a
    Sic8                     @   s   d Z ddlZddlm  mZ ddlmZ ddl	m
Z
 zddlZW n eyX   dZY n0 dZe
dg ddddZdd Zdd Zdd ZdddZdd ZdS )z&Keras audio dataset loading utilities.    N)dataset_utils)keras_export)z.wavz(keras.utils.audio_dataset_from_directory)v1inferredint    FTc                 C   s  |dvr<t |ttfs$td| |r<td| d| |dvrRtd| |rf|durftd|durt |tstd	| |d
krtd| tdu rtd|du s|du rd}d}t|
|||	 |	du rt	j
d}	tj| |t|||	|d\}}}|dkr,t|dkr,td| |dkrt|||
| |||||d	\}}t||||	|||d}t||d|	|||d}||fS t||| |
||||||d
}t||||	|||d}|S dS )a  Generates a `tf.data.Dataset` from audio files in a directory.

    If your directory structure is:

    ```
    main_directory/
    ...class_a/
    ......a_audio_1.wav
    ......a_audio_2.wav
    ...class_b/
    ......b_audio_1.wav
    ......b_audio_2.wav
    ```

    Then calling `audio_dataset_from_directory(main_directory,
    labels='inferred')`
    will return a `tf.data.Dataset` that yields batches of audio files from
    the subdirectories `class_a` and `class_b`, together with labels
    0 and 1 (0 corresponding to `class_a` and 1 corresponding to `class_b`).

    Only `.wav` files are supported at this time.

    Args:
      directory: Directory where the data is located. If `labels` is "inferred",
        it should contain subdirectories, each containing audio files for a
        class. Otherwise, the directory structure is ignored.
      labels: Either "inferred" (labels are generated from the directory
        structure), None (no labels), or a list/tuple of integer labels of the
        same size as the number of audio files found in the directory. Labels
        should be sorted according to the alphanumeric order of the audio file
        paths (obtained via `os.walk(directory)` in Python).
      label_mode: String describing the encoding of `labels`. Options are:
          - 'int': means that the labels are encoded as integers (e.g. for
            `sparse_categorical_crossentropy` loss). - 'categorical' means that
            the labels are encoded as a categorical vector (e.g. for
            `categorical_crossentropy` loss). - 'binary' means that the labels
            (there can be only 2) are encoded as `float32` scalars with values 0
            or 1 (e.g. for `binary_crossentropy`). - None (no labels).
      class_names: Only valid if "labels" is "inferred". This is the explicit
        list of class names (must match names of subdirectories). Used to
        control the order of the classes (otherwise alphanumerical order is
        used).
      batch_size: Size of the batches of data. Default: 32. If `None`, the data
        will not be batched (the dataset will yield individual samples).
      sampling_rate: Audio sampling rate (in samples per second).
      output_sequence_length: Maximum length of an audio sequence. Audio files
        longer than this will be truncated to `output_sequence_length`. If set
        to `None`, then all sequences in the same batch will be padded to the
        length of the longest sequence in the batch.
      ragged: Whether to return a Ragged dataset (where each sequence has its
        own length). Default: False.
      shuffle: Whether to shuffle the data. Default: True. If set to False,
        sorts the data in alphanumeric order.
      seed: Optional random seed for shuffling and transformations.
      validation_split: Optional float between 0 and 1, fraction of data to
        reserve for validation.
      subset: Subset of the data to return. One of "training", "validation" or
        "both". Only used if `validation_split` is set.
      follow_links: Whether to visits subdirectories pointed to by symlinks.
        Defaults to False.

    Returns:
      A `tf.data.Dataset` object.
        - If `label_mode` is None, it yields `string` tensors of shape
          `(batch_size,)`, containing the contents of a batch of audio files.
        - Otherwise, it yields a tuple `(audio, labels)`, where `audio`
          has shape `(batch_size, sequence_length, num_channels)` and `labels`
          follows the format described
          below.

    Rules regarding labels format:
      - if `label_mode` is `int`, the labels are an `int32` tensor of shape
        `(batch_size,)`.
      - if `label_mode` is `binary`, the labels are a `float32` tensor of
        1s and 0s of shape `(batch_size, 1)`.
      - if `label_mode` is `categorical`, the labels are a `float32` tensor
        of shape `(batch_size, num_classes)`, representing a one-hot
        encoding of the class index.
    )r   Naf  The `labels` argument should be a list/tuple of integer labels, of the same size as the number of audio files in the target directory. If you wish to infer the labels from the subdirectory names in the target directory, pass `labels="inferred"`. If you wish to get a dataset that only contains audio samples (no labels), pass `labels=None`. Received: labels=zIYou can only pass `class_names` if `labels="inferred"`. Received: labels=z, and class_names=>   categoricalNr   binaryzc`label_mode` argument must be one of "int", "categorical", "binary", or None. Received: label_mode=Nz5Cannot set both `ragged` and `output_sequence_length`zF`sampling_rate` should have an integer value. Received: sampling_rate=r   zA`sampling_rate` should be higher than 0. Received: sampling_rate=zzTo use the argument `sampling_rate`, you should install tensorflow_io. You can install it via `pip install tensorflow-io`.g    .A)formatsclass_namesshuffleseedfollow_linksr	      z_When passing `label_mode="binary"`, there must be exactly 2 class_names. Received: class_names=both)	
file_pathslabelsvalidation_split	directory
label_moder   sampling_rateoutput_sequence_lengthraggeddataset
batch_sizer   r   r   r   r   F)
r   r   r   r   subsetr   r   r   r   r   )
isinstancelisttuple
ValueErrorr   tfioImportErrorr   Zcheck_validation_split_argnprandomrandintZindex_directoryALLOWED_FORMATSlen#get_training_and_validation_datasetprepare_datasetget_dataset)r   r   r   r   r   r   r   r   r   r   r   r   r   r   train_datasetval_datasetr    r-   U/var/www/html/django/DPS/env/lib/python3.9/site-packages/keras/utils/audio_dataset.pyaudio_dataset_from_directory"   s    _	



			r/   c                 C   sx   |  tjj} |d ur\|r,| j|d |d} |d u rP|sP| j|d d gg fd} qn| |} n|rn| jd|d} || _| S )N   )buffer_sizer   )padded_shapesi   )prefetchtfdataAUTOTUNEr   padded_batchbatchr   r   r-   r-   r.   r)     s    	r)   c	              	   C   s   t | ||d\}	}
|	s,td| dt t | ||d\}}|sXtd| dt t|	|
|t||||d}t|||t||||d}||fS )Ntrainingz+No training audio files found in directory . Allowed format(s): 
validationz-No validation audio files found in directory r   r   r   num_classesr   r   r   r   Z get_training_or_validation_splitr    r&   paths_and_labels_to_datasetr'   )r   r   r   r   r   r   r   r   r   Zfile_paths_trainZlabels_trainZfile_paths_valZ
labels_valr+   r,   r-   r-   r.   r(   %  sP    

r(   c
              	   C   sJ   t | |||\} }| s,td| dt t| ||t||||	d}
|
S )Nz"No audio files found in directory r:   r<   r>   )r   r   r   r   r   r   r   r   r   r   r   r-   r-   r.   r*   \  s&    
r*   c                 C   sX   t j| }|du rd}t jj||d\}}|durTt |t j}tjj|||d}|S )zReads and decodes audio file.N)contentsdesired_samples)inputZrate_inZrate_out)	r4   io	read_fileaudio
decode_wavcastint64r!   Zresample)pathr   r   rF   Zdefault_audio_rater-   r-   r.   read_and_decode_audio~  s    
rK   c           
         sl   t jj| }|j fddt jjd}|rD|jdd t jjd}|rht|||}	t jj||	f}|S )z4Constructs a fixed-size dataset of audio and labels.c                    s   t |  S N)rK   xr   r   r-   r.   <lambda>  s   z-paths_and_labels_to_dataset.<locals>.<lambda>)num_parallel_callsc                 S   s   t j| S rL   )r4   RaggedTensorfrom_tensorrM   r-   r-   r.   rP         )	r4   r5   Datasetfrom_tensor_slicesmapr6   r   Zlabels_to_datasetzip)
r   r   r   r=   r   r   r   Zpath_dsZaudio_dsZlabel_dsr-   rO   r.   r?     s     
r?   )r   r   Nr   NNFTNNNF)NN)__doc__numpyr#   tensorflow.compat.v2compatv2r4   keras.utilsr    tensorflow.python.util.tf_exportr   Ztensorflow_ior!   r"   r&   r/   r)   r(   r*   rK   r?   r-   r-   r-   r.   <module>   s<   

             f7# 
