_val=open("./ Training set /amount/val_list.txt".'w')

i=0
for key in amount_gt:
    if i%10= =0:
        f_val.write(key+ '\t'+amount_gt[key]+'\n')
    else:
        f_train.write(key+ '\t'+amount_gt[key]+'\n')
    i=i+1
Copy the code

/home/aistudio
Copy the code

! Head./ training set /amount/train_list.txtCopy the code

8 bb39447760a31c801762283f9dd63cb. JPG two company for hk $2 whole 8 bb1943d774eb211017784b7af783c23. JPG above hk but spreading 8 bb194277657bb0501768d5379a4262b. JPG wu bai SAN she yuan 3 Angle of eight points and eight bb3942b7657bb83017674d349786868. JPG or spreading 8 bb1943d760a31b70176275a31832557. JPG one over two thousand ErBai $8 bb19437760a2b5f017641f9743b41b4. JPG 3 m thousand hundred five yuan spreading Angle of points 8 bb1941c7657bb01017674b446cc2a2e. JPG two $times or spreading lu yuan whole 8 bb39441760a31b601764a13149e3008. JPG nine company boss mean of five yuan 8 bb3943c774eb20601775cf697f0456b. JPG one wan and pure thousand ErBai 3 ten thousands yuan 8 bb194207657bb1201765fd7645934b5. JPG strikes us $3 two Angle of the wholeCopy the code

date_gt.update(amount_gt)
s = ' '
for x in date_gt:
    s += date_gt[x]
char_list = list(set(list(s)))
char_list = char_list

with open('./ training set /amount/vocabulary. TXT '.'w') as up:
    for x in char_list:
        up.write(x + '\n')
Copy the code

! /amount/vocabulary. TXTCopy the code

Nine hundred and nine hundred and seventy-six dollars and two hundred and eighty fourCopy the code

2. Date data processing

%cd ~
date_jpgs = glob.glob('./ Training set /date/images/*.jpg')

lines = codecs.open('./ Training set /date/gt.json', encoding='utf-8').readlines()
lines = ' '.join(lines)
date_gt = json.loads(lines.replace(',\n}'.'} '))
Copy the code

/home/aistudio
Copy the code

# Divide train and eval
Write to the list file
f_train=open("./ trainset /date/train_list.txt".'w')
f_val=open("./ training set /date/val_list.txt".'w')

i=0
for key in date_gt:
    if i%10= =0:
        f_val.write(key+ '\t'+date_gt[key]+'\n')
    else:
        f_train.write(key+ '\t'+date_gt[key]+'\n')
    i=i+1
Copy the code

date_gt.update(date_gt)
s = ' '
for x in date_gt:
    s += date_gt[x]
char_list = list(set(list(s)))
char_list = char_list

with open('./ training set /date/ gloss.txt '.'w') as up:
    for x in char_list:
        up.write(x + '\n')
Copy the code

! Cat./ Training set /date/ gloss.txtCopy the code

Nine, three, seven, six, eight, two, forty-fiveCopy the code

Iv. Amount training and evaluation

Use PaddleOCR/configs/rec/ ch_pPOcr_v2.0 / rec_chinese_common_train_V2.0.yml as the reference

1. Money training

Global: use_gpu: true epoch_num: 500 log_smooth_window: 20 print_batch_step: 10 save_model_dir: . / output/rec_chinese_common_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: checkpoints: save_inference_dir: use_visualdl: False infer_img: doc/imgs_words/ch/word_1.jpg # for data or label process character_dict_path: TXT max_text_length: 25 infer_mode: False use_space_char: True save_res_path: ./output/rec/predicts_chinese_common_v2.0.txt Optimizer: name: Adam beta1:0.9 beta2:0.999 LR: name: Cosup_epoch: 5 Regularizer: name: 'L2' Factor: 0.00004 Architecture: Model_type: rec algorithm: CRNN Transform: Backbone: name: ResNet layers: 34 Neck: name: SequenceEncoder encoder_type: RNN hidden_size: 256 Head: name: CTCHead fc_decay: 0.00004 Loss: name: CTCLoss PostProcess: name: CTCLabelDecode Metric: name: RecMetric main_indicator: acc Train: dataset: name: SimpleDataSet data_dir: /home/aistudio/ training set /amount/images label_file_list: ["/home/aistudio/ training set /amount/train_list.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: 8 Eval: dataset: name: SimpleDataSet data_dir: /home/aistudio/ training set /amount/images label_file_list: ["/home/aistudio/ training set /amount/val_list.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: 8Copy the code

2. Download the pre-training model

%cd ~/PaddleOCR/
# server model! 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
Copy the code

/home/aistudio/PaddleOCR --2022-01-09 19:54:27-- https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar Resolving paddleocr.bj.bcebos.com (paddleocr.bj.bcebos.com)... 182.61.200.229 182.61.200.195, 2409:8c04:1001:1002:0:ff:b001:368a Connecting to paddleocr.bj.bcebos.com (paddleocr.bj.bcebos.com) | 182.61.200.229 | : 443... connected. HTTP request sent, awaiting response... 200 OK Length: 490184704 (467M) [application/x-tar] Saving to: 'ch_ppocr_server_v2. 0 _rec_pre. Tar' ch_ppocr_server_v2. 100% [= = = = = = = = = = = = = = = = = = = >] 467.48 M 48.1 MB/s in 13 in the late 2022-01-09 s 19:54:40 (35.6 MB/s) - 'CH_pPOcr_server_v2.0_rec_pre-.tar' SAVED [490184704/490184704]Copy the code

3. Money training

Overwrite the configuration file! cp -f .. /rec_chinese_common_train_v2. 0.yml ./configs/rec/ch_ppocr_v2. 0/rec_chinese_common_train_v2. 0.yml 
Copy the code

# server model%cd ~/PaddleOCR/ ! python tools/train.py -c ./configs/rec/ch_ppocr_v2. 0/rec_chinese_common_train_v2. 0.yml
Copy the code

Training log

[2022/01/09 20:21:27] Root INFO: epoch: [35/500], ITER: 480, LR: 0.000992, Loss: 0.322123, ACC: 0.972652, norm_edit_dis: 0.994506, reader_cost: 0.57496s, batCH_cost: 0.89715s, samples: 1280, ips: 142.67360 [2022/01/09 20:21:43] root INFO: epoch: [35/500], ITER: 489, LR: 0.000992, Loss: 0.256427, ACC: 0.974606, NORM_edit_dis: 0.995029, reader_cost: 0.00015s, batCH_cost: 0.55269s, samples: 2304, IPS: 416.86967 [2022/01/09 20:21:47] root INFO: Save model in./output/rec_chinese_common_v2.0/latest [2022/01/09 20:21:47] root INFO: Initialize Indexs of datasets:['/home/aistudio/ training set /amount/train_list. TXT '] [2022/01/09 20:21:55] root INFO: epoch: [36/500], iter: 490, LR: 0.000992, Loss: 0.249966, ACC: 0.974606, NORM_EDIT_dis: 0.995029, reader_cost: Samples: 256, IPS: 36.59348 [2022/01/09 20:22:13] root INFO: epoch: [36/500], iter: 500, LR: 0.000991, loss: 0.246262, ACC: 0.968746, NORM_EDIT_dis: 0.995142, reader_cost: 0.00045s, batCH_cost: 0.61365s, samples: 2560, IPS: 417.17631 Eval Model :: 100% | █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ █ | 2/2 [00:02 < 00:00, 1.04 s/it] [2022/01/09 20:22:15] root INFO: cur metric, acc: 0.9699975750060625, norm_EDIT_dis: 0.9909632884925447, FPS: 456.3268190347603Copy the code

3. Amount model evaluation

# server model! 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
Copy the code

/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/utils.py:26: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  def convert_to_list(value, n, name, dtype=np.int):
-----------  Configuration Arguments -----------
gpus: None
heter_worker_num: None
heter_workers: 
http_port: None
ips: 127.0.0.1
log_dir: log
nproc_per_node: None
server_num: None
servers: 
training_script: tools/eval.py
training_script_args: ['-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']
worker_num: None
workers: 
------------------------------------------------
WARNING 2022-01-09 20:25:44,789 launch.py:316] Not found distinct arguments and compiled with cuda. Default use collective mode
launch train in GPU mode
INFO 2022-01-09 20:25:44,793 launch_utils.py:471] Local start 1 processes. First process distributed environment info (Only For Debug): 
    +=======================================================================================+
    |                        Distributed Envs                      Value                    |
    +---------------------------------------------------------------------------------------+
    |                       PADDLE_TRAINER_ID                        0                      |
    |                 PADDLE_CURRENT_ENDPOINT                 127.0.0.1:45561               |
    |                     PADDLE_TRAINERS_NUM                        1                      |
    |                PADDLE_TRAINER_ENDPOINTS                 127.0.0.1:45561               |
    |                     FLAGS_selected_gpus                        0                      |
    +=======================================================================================+

INFO 2022-01-09 20:25:44,793 launch_utils.py:475] details abouts PADDLE_TRAINER_ENDPOINTS can be found in log/endpoints.log, and detail running logs maybe found in log/workerlog.0
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/utils.py:26: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  def convert_to_list(value, n, name, dtype=np.int):
[2022/01/09 20:25:46] root INFO: Architecture : 
[2022/01/09 20:25:46] root INFO:     Backbone : 
[2022/01/09 20:25:46] root INFO:         layers : 34
[2022/01/09 20:25:46] root INFO:         name : ResNet
[2022/01/09 20:25:46] root INFO:     Head : 
[2022/01/09 20:25:46] root INFO:         fc_decay : 4e-05
[2022/01/09 20:25:46] root INFO:         name : CTCHead
[2022/01/09 20:25:46] root INFO:     Neck : 
[2022/01/09 20:25:46] root INFO:         encoder_type : rnn
[2022/01/09 20:25:46] root INFO:         hidden_size : 256
[2022/01/09 20:25:46] root INFO:         name : SequenceEncoder
[2022/01/09 20:25:46] root INFO:     Transform : None
[2022/01/09 20:25:46] root INFO:     algorithm : CRNN
[2022/01/09 20:25:46] root INFO:     model_type : rec
[2022/01/09 20:25:46] root INFO: Eval : 
[2022/01/09 20:25:46] root INFO:     dataset : 
[2022/01/09 20:25:46] root INFO:         data_dir : /home/aistudio/训练集/amount/images
[2022/01/09 20:25:46] root INFO:         label_file_list : ['/home/aistudio/训练集/amount/val_list.txt']
[2022/01/09 20:25:46] root INFO:         name : SimpleDataSet
[2022/01/09 20:25:46] root INFO:         transforms : 
[2022/01/09 20:25:46] root INFO:             DecodeImage : 
[2022/01/09 20:25:46] root INFO:                 channel_first : False
[2022/01/09 20:25:46] root INFO:                 img_mode : BGR
[2022/01/09 20:25:46] root INFO:             CTCLabelEncode : None
[2022/01/09 20:25:46] root INFO:             RecResizeImg : 
[2022/01/09 20:25:46] root INFO:                 image_shape : [3, 32, 320]
[2022/01/09 20:25:46] root INFO:             KeepKeys : 
[2022/01/09 20:25:46] root INFO:                 keep_keys : ['image', 'label', 'length']
[2022/01/09 20:25:46] root INFO:     loader : 
[2022/01/09 20:25:46] root INFO:         batch_size_per_card : 256
[2022/01/09 20:25:46] root INFO:         drop_last : False
[2022/01/09 20:25:46] root INFO:         num_workers : 8
[2022/01/09 20:25:46] root INFO:         shuffle : False
[2022/01/09 20:25:46] root INFO: Global : 
[2022/01/09 20:25:46] root INFO:     cal_metric_during_train : True
[2022/01/09 20:25:46] root INFO:     character_dict_path : /home/aistudio/训练集/amount/vocabulary.txt
[2022/01/09 20:25:46] root INFO:     checkpoints : ./output/rec_chinese_common_v2.0/best_accuracy.pdparams
[2022/01/09 20:25:46] root INFO:     debug : False
[2022/01/09 20:25:46] root INFO:     distributed : False
[2022/01/09 20:25:46] root INFO:     epoch_num : 500
[2022/01/09 20:25:46] root INFO:     eval_batch_step : [100, 100]
[2022/01/09 20:25:46] root INFO:     infer_img : doc/imgs_words/ch/word_1.jpg
[2022/01/09 20:25:46] root INFO:     infer_mode : False
[2022/01/09 20:25:46] root INFO:     log_smooth_window : 20
[2022/01/09 20:25:46] root INFO:     max_text_length : 25
[2022/01/09 20:25:46] root INFO:     pretrained_model : ./ch_ppocr_server_v2.0_rec_pre/best_accuracy
[2022/01/09 20:25:46] root INFO:     print_batch_step : 10
[2022/01/09 20:25:46] root INFO:     save_epoch_step : 3
[2022/01/09 20:25:46] root INFO:     save_inference_dir : None
[2022/01/09 20:25:46] root INFO:     save_model_dir : ./output/rec_chinese_common_v2.0
[2022/01/09 20:25:46] root INFO:     save_res_path : ./output/rec/predicts_chinese_common_v2.0.txt
[2022/01/09 20:25:46] root INFO:     use_gpu : True
[2022/01/09 20:25:46] root INFO:     use_space_char : True
[2022/01/09 20:25:46] root INFO:     use_visualdl : False
[2022/01/09 20:25:46] root INFO: Loss : 
[2022/01/09 20:25:46] root INFO:     name : CTCLoss
[2022/01/09 20:25:46] root INFO: Metric : 
[2022/01/09 20:25:46] root INFO:     main_indicator : acc
[2022/01/09 20:25:46] root INFO:     name : RecMetric
[2022/01/09 20:25:46] root INFO: Optimizer : 
[2022/01/09 20:25:46] root INFO:     beta1 : 0.9
[2022/01/09 20:25:46] root INFO:     beta2 : 0.999
[2022/01/09 20:25:46] root INFO:     lr : 
[2022/01/09 20:25:46] root INFO:         learning_rate : 0.001
[2022/01/09 20:25:46] root INFO:         name : Cosine
[2022/01/09 20:25:46] root INFO:         warmup_epoch : 5
[2022/01/09 20:25:46] root INFO:     name : Adam
[2022/01/09 20:25:46] root INFO:     regularizer : 
[2022/01/09 20:25:46] root INFO:         factor : 4e-05
[2022/01/09 20:25:46] root INFO:         name : L2
[2022/01/09 20:25:46] root INFO: PostProcess : 
[2022/01/09 20:25:46] root INFO:     name : CTCLabelDecode
[2022/01/09 20:25:46] root INFO: Train : 
[2022/01/09 20:25:46] root INFO:     dataset : 
[2022/01/09 20:25:46] root INFO:         data_dir : /home/aistudio/训练集/amount/images
[2022/01/09 20:25:46] root INFO:         label_file_list : ['/home/aistudio/训练集/amount/train_list.txt']
[2022/01/09 20:25:46] root INFO:         name : SimpleDataSet
[2022/01/09 20:25:46] root INFO:         transforms : 
[2022/01/09 20:25:46] root INFO:             DecodeImage : 
[2022/01/09 20:25:46] root INFO:                 channel_first : False
[2022/01/09 20:25:46] root INFO:                 img_mode : BGR
[2022/01/09 20:25:46] root INFO:             RecAug : None
[2022/01/09 20:25:46] root INFO:             CTCLabelEncode : None
[2022/01/09 20:25:46] root INFO:             RecResizeImg : 
[2022/01/09 20:25:46] root INFO:                 image_shape : [3, 32, 320]
[2022/01/09 20:25:46] root INFO:             KeepKeys : 
[2022/01/09 20:25:46] root INFO:                 keep_keys : ['image', 'label', 'length']
[2022/01/09 20:25:46] root INFO:     loader : 
[2022/01/09 20:25:46] root INFO:         batch_size_per_card : 256
[2022/01/09 20:25:46] root INFO:         drop_last : True
[2022/01/09 20:25:46] root INFO:         num_workers : 8
[2022/01/09 20:25:46] root INFO:         shuffle : True
[2022/01/09 20:25:46] root INFO: profiler_options : None
[2022/01/09 20:25:46] root INFO: train with paddle 2.0.2 and device CUDAPlace(0)
[2022/01/09 20:25:46] root INFO: Initialize indexs of datasets:['/home/aistudio/训练集/amount/val_list.txt']
W0109 20:25:46.365166  6137 device_context.cc:362] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1
W0109 20:25:46.370265  6137 device_context.cc:372] device: 0, cuDNN Version: 7.6.
[2022/01/09 20:25:52] root INFO: resume from ./output/rec_chinese_common_v2.0/best_accuracy
[2022/01/09 20:25:52] root INFO: metric in ckpt ***************
[2022/01/09 20:25:52] root INFO: acc:0.9699975750060625
[2022/01/09 20:25:52] root INFO: norm_edit_dis:0.9909632884925447
[2022/01/09 20:25:52] root INFO: fps:456.3268190347603
[2022/01/09 20:25:52] root INFO: best_epoch:36
[2022/01/09 20:25:52] root INFO: start_epoch:37

eval model::   0%|          | 0/2 [00:00<?, ?it/s]
eval model::  50%|█████     | 1/2 [00:01<00:01,  1.72s/it]
eval model:: 100%|██████████| 2/2 [00:02<00:00,  1.29s/it]
eval model:: 100%|██████████| 2/2 [00:02<00:00,  1.11s/it]
[2022/01/09 20:25:54] root INFO: metric eval ***************
[2022/01/09 20:25:54] root INFO: acc:0.9699975750060625
[2022/01/09 20:25:54] root INFO: norm_edit_dis:0.9909632884925447
[2022/01/09 20:25:54] root INFO: fps:439.9205808964122
INFO 2022-01-09 20:25:56,825 launch.py:240] Local processes completed.
Copy the code

V. Date training and evaluation

Overwrite the configuration file! cp ./configs/rec/ch_ppocr_v2. 0/rec_chinese_common_train_v2. 0_date.yml ~/rec_chinese_common_train_v2. 0_date.yml
Copy the code

1. The configuration

Global: use_gpu: true epoch_num: 500 log_smooth_window: 20 print_batch_step: 10 save_model_dir: . / output/rec_chinese_common_v2. 0 _date save_epoch_step: 3 # evaluation is run every 5000 iterations after the 4000th iteration eval_batch_step: [100, 100] Cal_metric_during_train: parameter Description value Pretrained_model:./ ch_pPOcr_server_v2.0_rec_pre /best_accuracy I/O initialization: changing cpus save_inference_dir: use_visualdl: False infer_img: doc/imgs_words/ch/word_1.jpg # for data or label process character_dict_path: TXT max_text_length: 25 infer_mode: False use_space_char: True save_res_path: ./output/rec/predicts_chinese_common_v2.0.txt Optimizer: name: Adam beta1:0.9 beta2:0.999 LR: name: Cosup_epoch: 5 Regularizer: name: 'L2' Factor: 0.00004 Architecture: Model_type: rec algorithm: CRNN Transform: Backbone: name: ResNet layers: 34 Neck: name: SequenceEncoder encoder_type: RNN hidden_size: 256 Head: name: CTCHead fc_decay: 0.00004 Loss: name: CTCLoss PostProcess: name: CTCLabelDecode Metric: name: RecMetric main_indicator: acc Train: dataset: name: SimpleDataSet data_dir: /home/aistudio/ trainset /date/images Transforms label_file_list: ["/home/aistudio/ trainset /date/train_list.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: 8 Eval: dataset: name: SimpleDataSet data_dir: /home/aistudio/ trainset /date/images Transforms label_file_list: ["/home/aistudio/ trainset /date/val_list.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: 8Copy the code

2. Date model training

# server model%cd ~/PaddleOCR/ ! python tools/train.py -c ./configs/rec/ch_ppocr_v2. 0/rec_chinese_common_train_v2. 0_date.yml
Copy the code

Training log

[2022/01/09 21:15:41] root INFO: Initialize Indexs of datasets:['/home/aistudio/ training /date/train_list. TXT '] [2022/01/09 21:15:56] root INFO: epoch: [69/500], iter: 410, LR: 0.000963, Loss: 0.282951, ACC: 0.978514, NORM_EDIT_dis: 0.991211, reader_cost: 0.46780s, BATCH_cost: 0.81243s, samples: 1536, IPS: 189.06251 [2022/01/09 21:16:06] root INFO: epoch: [69/500], iter: 413, LR: 0.000962, Loss: 0.272608, ACC: 0.979490, NORM_EDIT_dis: 0.992269, reader_cost: 0.00150s, batCH_cost: 0.34571s, samples: 1536, IPS: 444.29798 [2022/01/09 21:16:10] root INFO: Save model in./output/ rec_chinese_common_V2.0_date /latest [2022/01/09 21:16:13] root INFO: Save model in./output/ rec_chinese_common_V2.0_date /iter_epoch_69 [2022/01/09 21:16:13] root INFO: Initialize Indexs of datasets:['/home/aistudio/ training /date/train_list. TXT '] [2022/01/09 21:16:39] root INFO: epoch: [70/500], iter: 419, LR: 0.000961, Loss: 0.259662, ACC: 0.983397, NORM_EDIT_dis: 0.993701, reader_cost: 0.51926s, batCH_cost: 1.21329s, samples: 3072, IPS: 253.19623 [2022/01/09 21:16:43] root INFO: Save model in./output/ rec_chinese_common_V2.0_date /latest [2022/01/09 21:16:43] root INFO: Initialize Indexs of datasets:['/home/aistudio/ training /date/train_list. TXT '] [2022/01/09 21:16:52] root INFO: epoch: [71/500], iter: 420, LR: 0.000961, Loss: 0.259662, ACC: 0.984373, NORM_EDIT_dis: 0.994189, reader_cost: Samples: 512, IPS: 76.32220 [2022/01/09 21:17:09] root INFO: epoch: [71/500], iter: 425, LR: 0.000960, Loss: 0.241655, ACC: 0.985350, NORM_EDIT_dis: 0.995117, reader_cost: 0.00232s, batCH_cost: 0.57741s, samples: 2560, IPS: 443.35555Copy the code

3. Date model evaluation

# server model! python -m paddle.distributed.launch tools/eval.py -c configs/rec/ch_ppocr_v2. 0/rec_chinese_common_train_v2. 0_date.yml \
    -o Global.checkpoints=./output/rec_chinese_common_v2. 0_date/best_accuracy.pdparams
Copy the code

/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/utils.py:26: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  def convert_to_list(value, n, name, dtype=np.int):
-----------  Configuration Arguments -----------
gpus: None
heter_worker_num: None
heter_workers: 
http_port: None
ips: 127.0.0.1
log_dir: log
nproc_per_node: None
server_num: None
servers: 
training_script: tools/eval.py
training_script_args: ['-c', 'configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0_date.yml', '-o', 'Global.checkpoints=./output/rec_chinese_common_v2.0_date/best_accuracy.pdparams']
worker_num: None
workers: 
------------------------------------------------
WARNING 2022-01-09 21:17:26,064 launch.py:316] Not found distinct arguments and compiled with cuda. Default use collective mode
launch train in GPU mode
INFO 2022-01-09 21:17:26,068 launch_utils.py:471] Local start 1 processes. First process distributed environment info (Only For Debug): 
    +=======================================================================================+
    |                        Distributed Envs                      Value                    |
    +---------------------------------------------------------------------------------------+
    |                       PADDLE_TRAINER_ID                        0                      |
    |                 PADDLE_CURRENT_ENDPOINT                 127.0.0.1:50745               |
    |                     PADDLE_TRAINERS_NUM                        1                      |
    |                PADDLE_TRAINER_ENDPOINTS                 127.0.0.1:50745               |
    |                     FLAGS_selected_gpus                        0                      |
    +=======================================================================================+

INFO 2022-01-09 21:17:26,068 launch_utils.py:475] details abouts PADDLE_TRAINER_ENDPOINTS can be found in log/endpoints.log, and detail running logs maybe found in log/workerlog.0
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/utils.py:26: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
  def convert_to_list(value, n, name, dtype=np.int):
[2022/01/09 21:17:27] root INFO: Architecture : 
[2022/01/09 21:17:27] root INFO:     Backbone : 
[2022/01/09 21:17:27] root INFO:         layers : 34
[2022/01/09 21:17:27] root INFO:         name : ResNet
[2022/01/09 21:17:27] root INFO:     Head : 
[2022/01/09 21:17:27] root INFO:         fc_decay : 4e-05
[2022/01/09 21:17:27] root INFO:         name : CTCHead
[2022/01/09 21:17:27] root INFO:     Neck : 
[2022/01/09 21:17:27] root INFO:         encoder_type : rnn
[2022/01/09 21:17:27] root INFO:         hidden_size : 256
[2022/01/09 21:17:27] root INFO:         name : SequenceEncoder
[2022/01/09 21:17:27] root INFO:     Transform : None
[2022/01/09 21:17:27] root INFO:     algorithm : CRNN
[2022/01/09 21:17:27] root INFO:     model_type : rec
[2022/01/09 21:17:27] root INFO: Eval : 
[2022/01/09 21:17:27] root INFO:     dataset : 
[2022/01/09 21:17:27] root INFO:         data_dir : /home/aistudio/训练集/date/images
[2022/01/09 21:17:27] root INFO:         label_file_list : ['/home/aistudio/训练集/date/val_list.txt']
[2022/01/09 21:17:27] root INFO:         name : SimpleDataSet
[2022/01/09 21:17:27] root INFO:         transforms : 
[2022/01/09 21:17:27] root INFO:             DecodeImage : 
[2022/01/09 21:17:27] root INFO:                 channel_first : False
[2022/01/09 21:17:27] root INFO:                 img_mode : BGR
[2022/01/09 21:17:27] root INFO:             CTCLabelEncode : None
[2022/01/09 21:17:27] root INFO:             RecResizeImg : 
[2022/01/09 21:17:27] root INFO:                 image_shape : [3, 32, 320]
[2022/01/09 21:17:27] root INFO:             KeepKeys : 
[2022/01/09 21:17:27] root INFO:                 keep_keys : ['image', 'label', 'length']
[2022/01/09 21:17:27] root INFO:     loader : 
[2022/01/09 21:17:27] root INFO:         batch_size_per_card : 256
[2022/01/09 21:17:27] root INFO:         drop_last : False
[2022/01/09 21:17:27] root INFO:         num_workers : 8
[2022/01/09 21:17:27] root INFO:         shuffle : False
[2022/01/09 21:17:27] root INFO: Global : 
[2022/01/09 21:17:27] root INFO:     cal_metric_during_train : True
[2022/01/09 21:17:27] root INFO:     character_dict_path : /home/aistudio/训练集/date/vocabulary.txt
[2022/01/09 21:17:27] root INFO:     checkpoints : ./output/rec_chinese_common_v2.0_date/best_accuracy.pdparams
[2022/01/09 21:17:27] root INFO:     debug : False
[2022/01/09 21:17:27] root INFO:     distributed : False
[2022/01/09 21:17:27] root INFO:     epoch_num : 500
[2022/01/09 21:17:27] root INFO:     eval_batch_step : [100, 100]
[2022/01/09 21:17:27] root INFO:     infer_img : doc/imgs_words/ch/word_1.jpg
[2022/01/09 21:17:27] root INFO:     infer_mode : False
[2022/01/09 21:17:27] root INFO:     log_smooth_window : 20
[2022/01/09 21:17:27] root INFO:     max_text_length : 25
[2022/01/09 21:17:27] root INFO:     pretrained_model : ./ch_ppocr_server_v2.0_rec_pre/best_accuracy
[2022/01/09 21:17:27] root INFO:     print_batch_step : 10
[2022/01/09 21:17:27] root INFO:     save_epoch_step : 3
[2022/01/09 21:17:27] root INFO:     save_inference_dir : None
[2022/01/09 21:17:27] root INFO:     save_model_dir : ./output/rec_chinese_common_v2.0_date
[2022/01/09 21:17:27] root INFO:     save_res_path : ./output/rec/predicts_chinese_common_v2.0.txt
[2022/01/09 21:17:27] root INFO:     use_gpu : True
[2022/01/09 21:17:27] root INFO:     use_space_char : True
[2022/01/09 21:17:27] root INFO:     use_visualdl : False
[2022/01/09 21:17:27] root INFO: Loss : 
[2022/01/09 21:17:27] root INFO:     name : CTCLoss
[2022/01/09 21:17:27] root INFO: Metric : 
[2022/01/09 21:17:27] root INFO:     main_indicator : acc
[2022/01/09 21:17:27] root INFO:     name : RecMetric
[2022/01/09 21:17:27] root INFO: Optimizer : 
[2022/01/09 21:17:27] root INFO:     beta1 : 0.9
[2022/01/09 21:17:27] root INFO:     beta2 : 0.999
[2022/01/09 21:17:27] root INFO:     lr : 
[2022/01/09 21:17:27] root INFO:         learning_rate : 0.001
[2022/01/09 21:17:27] root INFO:         name : Cosine
[2022/01/09 21:17:27] root INFO:         warmup_epoch : 5
[2022/01/09 21:17:27] root INFO:     name : Adam
[2022/01/09 21:17:27] root INFO:     regularizer : 
[2022/01/09 21:17:27] root INFO:         factor : 4e-05
[2022/01/09 21:17:27] root INFO:         name : L2
[2022/01/09 21:17:27] root INFO: PostProcess : 
[2022/01/09 21:17:27] root INFO:     name : CTCLabelDecode
[2022/01/09 21:17:27] root INFO: Train : 
[2022/01/09 21:17:27] root INFO:     dataset : 
[2022/01/09 21:17:27] root INFO:         data_dir : /home/aistudio/训练集/date/images
[2022/01/09 21:17:27] root INFO:         label_file_list : ['/home/aistudio/训练集/date/train_list.txt']
[2022/01/09 21:17:27] root INFO:         name : SimpleDataSet
[2022/01/09 21:17:27] root INFO:         transforms : 
[2022/01/09 21:17:27] root INFO:             DecodeImage : 
[2022/01/09 21:17:27] root INFO:                 channel_first : False
[2022/01/09 21:17:27] root INFO:                 img_mode : BGR
[2022/01/09 21:17:27] root INFO:             RecAug : None
[2022/01/09 21:17:27] root INFO:             CTCLabelEncode : None
[2022/01/09 21:17:27] root INFO:             RecResizeImg : 
[2022/01/09 21:17:27] root INFO:                 image_shape : [3, 32, 320]
[2022/01/09 21:17:27] root INFO:             KeepKeys : 
[2022/01/09 21:17:27] root INFO:                 keep_keys : ['image', 'label', 'length']
[2022/01/09 21:17:27] root INFO:     loader : 
[2022/01/09 21:17:27] root INFO:         batch_size_per_card : 512
[2022/01/09 21:17:27] root INFO:         drop_last : True
[2022/01/09 21:17:27] root INFO:         num_workers : 8
[2022/01/09 21:17:27] root INFO:         shuffle : True
[2022/01/09 21:17:27] root INFO: profiler_options : None
[2022/01/09 21:17:27] root INFO: train with paddle 2.0.2 and device CUDAPlace(0)
[2022/01/09 21:17:27] root INFO: Initialize indexs of datasets:['/home/aistudio/训练集/date/val_list.txt']
W0109 21:17:27.794884 15547 device_context.cc:362] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1
W0109 21:17:27.800077 15547 device_context.cc:372] device: 0, cuDNN Version: 7.6.
[2022/01/09 21:17:33] root INFO: resume from ./output/rec_chinese_common_v2.0_date/best_accuracy
[2022/01/09 21:17:33] root INFO: metric in ckpt ***************
[2022/01/09 21:17:33] root INFO: acc:0.991173555371896
[2022/01/09 21:17:33] root INFO: norm_edit_dis:0.9953431509515168
[2022/01/09 21:17:33] root INFO: fps:443.3070479891199
[2022/01/09 21:17:33] root INFO: best_epoch:67
[2022/01/09 21:17:33] root INFO: start_epoch:68

eval model::   0%|          | 0/2 [00:00<?, ?it/s]
eval model::  50%|█████     | 1/2 [00:01<00:01,  1.59s/it]
eval model:: 100%|██████████| 2/2 [00:01<00:00,  1.17s/it]
eval model:: 100%|██████████| 2/2 [00:01<00:00,  1.02it/s]
[2022/01/09 21:17:35] root INFO: metric eval ***************
[2022/01/09 21:17:35] root INFO: acc:0.991173555371896
[2022/01/09 21:17:35] root INFO: norm_edit_dis:0.9953431509515168
[2022/01/09 21:17:35] root INFO: fps:441.1924785284007
INFO 2022-01-09 21:17:38,107 launch.py:240] Local processes completed.
Copy the code

6. Result prediction

Modify the tools/infer_rec. Py

with open(save_res_path, "w") as fout: 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(os.path.basename(file) + "\t" + post_result[0][0]+"\n") logger.info("success!" )Copy the code

! cp ~/infer_rec.py ~/PaddleOCR/tools/infer_rec.pyCopy the code

1. Amount forecast

# server model! 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/ test set /amount/images" \
    Global.checkpoints=./output/rec_chinese_common_v2. 0/best_accuracy
Copy the code

The output log

[2022/01/09 21:33:25] root INFO: infer_img: / home/aistudio/test set/amount/images / 8 bb1941c760a2c1d01762c63a2220571. JPG [2022/01/09 21:33:25] root INFO: the result: [2022/01/09 21:33:25] root INFO: infer_img: / home/aistudio/test set/amount/images / 8 bb1941c760a2c1d01762cc9ce6e6029. JPG [2022/01/09 21:33:25] root INFO: the result: [2022/01/09 21:33:25] Root INFO: infer_img: / home/aistudio/test set/amount/images / 8 bb1941c760a2c1d017640031a39469f. JPG [2022/01/09 21:33:25] root INFO: the result: [2022/01/09 21:33:25] root INFO: infer_img: / home/aistudio/test set/amount/images / 8 bb1941c760a2c1d0176415a9ec807fe. JPG [2022/01/09 21:33:25] root INFO: the result: [2022/01/09 21:33:25] Root INFO: infer_img: / home/aistudio/test set/amount/images / 8 bb1941c760a2c1d017645417b3b5c5e. JPG [2022/01/09 21:33:25] root INFO: the result: [2022/01/09 21:33:25] Root INFO: infer_img: / home/aistudio/test set/amount/images / 8 bb1941c760a2c1d017646019cf7387d. JPG [2022/01/09 21:33:25] root INFO: the result: [2022/01/09 21:33:25] Root INFO: infer_img: / home/aistudio/test set/amount/images / 8 bb1941c760a2c1d01764b77a53735a0. JPG [2022/01/09 21:33:25] root INFO: the result: Seven hundred and forty-one Yuan seventy-three minutesCopy the code

! head ./output/rec/predicts_chinese_common_v2. 0.txt
Copy the code

8 bb1941c760a2c1d017626c361da6c4d. JPG one will visit hk suhuang yuan is 8 bb1941c760a2c1d01762b943a624421. JPG one picked up a will 8 bb1941c760a2c1d01762c63a2220571. JPG above usd but transgressed, two horn three points and eight bb1941c760a2c1d01762cc9ce6e6029. JPG Wan San thousand yuan 8 bb1941c760a2c1d017640031a39469f. JPG nine than pure thousand hundred five pure yuan lu wu Angle points and eight bb1941c760a2c1d0176415a9ec807fe spreading. JPG wu wan and pure thousand yuan 8 bb1941c760a2c1d017645417b3b5c5e. JPG three Wan San thousand hundred boss lu wu yuan boss Angle of nine points and eight bb1941c760a2c1d017646019cf7387d. JPG to& zero five Angle of spreading the whole nine yuan 8 bb1941c760a2c1d01764b77a53735a0. JPG and pure hundred ten thousands yuan widely spreading Angle of three points and eight bb1941c7657bb0101765edc72b01d52. JPG one over two thousand ErBai suhuang bossCopy the code

2. Date prediction

# server model! python tools/infer_rec.py -c configs/rec/ch_ppocr_v2. 0/rec_chinese_common_train_v2. 0_date.yml \
    -o Global.infer_img="/home/aistudio/ test set /date/images" \
    Global.checkpoints=./output/rec_chinese_common_v2. 0_date/best_accuracy
Copy the code

The output log

[2022/01/09 21:34:48] root INFO: infer_img: / home/aistudio/test set/date/images / 0 _8bb1941c7a248693017a421e33087817. JPG [2022/01/09 21:34:48] root INFO: the result: [2022/01/09 21:34:48] Root INFO: infer_img: / home/aistudio/test set/date/images / 0 _8bb1941c7a248693017a5653c6d32277. JPG [2022/01/09 21:34:48] root INFO: the result: [2022/01/09 21:34:48] Root INFO: infer_img: / home/aistudio/test set/date/images / 0 _8bb1941c7a248693017a56bc0a886d10. JPG [2022/01/09 21:34:48] root INFO: the result: [2022/01/09 21:34:48] Root INFO: infer_img: / home/aistudio/test set/date/images / 0 _8bb1941c7a248693017a8955798e0c20. JPG [2022/01/09 21:34:48] root INFO: the result: [2022/01/09 21:34:48] Root INFO: infer_img: / home/aistudio/test set/date/images / 0 _8bb1941c7a248693017aa87d11e203b6. JPG [2022/01/09 21:34:48] root INFO: the result: [2022/01/09 21:34:48] Root INFO: infer_img: / home/aistudio/test set/date/images / 0 _8bb1941c7a248694017a31b07a3a1b2c. JPG [2022/01/09 21:34:48] root INFO: the result: [2022/01/09 21:34:48] Root INFO: infer_img: / home/aistudio/test set/date/images / 0 _8bb1941c7a248694017a3cfacc781d85. JPG [2022/01/09 21:34:48] root INFO: the result: [2022/01/09 21:34:48] Root INFO: infer_img: / home/aistudio/test set/date/images / 0 _8bb1941c7a248694017a987384ab04e8. JPG [2022/01/09 21:34:48] root INFO: the result: Two zero one 0.9853095Copy the code

! head ./output/rec/predicts_chinese_common_v2. 0_date.txt
Copy the code

0 _8bb1941c7a248693017a377ec36606b7. JPG two zero two one 0 _8bb1941c7a248693017a421e33087817. JPG two zero two one 0 _8bb1941c7a248693017a5653c6d32277. JPG two zero two one 0 _8bb1941c7a248693017a56bc0a886d10. JPG two zero two one 0 _8bb1941c7a248693017a8955798e0c20. JPG two zero two one 0 _8bb1941c7a248693017aa87d11e203b6. JPG two zero two one 0 _8bb1941c7a248694017a31b07a3a1b2c. JPG two zero two one 0 _8bb1941c7a248694017a3cfacc781d85. JPG two zero two one 0 _8bb1941c7a248694017a987384ab04e8. JPG two zero two one 0 _8bb1941c7a248694017a9ee81daf390b. JPG two zero two oneCopy the code

/output/rec/predicts_chinese_common_v2.0. TXT and /output/rec/predicts_chinese_common_v2.0_date. TXT. The competition is now closed.