model_demo.yaml

# - requirement.txt  -  GPU: tensorflow-gpu, CPU: tensorflow
# - If you use the GPU version, you need to install some additional applications.
System:
  DeviceUsage: 0.7

# ModelName: Corresponding to the model file in the model directory,
# - such as YourModelName.pb, fill in YourModelName here.
# CharSet: Provides a default optional built-in solution:
# - [ALPHANUMERIC, ALPHANUMERIC_LOWER, ALPHANUMERIC_UPPER,
# -- NUMERIC, ALPHABET_LOWER, ALPHABET_UPPER, ALPHABET, ALPHANUMERIC_LOWER_MIX_CHINESE_3500]
# - Or you can use your own customized character set like: ['a', '1', '2'].
# CharMaxLength: Maximum length of characters， used for label padding.
# CharExclude: CharExclude should be a list, like: ['a', '1', '2']
# - which is convenient for users to freely combine character sets.
# - If you don't want to manually define the character set manually,
# - you can choose a built-in character set
# - and set the characters to be excluded by CharExclude parameter.
Model:
  Sites: [
    'YourModelName'
  ]
  ModelName: YourModelName
  ModelType: 150x50
  CharSet: ALPHANUMERIC_LOWER
  CharExclude: []
  CharReplace: {}
  ImageWidth: 150
  ImageHeight: 50

# Binaryzation: [-1: Off, >0 and < 255: On].
# Smoothing: [-1: Off, >0: On].
# Blur: [-1: Off, >0: On].
# Resize: [WIDTH, HEIGHT]
# - If the image size is too small, the training effect will be poor and you need to zoom in.
# ReplaceTransparent: [True, False]
# - True: Convert transparent images in RGBA format to opaque RGB format,
# - False: Keep the original image
Pretreatment:
  Binaryzation: -1
  Smoothing: -1
  Blur: -1
  Resize: [150, 50]
  ReplaceTransparent: True

# CNNNetwork: [CNN5, ResNet, DenseNet]
# RecurrentNetwork: [BLSTM, LSTM, SRU, BSRU, GRU]
# - The recommended configuration is CNN5+BLSTM / ResNet+BLSTM
# HiddenNum: [64, 128, 256]
# - This parameter indicates the number of nodes used to remember and store past states.
# Optimizer: Loss function algorithm for calculating gradient.
# - [AdaBound, Adam, Momentum]
NeuralNet:
  CNNNetwork: CNN5
  RecurrentNetwork: BLSTM
  HiddenNum: 64
  KeepProb: 0.98
  Optimizer: AdaBound
  PreprocessCollapseRepeated: False
  CTCMergeRepeated: True
  CTCBeamWidth: 1
  CTCTopPaths: 1
  WarpCTC: False

# TrainsPath and TestPath: The local absolute path of your training and testing set.
# DatasetPath: Package a sample of the TFRecords format from this path.
# TrainRegex and TestRegex: Default matching apple_20181010121212.jpg file.
# - The Default is .*?(?=_.*\.)
# TestSetNum: This is an optional parameter that is used when you want to extract some of the test set
# - from the training set when you are not preparing the test set separately.
# SavedSteps: A Session.run() execution is called a Step,
# - Used to save training progress, Default value is 100.
# ValidationSteps: Used to calculate accuracy, Default value is 500.
# TestSetNum: The number of test sets, if an automatic allocation strategy is used (TestPath not set).
# EndAcc: Finish the training when the accuracy reaches [EndAcc*100]% and other conditions.
# EndCost: Finish the training when the cost reaches EndCost and other conditions.
# EndEpochs: Finish the training when the epoch is greater than the defined epoch and other conditions.
# BatchSize: Number of samples selected for one training step.
# TestBatchSize: Number of samples selected for one validation step.
# LearningRate: Recommended value[0.01: MomentumOptimizer/AdamOptimizer, 0.001: AdaBoundOptimizer]
Trains:
  TrainsPath: './dataset/mnist-CNN5BLSTM-H64-28x28_trains.tfrecords'
  TestPath: './dataset/mnist-CNN5BLSTM-H64-28x28_test.tfrecords'
  DatasetPath: [
    "D:/***"
  ]
  TrainRegex: '.*?(?=_)'
  TestSetNum: 300
  SavedSteps: 100
  ValidationSteps: 500
  EndAcc: 0.95
  EndCost: 0.1
  EndEpochs: 2
  BatchSize: 128
  TestBatchSize: 300
  LearningRate: 0.001
  DecayRate: 0.98
  DecaySteps: 10000