2VhDBddlZddlmZddlmZddlmZddlmZddl m Z dZ edd g d d Z dd Z dd Zy)N) keras_export)standardize_data_format) dataset_utils) image_utils tensorflow)z.bmpz.gifz.jpegz.jpgz.pngz(keras.utils.image_dataset_from_directoryz0keras.preprocessing.image_dataset_from_directoryc|dvr7t|ttfstd||rtd|d||dvrtd|||d}d}|dk(rd }n|d k(rd }n|d k(rd }ntd|t|tr||f}n2t|ttfrt |dk(std|| j } d}| |vrtd|d| tj| | |||tjjd}tj||t|||| |\}}}|dk(rt |dk7rtd|t|}||dz}nd}| dk(rDtj||| d\}}tj||| d\}}|std|dt|std |dtt!||||||r t |nd!| | |||||" }t!||||||r t |nd!| | ||d#$ }|"|j#|}|j#|}|j%t&j(j*}|j%t&j(j*}||_||_||_||_||g}|Stj||| | \}}|std%|dtt!||||||r t |nd!| | |||||" }||j#|}|j%t&j(j*}||_||_|S)&ahGenerates a `tf.data.Dataset` from image files in a directory. If your directory structure is: ``` main_directory/ ...class_a/ ......a_image_1.jpg ......a_image_2.jpg ...class_b/ ......b_image_1.jpg ......b_image_2.jpg ``` Then calling `image_dataset_from_directory(main_directory, labels='inferred')` will return a `tf.data.Dataset` that yields batches of images 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`). Supported image formats: `.jpeg`, `.jpg`, `.png`, `.bmp`, `.gif`. Animated gifs are truncated to the first frame. Args: directory: Directory where the data is located. If `labels` is `"inferred"`, it should contain subdirectories, each containing images 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 image files found in the directory. Labels should be sorted according to the alphanumeric order of the image 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). color_mode: One of `"grayscale"`, `"rgb"`, `"rgba"`. Whether the images will be converted to have 1, 3, or 4 channels. Defaults to `"rgb"`. batch_size: Size of the batches of data. Defaults to 32. If `None`, the data will not be batched (the dataset will yield individual samples). image_size: Size to resize images to after they are read from disk, specified as `(height, width)`. Since the pipeline processes batches of images that must all have the same size, this must be provided. Defaults to `(256, 256)`. shuffle: Whether to shuffle the data. Defaults to `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. When `subset="both"`, the utility returns a tuple of two datasets (the training and validation datasets respectively). interpolation: String, the interpolation method used when resizing images. Supports `"bilinear"`, `"nearest"`, `"bicubic"`, `"area"`, `"lanczos3"`, `"lanczos5"`, `"gaussian"`, `"mitchellcubic"`. Defaults to `"bilinear"`. follow_links: Whether to visit subdirectories pointed to by symlinks. Defaults to `False`. crop_to_aspect_ratio: If `True`, resize the images without aspect ratio distortion. When the original aspect ratio differs from the target aspect ratio, the output image will be cropped so as to return the largest possible window in the image (of size `image_size`) that matches the target aspect ratio. By default (`crop_to_aspect_ratio=False`), aspect ratio may not be preserved. pad_to_aspect_ratio: If `True`, resize the images without aspect ratio distortion. When the original aspect ratio differs from the target aspect ratio, the output image will be padded so as to return the largest possible window in the image (of size `image_size`) that matches the target aspect ratio. By default (`pad_to_aspect_ratio=False`), aspect ratio may not be preserved. data_format: If None uses keras.config.image_data_format() otherwise either 'channel_last' or 'channel_first'. 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 `float32` tensors of shape `(batch_size, image_size[0], image_size[1], num_channels)`, encoding images (see below for rules regarding `num_channels`). - Otherwise, it yields a tuple `(images, labels)`, where `images` has shape `(batch_size, image_size[0], image_size[1], 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. Rules regarding number of channels in the yielded images: - if `color_mode` is `"grayscale"`, there's 1 channel in the image tensors. - if `color_mode` is `"rgb"`, there are 3 channels in the image tensors. - if `color_mode` is `"rgba"`, there are 4 channels in the image tensors. )inferredNa[`labels` argument should be a list/tuple of integer labels, of the same size as the number of image 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 images (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=Nrgbrgba grayscalezO`color_mode` must be one of {"rgb", "rgba", "grayscale"}. Received: color_mode=zQInvalid `image_size` value. Expected a tuple of 2 integers. Received: image_size=)bilinearnearestbicubicarealanczos3lanczos5gaussian mitchellcubicz*Argument `interpolation` should be one of z. Received: interpolation=g.A)formats class_namesshuffleseed follow_linksverboser z_When passing `label_mode="binary"`, there must be exactly 2 class_names. Received: class_names=) data_formatbothtraining validationz&No training images found in directory z. Allowed formats: z(No validation images found in directory r) image_paths image_size num_channelslabels label_mode num_classes interpolationcrop_to_aspect_ratiopad_to_aspect_ratior#rshuffle_buffer_sizer F) r)r*r+r,r-r.r/r0r1r#rzNo images found in directory ) isinstancelisttuple ValueErrorr lenlowerrcheck_validation_split_argnprandomrandintindex_directoryALLOWLIST_FORMATSr get_training_or_validation_splitpaths_and_labels_to_datasetbatchprefetchtfdataAUTOTUNEr file_paths) directoryr,r-r color_mode batch_sizer*rr validation_splitsubsetr/r!r0r1r#r"r+supported_interpolationsr)r2image_paths_train labels_trainimage_paths_val labels_val train_dataset val_datasetdatasets S/home/dcms/DCMS/lib/python3.12/site-packages/keras/src/utils/image_dataset_utils.pyimage_dataset_from_directoryrU sl''&4-0E FLH N  99?A*m-  ?? --7L :  ~+ U v  { "  $$.< 1  *c" *-  T5M 2#j/Q:N $$.< 1  "'')M 44 8'()''4o 7  ,,&'4 |yy  %'4'D'D! ! ($KX#k"2a"7 22= @  *kBK(1n"   : : !1:     : : !1<   !8 D$$5#68 :9+F$$5#68 4)!%!,7K(Q'!5 3# 3 2'!%!,7K(Q'!5 3#    !)// ;M%++J7K%..rww/?/?@ !**277+;+;< %0 !"- $5  !0  +.J NG,LL !16  V/ {;$$5#68  .#!%!,7K(Q'!5 3# 3   !mmJ/G""277#3#34)) Nc tjjj|} |rCt j |||}tjjj | |f}n| }| r|j| xsd| }|||||| f|r0|jfdtjj}|S|jfdtjj}|S)z*Constructs a dataset of images and labels.r%) buffer_sizer c t|g|fSN load_image)xyargss rTz-paths_and_labels_to_dataset..s*Q..2rV)num_parallel_callsct|gSrZr[)r]r_s rTr`z-paths_and_labels_to_dataset..sj*T*rV) rCrDDatasetfrom_tensor_slicesrlabels_to_datasetziprmaprE)r)r*r+r,r-r.r/r#r0r1rr2r path_dslabel_dsdsr_s @rTr@r@ks ggoo00=G 22 J  WW__ '8!4 5  ZZ$7$?4dZ K   D VV 2!ww//  IVV *rww?O?O  IrVctjj|}tjj ||d}|r |r t d|r * *,,sI.C&&  '#%   hh&& A 1 m'  * *,,sI.Chhooc:moD * *,,sI.Co% z!}jm\BC J |Z]JqMBC JrV)r r Nr )rTNNNrFFFNT)FFFNN)FF)numpyr:keras.src.api_exportrkeras.src.backend.configrkeras.src.utilsrrkeras.src.utils.module_utilsrrCr>rUr@r\rVrTrs-<)'9=2:     #V  VD   -l0rV