omnizart/patch_cnn/patch_cnn_melody/configurations.yaml

General:
    TranscriptionMode:
        Description: Mode of transcription by executing the `omnizart_fix patch-cnn transcribe` command.
        Type: String 
        Value: Melody
    CheckpointPath:
        Description: Path to the pre-trained models.
        Type: Map
        SubType: [String, String]
        Value:
            Melody: checkpoints/patch_cnn/patch_cnn_melody
    Feature:
        Description: Default settings of feature extraction
        Settings:
            PatchSize:
                Description: Input size of feature dimension.
                Type: Integer
                Value: 25
            PeakThreshold:
                Description: Threshold used to filter out peaks with small value.
                Type: Float
                Value: 0.5
            HopSize:
                Description: Hop size in seconds with respect to sampling rate.
                Type: Float
                Value: 0.02
            SamplingRate:
                Description: Adjust input sampling rate to this value.
                Type: Integer
                Value: 16000
            WindowSize:
                Type: Integer
                Value: 2049
            FrequencyResolution:
                Type: Float
                Value: 2.0
            FrequencyCenter:
                Description: Lowest frequency to extract.
                Type: Float
                Value: 80
            TimeCenter:
                Description: Highest frequency to extract (1/time_center).
                Type: Float
                Value: 0.001
            Gamma:
                Type: List
                SubType: Float
                Value: [0.24, 0.6, 1.0]
            BinsPerOctave:
                Description: Number of bins for each octave.
                Type: Integer
                Value: 48
    Model:
        Description: Default settings of training / testing the model.
        Settings:
            SavePrefix:
                Description: Prefix of the trained model's name to be saved.
                Type: String
                Value: patch_cnn
            SavePath:
                Description: Path to save the trained model.
                Type: String
                Value: ./checkpoints/patch_cnn
    Dataset:
        Description: Settings of datasets.
        Settings:
            SavePath:
                Description: Path for storing the downloaded datasets.
                Type: String
                Value: ./
            FeatureSavePath:
                Description: Path for storing the extracted feature. Default to the path under the dataset folder.
                Type: String
                Value: +
    Inference:
        Description: Default settings when infering notes.
        Settings:
            Threshold:
                Description: Threshold of the prediction value.
                Type: Float
                Value: 0.5
            MaxMethod:
                Description: Method of determine the position of the max prediction value.
                Type: String
                Value: posterior
                Choices: ["posterior", "prior"]
    Training:
        Description: Hyper parameters for training
        Settings:
            Epoch:
                Description: Maximum number of epochs for training.
                Type: Integer
                Value: 10
            Steps:
                Description: Number of training steps for each epoch.
                Type: Integer
                Value: 1000
            ValSteps:
                Description: Number of validation steps after each training epoch.
                Type: Integer
                Value: 500
            BatchSize:
                Description: Batch size of each training step.
                Type: Integer
                Value: 32
            ValBatchSize:
                Description: Batch size of each validation step.
                Type: Integer
                Value: 32
            EarlyStop:
                Description: Terminate the training if the validation performance doesn't imrove after n epochs.
                Type: Integer
                Value: 4
            InitLearningRate:
                Descriptoin: Initial learning rate.
                Type: Float
                Value: 0.0001