2Vh ;ddlZddlmZddlmZddlmZddlm Z dZ ed ddZ d Z dd Z dd Z dd Z dd Zy)N) keras_export) dataset_utils) tensorflow) tensorflow_io)z.wavz(keras.utils.audio_dataset_from_directorycR|dvr7t|ttfstd||rtd|d||dvrtd||r | td|Lt|tstd ||d krtd |t j s td ||d}d}tj| | || | tjjd } ||dz}nd}tj||t||| | | \}}}|dk(rt|dk7rtd|| dk(r>t!||| |||||||||  \}}t#|||||}t#|||||}||fSt%|||| | ||||||||  }t#|||||}|S)aGenerates 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). Defaults to `False`. shuffle: Whether to shuffle the data. If set to `False`, sorts the data in alphanumeric order. Defaults to `True`. 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`. verbose: Whether to display number information on classes and number of files found. Defaults to `True`. 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. )inferredNafThe `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=>Nintbinary categoricalzc`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=rzA`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_namesshuffleseed follow_linksverboser z_When passing `label_mode="binary"`, there must be exactly 2 class_names. Received: class_names=both) file_pathslabelsvalidation_split directory label_moder sampling_rateoutput_sequence_lengthraggedrshuffle_buffer_sizerdataset batch_sizerrr rrrrsubsetrrrrrrrr) isinstancelisttuple ValueErrorr tfio available ImportErrorrcheck_validation_split_argnprandomrandintindex_directoryALLOWED_FORMATSlen#get_training_and_validation_datasetprepare_dataset get_dataset)rrrrr!rrrrrrr#rrrr train_dataset val_datasetr s S/home/dcms/DCMS/lib/python3.12/site-packages/keras/src/utils/audio_dataset_utils.pyaudio_dataset_from_directoryr8 sX''&4-0E FLH N  99?A*m-  ?? --7L :  (4 C   --++8/;  A ++8/;  ~~"  ~+ ,,&'4 |yy  %(1n"&3&C&C ! '#J X#k"2a"7 22= @  %H!-!#'#9 3 & " {(!!##9  &!##9  k))!-!#'#9 3 "!##9  c|jtjj}|-||s|j |ddggf}n|j |}||_|S)N) padded_shapes)prefetchtfdataAUTOTUNE padded_batchbatchrrs r7r3r3snrww//0G ! )&**D$<*<+GmmJ/G&G Nr9c Vtj|||d\} } | std|dttj|||d\}}|std|dtt | | ||r t |nd|||| | |  }t ||||r t |nd|||d }||fS) Ntrainingz+No training audio files found in directory . Allowed format(s): validationz-No validation audio files found in directory r rrr num_classesrrrrrrF)rrrrGrrrrr get_training_or_validation_splitr'r0paths_and_labels_to_datasetr1)rrrrrrrrrrrrfile_paths_train labels_trainfile_paths_val labels_valr5r6s r7r2r2s " 66F,j  9)E""1!2 4  "/!O!OF,l"NJ ;I;G""1!2 4  0#(3C $#5/  M.!(3C $#5 K + %%r9c tj||||\}}|std|dtt ||||r t |nd||| | | |  S)Nz"No audio files found in directory rDrrFrHr"s r7r4r4Ts'GGF,fJ 0 <""1!2 4  '(3C $#5/   r9c$tjj|}|d}tjj ||\}}|Ftj |tj }tjj|||}|S)zReads and decodes audio file.)contentsdesired_samples)inputrate_inrate_out) r=io read_fileaudio decode_wavcastint64r(resample)pathrrrYdefault_audio_rates r7read_and_decode_audior`zs EEOOD !E%!# " 3 3(>!4!E  WW%7B ##!3m$  Lr9c tjjj|} |rCt j |||} tjjj | | f} n| } |r| j|xsd| } |r_| jfdtjj} |r,| jdtjj} | S| jfdtjj} |r,| jdtjj} | S)z4Constructs a fixed-size dataset of audio and labels.r ) buffer_sizerc"t||fSNr`)xyrrs r7z-paths_and_labels_to_dataset..s%a8NOr9)num_parallel_callscDtjj||fSrdr= RaggedTensor from_tensor)rfrgs r7rhz-paths_and_labels_to_dataset..sboo99!.s+="8r9c@tjj|Srdrk)rfs r7rhz-paths_and_labels_to_dataset..s"//55a8r9) r=r>Datasetfrom_tensor_slicesrlabels_to_datasetziprmapr?) rrrrGrrrrrrpath_dslabel_dsdss `` r7rJrJs'ggoo00r~s-)9>89      r:rj>  ;&R  #N6::  6r9