a Sic8@svdZddlZddlmmZddlmZddlm Z ddl m Z dZ e ddgd dddZ dddZdddZdS)z&Keras image dataset loading utilities.N) dataset_utils) image_utils) keras_export)z.bmpz.gifz.jpegz.jpgz.pngz(keras.utils.image_dataset_from_directoryz0keras.preprocessing.image_dataset_from_directory)v1inferredintrgb r TbilinearFc Ksd|vr|d} |r,tdt||dvrht|ttfsPtd||rhtd|d||dvr~td||d us|d urd }d }|d krd }n*|d krd }n|dkrd}ntd|t| } t | | |||d urt j d}t j||t|||| d\}}}|dkr@t|dkr@td|| dkrht ||| d\}}t ||| d\}}|std|dt|std|dtt|||||t|| | d}t|||||t|| | d}|tjj}|tjj}|d ur2|r|j|d|d}||}||}n|rF|jd|d}||_||_||_||_||g}nt ||| | \}}|std |dtt|||||t|| | d}|tjj}|d ur|r|j|d|d}||}n|r|jd|d}||_||_|S)!aGenerates 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, 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". Default: "rgb". Whether the images will be converted to have 1, 3, or 4 channels. batch_size: Size of the batches of data. Default: 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)`. Defaults to `(256, 256)`. Since the pipeline processes batches of images that must all have the same size, this must be provided. 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. 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. Defaults to `bilinear`. Supports `bilinear`, `nearest`, `bicubic`, `area`, `lanczos3`, `lanczos5`, `gaussian`, `mitchellcubic`. 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. **kwargs: Legacy keyword arguments. 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. smart_resizezUnknown keywords argument(s): )rNa[`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=> categoricalNrbinaryzc`label_mode` argument must be one of "int", "categorical", "binary", or None. Received: label_mode=NrrgbaZ grayscalezO`color_mode` must be one of {"rgb", "rgba", "grayscale"}. Received: color_mode=g.A)formats class_namesshuffleseed follow_linksrz_When passing `label_mode="binary"`, there must be exactly 2 class_names. Received: class_names=bothtraining validationz&No training images found in directory z. Allowed formats: z(No validation images found in directory ) image_paths image_size num_channelslabels label_mode num_classes interpolationcrop_to_aspect_ratio) buffer_sizerizNo images found in directory )pop TypeErrortuplekeys isinstancelist ValueErrorrZget_interpolationrcheck_validation_split_argnprandomrandintindex_directoryALLOWLIST_FORMATSlen get_training_or_validation_splitpaths_and_labels_to_datasetprefetchtfdataAUTOTUNErbatchr file_paths) directoryr r!rZ color_mode batch_sizerrrvalidation_splitsubsetr#rr$kwargsrrZimage_paths_train labels_trainZimage_paths_val labels_val train_dataset val_datasetdatasetrGU/var/www/html/django/DPS/env/lib/python3.9/site-packages/keras/utils/image_dataset.pyimage_dataset_from_directorys2               rIc s\tjj|}||||f|jfddtjjd} |rXt|||} tjj| | f} | S)z*Constructs a dataset of images and labels.cst|gRS)N) load_image)xargsrGrHUz-paths_and_labels_to_dataset..)num_parallel_calls) r8r9Datasetfrom_tensor_slicesmapr:rlabels_to_datasetzip) rrrr r!r"r#r$path_dsZimg_dslabel_dsrGrLrHr6Fs  r6cCsbtj|}tjj||dd}|r4tj|||d}ntjj|||d}||d|d|f|S)z(Load an image from a path and resize it.F)channelsexpand_animations)r#)methodrr) r8io read_fileimage decode_imagerr resize set_shape)pathrrr#r$imgrGrGrHrJ_s rJ) rrNrr r TNNNr FF)F)F)__doc__numpyr/tensorflow.compat.v2compatv2r8 keras.utilsrr tensorflow.python.util.tf_exportrr3rIr6rJrGrGrGrHs>    -