Keras_Preprocessing-1.0.5/0000755000000000116100000000000013353522261015224 5ustar rooteng00000000000000Keras_Preprocessing-1.0.5/PKG-INFO0000644000000000116100000000302713353522261016323 0ustar rooteng00000000000000Metadata-Version: 2.1 Name: Keras_Preprocessing Version: 1.0.5 Summary: Easy data preprocessing and data augmentation for deep learning models Home-page: https://github.com/keras-team/keras-preprocessing Author: Keras Team License: MIT Download-URL: https://github.com/keras-team/keras-preprocessing/tarball/1.0.5 Description: Keras Preprocessing is the data preprocessing and data augmentation module of the Keras deep learning library. It provides utilities for working with image data, text data, and sequence data. Read the documentation at: https://keras.io/ Keras Preprocessing may be imported directly from an up-to-date installation of Keras: ``` from keras import preprocessing ``` Keras Preprocessing is compatible with Python 2.7-3.6 and is distributed under the MIT license. Platform: UNKNOWN Classifier: Development Status :: 5 - Production/Stable Classifier: Intended Audience :: Developers Classifier: Intended Audience :: Education Classifier: Intended Audience :: Science/Research Classifier: License :: OSI Approved :: MIT License Classifier: Programming Language :: Python :: 2 Classifier: Programming Language :: Python :: 2.7 Classifier: Programming Language :: Python :: 3 Classifier: Programming Language :: Python :: 3.6 Classifier: Topic :: Software Development :: Libraries Classifier: Topic :: Software Development :: Libraries :: Python Modules Provides-Extra: tests Provides-Extra: image Keras_Preprocessing-1.0.5/keras_preprocessing/0000755000000000116100000000000013353522261021274 5ustar rooteng00000000000000Keras_Preprocessing-1.0.5/keras_preprocessing/sequence.py0000644000000000116100000004127513353510160023462 0ustar rooteng00000000000000# -*- coding: utf-8 -*- """Utilities for preprocessing sequence data. """ from __future__ import absolute_import from __future__ import division from __future__ import print_function import numpy as np import random import json from six.moves import range import six def pad_sequences(sequences, maxlen=None, dtype='int32', padding='pre', truncating='pre', value=0.): """Pads sequences to the same length. This function transforms a list of `num_samples` sequences (lists of integers) into a 2D Numpy array of shape `(num_samples, num_timesteps)`. `num_timesteps` is either the `maxlen` argument if provided, or the length of the longest sequence otherwise. Sequences that are shorter than `num_timesteps` are padded with `value` at the end. Sequences longer than `num_timesteps` are truncated so that they fit the desired length. The position where padding or truncation happens is determined by the arguments `padding` and `truncating`, respectively. Pre-padding is the default. # Arguments sequences: List of lists, where each element is a sequence. maxlen: Int, maximum length of all sequences. dtype: Type of the output sequences. To pad sequences with variable length strings, you can use `object`. padding: String, 'pre' or 'post': pad either before or after each sequence. truncating: String, 'pre' or 'post': remove values from sequences larger than `maxlen`, either at the beginning or at the end of the sequences. value: Float or String, padding value. # Returns x: Numpy array with shape `(len(sequences), maxlen)` # Raises ValueError: In case of invalid values for `truncating` or `padding`, or in case of invalid shape for a `sequences` entry. """ if not hasattr(sequences, '__len__'): raise ValueError('`sequences` must be iterable.') lengths = [] for x in sequences: if not hasattr(x, '__len__'): raise ValueError('`sequences` must be a list of iterables. ' 'Found non-iterable: ' + str(x)) lengths.append(len(x)) num_samples = len(sequences) if maxlen is None: maxlen = np.max(lengths) # take the sample shape from the first non empty sequence # checking for consistency in the main loop below. sample_shape = tuple() for s in sequences: if len(s) > 0: sample_shape = np.asarray(s).shape[1:] break is_dtype_str = np.issubdtype(dtype, np.str_) or np.issubdtype(dtype, np.unicode_) if isinstance(value, six.string_types) and dtype != object and not is_dtype_str: raise ValueError("`dtype` {} is not compatible with `value`'s type: {}\n" "You should set `dtype=object` for variable length strings." .format(dtype, type(value))) x = np.full((num_samples, maxlen) + sample_shape, value, dtype=dtype) for idx, s in enumerate(sequences): if not len(s): continue # empty list/array was found if truncating == 'pre': trunc = s[-maxlen:] elif truncating == 'post': trunc = s[:maxlen] else: raise ValueError('Truncating type "%s" ' 'not understood' % truncating) # check `trunc` has expected shape trunc = np.asarray(trunc, dtype=dtype) if trunc.shape[1:] != sample_shape: raise ValueError('Shape of sample %s of sequence at position %s ' 'is different from expected shape %s' % (trunc.shape[1:], idx, sample_shape)) if padding == 'post': x[idx, :len(trunc)] = trunc elif padding == 'pre': x[idx, -len(trunc):] = trunc else: raise ValueError('Padding type "%s" not understood' % padding) return x def make_sampling_table(size, sampling_factor=1e-5): """Generates a word rank-based probabilistic sampling table. Used for generating the `sampling_table` argument for `skipgrams`. `sampling_table[i]` is the probability of sampling the word i-th most common word in a dataset (more common words should be sampled less frequently, for balance). The sampling probabilities are generated according to the sampling distribution used in word2vec: ``` p(word) = (min(1, sqrt(word_frequency / sampling_factor) / (word_frequency / sampling_factor))) ``` We assume that the word frequencies follow Zipf's law (s=1) to derive a numerical approximation of frequency(rank): `frequency(rank) ~ 1/(rank * (log(rank) + gamma) + 1/2 - 1/(12*rank))` where `gamma` is the Euler-Mascheroni constant. # Arguments size: Int, number of possible words to sample. sampling_factor: The sampling factor in the word2vec formula. # Returns A 1D Numpy array of length `size` where the ith entry is the probability that a word of rank i should be sampled. """ gamma = 0.577 rank = np.arange(size) rank[0] = 1 inv_fq = rank * (np.log(rank) + gamma) + 0.5 - 1. / (12. * rank) f = sampling_factor * inv_fq return np.minimum(1., f / np.sqrt(f)) def skipgrams(sequence, vocabulary_size, window_size=4, negative_samples=1., shuffle=True, categorical=False, sampling_table=None, seed=None): """Generates skipgram word pairs. This function transforms a sequence of word indexes (list of integers) into tuples of words of the form: - (word, word in the same window), with label 1 (positive samples). - (word, random word from the vocabulary), with label 0 (negative samples). Read more about Skipgram in this gnomic paper by Mikolov et al.: [Efficient Estimation of Word Representations in Vector Space](http://arxiv.org/pdf/1301.3781v3.pdf) # Arguments sequence: A word sequence (sentence), encoded as a list of word indices (integers). If using a `sampling_table`, word indices are expected to match the rank of the words in a reference dataset (e.g. 10 would encode the 10-th most frequently occurring token). Note that index 0 is expected to be a non-word and will be skipped. vocabulary_size: Int, maximum possible word index + 1 window_size: Int, size of sampling windows (technically half-window). The window of a word `w_i` will be `[i - window_size, i + window_size+1]`. negative_samples: Float >= 0. 0 for no negative (i.e. random) samples. 1 for same number as positive samples. shuffle: Whether to shuffle the word couples before returning them. categorical: bool. if False, labels will be integers (eg. `[0, 1, 1 .. ]`), if `True`, labels will be categorical, e.g. `[[1,0],[0,1],[0,1] .. ]`. sampling_table: 1D array of size `vocabulary_size` where the entry i encodes the probability to sample a word of rank i. seed: Random seed. # Returns couples, labels: where `couples` are int pairs and `labels` are either 0 or 1. # Note By convention, index 0 in the vocabulary is a non-word and will be skipped. """ couples = [] labels = [] for i, wi in enumerate(sequence): if not wi: continue if sampling_table is not None: if sampling_table[wi] < random.random(): continue window_start = max(0, i - window_size) window_end = min(len(sequence), i + window_size + 1) for j in range(window_start, window_end): if j != i: wj = sequence[j] if not wj: continue couples.append([wi, wj]) if categorical: labels.append([0, 1]) else: labels.append(1) if negative_samples > 0: num_negative_samples = int(len(labels) * negative_samples) words = [c[0] for c in couples] random.shuffle(words) couples += [[words[i % len(words)], random.randint(1, vocabulary_size - 1)] for i in range(num_negative_samples)] if categorical: labels += [[1, 0]] * num_negative_samples else: labels += [0] * num_negative_samples if shuffle: if seed is None: seed = random.randint(0, 10e6) random.seed(seed) random.shuffle(couples) random.seed(seed) random.shuffle(labels) return couples, labels def _remove_long_seq(maxlen, seq, label): """Removes sequences that exceed the maximum length. # Arguments maxlen: Int, maximum length of the output sequences. seq: List of lists, where each sublist is a sequence. label: List where each element is an integer. # Returns new_seq, new_label: shortened lists for `seq` and `label`. """ new_seq, new_label = [], [] for x, y in zip(seq, label): if len(x) < maxlen: new_seq.append(x) new_label.append(y) return new_seq, new_label class TimeseriesGenerator(object): """Utility class for generating batches of temporal data. This class takes in a sequence of data-points gathered at equal intervals, along with time series parameters such as stride, length of history, etc., to produce batches for training/validation. # Arguments data: Indexable generator (such as list or Numpy array) containing consecutive data points (timesteps). The data should be at 2D, and axis 0 is expected to be the time dimension. targets: Targets corresponding to timesteps in `data`. It should have same length as `data`. length: Length of the output sequences (in number of timesteps). sampling_rate: Period between successive individual timesteps within sequences. For rate `r`, timesteps `data[i]`, `data[i-r]`, ... `data[i - length]` are used for create a sample sequence. stride: Period between successive output sequences. For stride `s`, consecutive output samples would be centered around `data[i]`, `data[i+s]`, `data[i+2*s]`, etc. start_index: Data points earlier than `start_index` will not be used in the output sequences. This is useful to reserve part of the data for test or validation. end_index: Data points later than `end_index` will not be used in the output sequences. This is useful to reserve part of the data for test or validation. shuffle: Whether to shuffle output samples, or instead draw them in chronological order. reverse: Boolean: if `true`, timesteps in each output sample will be in reverse chronological order. batch_size: Number of timeseries samples in each batch (except maybe the last one). # Returns A [Sequence](/utils/#sequence) instance. # Examples ```python from keras.preprocessing.sequence import TimeseriesGenerator import numpy as np data = np.array([[i] for i in range(50)]) targets = np.array([[i] for i in range(50)]) data_gen = TimeseriesGenerator(data, targets, length=10, sampling_rate=2, batch_size=2) assert len(data_gen) == 20 batch_0 = data_gen[0] x, y = batch_0 assert np.array_equal(x, np.array([[[0], [2], [4], [6], [8]], [[1], [3], [5], [7], [9]]])) assert np.array_equal(y, np.array([[10], [11]])) ``` """ def __init__(self, data, targets, length, sampling_rate=1, stride=1, start_index=0, end_index=None, shuffle=False, reverse=False, batch_size=128): if len(data) != len(targets): raise ValueError('Data and targets have to be' + ' of same length. ' 'Data length is {}'.format(len(data)) + ' while target length is {}'.format(len(targets))) self.data = data self.targets = targets self.length = length self.sampling_rate = sampling_rate self.stride = stride self.start_index = start_index + length if end_index is None: end_index = len(data) - 1 self.end_index = end_index self.shuffle = shuffle self.reverse = reverse self.batch_size = batch_size if self.start_index > self.end_index: raise ValueError('`start_index+length=%i > end_index=%i` ' 'is disallowed, as no part of the sequence ' 'would be left to be used as current step.' % (self.start_index, self.end_index)) def __len__(self): return (self.end_index - self.start_index + self.batch_size * self.stride) // (self.batch_size * self.stride) def _empty_batch(self, num_rows): samples_shape = [num_rows, self.length // self.sampling_rate] samples_shape.extend(self.data.shape[1:]) targets_shape = [num_rows] targets_shape.extend(self.targets.shape[1:]) return np.empty(samples_shape), np.empty(targets_shape) def __getitem__(self, index): if self.shuffle: rows = np.random.randint( self.start_index, self.end_index + 1, size=self.batch_size) else: i = self.start_index + self.batch_size * self.stride * index rows = np.arange(i, min(i + self.batch_size * self.stride, self.end_index + 1), self.stride) samples, targets = self._empty_batch(len(rows)) for j, row in enumerate(rows): indices = range(rows[j] - self.length, rows[j], self.sampling_rate) samples[j] = self.data[indices] targets[j] = self.targets[rows[j]] if self.reverse: return samples[:, ::-1, ...], targets return samples, targets def get_config(self): '''Returns the TimeseriesGenerator configuration as Python dictionary. # Returns A Python dictionary with the TimeseriesGenerator configuration. ''' data = self.data if type(self.data).__module__ == np.__name__: data = self.data.tolist() try: json_data = json.dumps(data) except: raise TypeError('Data not JSON Serializable:', data) targets = self.targets if type(self.targets).__module__ == np.__name__: targets = self.targets.tolist() try: json_targets = json.dumps(targets) except: raise TypeError('Targets not JSON Serializable:', targets) return { 'data': json_data, 'targets': json_targets, 'length': self.length, 'sampling_rate': self.sampling_rate, 'stride': self.stride, 'start_index': self.start_index, 'end_index': self.end_index, 'shuffle': self.shuffle, 'reverse': self.reverse, 'batch_size': self.batch_size } def to_json(self, **kwargs): """Returns a JSON string containing the timeseries generator configuration. To load a generator from a JSON string, use `keras.preprocessing.sequence.timeseries_generator_from_json(json_string)`. # Arguments **kwargs: Additional keyword arguments to be passed to `json.dumps()`. # Returns A JSON string containing the tokenizer configuration. """ config = self.get_config() timeseries_generator_config = { 'class_name': self.__class__.__name__, 'config': config } return json.dumps(timeseries_generator_config, **kwargs) def timeseries_generator_from_json(json_string): """Parses a JSON timeseries generator configuration file and returns a timeseries generator instance. # Arguments json_string: JSON string encoding a timeseries generator configuration. # Returns A Keras TimeseriesGenerator instance """ full_config = json.loads(json_string) config = full_config.get('config') data = json.loads(config.pop('data')) config['data'] = data targets = json.loads(config.pop('targets')) config['targets'] = targets return TimeseriesGenerator(**config) Keras_Preprocessing-1.0.5/keras_preprocessing/__init__.py0000644000000000116100000000255713353522226023417 0ustar rooteng00000000000000"""Enables dynamic setting of underlying Keras module. """ from __future__ import absolute_import from __future__ import division from __future__ import print_function _KERAS_BACKEND = None _KERAS_UTILS = None def set_keras_submodules(backend, utils): # Deprecated, will be removed in the future. global _KERAS_BACKEND global _KERAS_UTILS _KERAS_BACKEND = backend _KERAS_UTILS = utils def get_keras_submodule(name): # Deprecated, will be removed in the future. if name not in {'backend', 'utils'}: raise ImportError( 'Can only retrieve "backend" and "utils". ' 'Requested: %s' % name) if _KERAS_BACKEND is None: raise ImportError('You need to first `import keras` ' 'in order to use `keras_preprocessing`. ' 'For instance, you can do:\n\n' '```\n' 'import keras\n' 'from keras_preprocessing import image\n' '```\n\n' 'Or, preferably, this equivalent formulation:\n\n' '```\n' 'from keras import preprocessing\n' '```\n') if name == 'backend': return _KERAS_BACKEND elif name == 'utils': return _KERAS_UTILS __version__ = '1.0.5' Keras_Preprocessing-1.0.5/keras_preprocessing/text.py0000644000000000116100000004510213353522226022635 0ustar rooteng00000000000000# -*- coding: utf-8 -*- """Utilities for text input preprocessing. """ from __future__ import absolute_import from __future__ import division from __future__ import print_function import string import sys import warnings from collections import OrderedDict from collections import defaultdict from hashlib import md5 import json import numpy as np from six.moves import range from six.moves import zip if sys.version_info < (3,): maketrans = string.maketrans else: maketrans = str.maketrans def text_to_word_sequence(text, filters='!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n', lower=True, split=" "): """Converts a text to a sequence of words (or tokens). # Arguments text: Input text (string). filters: list (or concatenation) of characters to filter out, such as punctuation. Default: ``!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n``, includes basic punctuation, tabs, and newlines. lower: boolean. Whether to convert the input to lowercase. split: str. Separator for word splitting. # Returns A list of words (or tokens). """ if lower: text = text.lower() if sys.version_info < (3,): if isinstance(text, unicode): translate_map = dict((ord(c), unicode(split)) for c in filters) text = text.translate(translate_map) elif len(split) == 1: translate_map = maketrans(filters, split * len(filters)) text = text.translate(translate_map) else: for c in filters: text = text.replace(c, split) else: translate_dict = dict((c, split) for c in filters) translate_map = maketrans(translate_dict) text = text.translate(translate_map) seq = text.split(split) return [i for i in seq if i] def one_hot(text, n, filters='!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n', lower=True, split=' '): """One-hot encodes a text into a list of word indexes of size n. This is a wrapper to the `hashing_trick` function using `hash` as the hashing function; unicity of word to index mapping non-guaranteed. # Arguments text: Input text (string). n: int. Size of vocabulary. filters: list (or concatenation) of characters to filter out, such as punctuation. Default: ``!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n``, includes basic punctuation, tabs, and newlines. lower: boolean. Whether to set the text to lowercase. split: str. Separator for word splitting. # Returns List of integers in [1, n]. Each integer encodes a word (unicity non-guaranteed). """ return hashing_trick(text, n, hash_function=hash, filters=filters, lower=lower, split=split) def hashing_trick(text, n, hash_function=None, filters='!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n', lower=True, split=' '): """Converts a text to a sequence of indexes in a fixed-size hashing space. # Arguments text: Input text (string). n: Dimension of the hashing space. hash_function: defaults to python `hash` function, can be 'md5' or any function that takes in input a string and returns a int. Note that 'hash' is not a stable hashing function, so it is not consistent across different runs, while 'md5' is a stable hashing function. filters: list (or concatenation) of characters to filter out, such as punctuation. Default: ``!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n``, includes basic punctuation, tabs, and newlines. lower: boolean. Whether to set the text to lowercase. split: str. Separator for word splitting. # Returns A list of integer word indices (unicity non-guaranteed). `0` is a reserved index that won't be assigned to any word. Two or more words may be assigned to the same index, due to possible collisions by the hashing function. The [probability]( https://en.wikipedia.org/wiki/Birthday_problem#Probability_table) of a collision is in relation to the dimension of the hashing space and the number of distinct objects. """ if hash_function is None: hash_function = hash elif hash_function == 'md5': hash_function = lambda w: int(md5(w.encode()).hexdigest(), 16) seq = text_to_word_sequence(text, filters=filters, lower=lower, split=split) return [(hash_function(w) % (n - 1) + 1) for w in seq] class Tokenizer(object): """Text tokenization utility class. This class allows to vectorize a text corpus, by turning each text into either a sequence of integers (each integer being the index of a token in a dictionary) or into a vector where the coefficient for each token could be binary, based on word count, based on tf-idf... # Arguments num_words: the maximum number of words to keep, based on word frequency. Only the most common `num_words` words will be kept. filters: a string where each element is a character that will be filtered from the texts. The default is all punctuation, plus tabs and line breaks, minus the `'` character. lower: boolean. Whether to convert the texts to lowercase. split: str. Separator for word splitting. char_level: if True, every character will be treated as a token. oov_token: if given, it will be added to word_index and used to replace out-of-vocabulary words during text_to_sequence calls By default, all punctuation is removed, turning the texts into space-separated sequences of words (words maybe include the `'` character). These sequences are then split into lists of tokens. They will then be indexed or vectorized. `0` is a reserved index that won't be assigned to any word. """ def __init__(self, num_words=None, filters='!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~\t\n', lower=True, split=' ', char_level=False, oov_token=None, document_count=0, **kwargs): # Legacy support if 'nb_words' in kwargs: warnings.warn('The `nb_words` argument in `Tokenizer` ' 'has been renamed `num_words`.') num_words = kwargs.pop('nb_words') if kwargs: raise TypeError('Unrecognized keyword arguments: ' + str(kwargs)) self.word_counts = OrderedDict() self.word_docs = defaultdict(int) self.filters = filters self.split = split self.lower = lower self.num_words = num_words self.document_count = document_count self.char_level = char_level self.oov_token = oov_token self.index_docs = defaultdict(int) self.word_index = dict() self.index_word = dict() def fit_on_texts(self, texts): """Updates internal vocabulary based on a list of texts. In the case where texts contains lists, we assume each entry of the lists to be a token. Required before using `texts_to_sequences` or `texts_to_matrix`. # Arguments texts: can be a list of strings, a generator of strings (for memory-efficiency), or a list of list of strings. """ for text in texts: self.document_count += 1 if self.char_level or isinstance(text, list): if self.lower: if isinstance(text, list): text = [text_elem.lower() for text_elem in text] else: text = text.lower() seq = text else: seq = text_to_word_sequence(text, self.filters, self.lower, self.split) for w in seq: if w in self.word_counts: self.word_counts[w] += 1 else: self.word_counts[w] = 1 for w in set(seq): # In how many documents each word occurs self.word_docs[w] += 1 wcounts = list(self.word_counts.items()) wcounts.sort(key=lambda x: x[1], reverse=True) # forcing the oov_token to index 1 if it exists if self.oov_token is None: sorted_voc = [] else: sorted_voc = [self.oov_token] sorted_voc.extend(wc[0] for wc in wcounts) # note that index 0 is reserved, never assigned to an existing word self.word_index = dict( list(zip(sorted_voc, list(range(1, len(sorted_voc) + 1))))) self.index_word = dict((c, w) for w, c in self.word_index.items()) for w, c in list(self.word_docs.items()): self.index_docs[self.word_index[w]] = c def fit_on_sequences(self, sequences): """Updates internal vocabulary based on a list of sequences. Required before using `sequences_to_matrix` (if `fit_on_texts` was never called). # Arguments sequences: A list of sequence. A "sequence" is a list of integer word indices. """ self.document_count += len(sequences) for seq in sequences: seq = set(seq) for i in seq: self.index_docs[i] += 1 def texts_to_sequences(self, texts): """Transforms each text in texts to a sequence of integers. Only top "num_words" most frequent words will be taken into account. Only words known by the tokenizer will be taken into account. # Arguments texts: A list of texts (strings). # Returns A list of sequences. """ return list(self.texts_to_sequences_generator(texts)) def texts_to_sequences_generator(self, texts): """Transforms each text in `texts` to a sequence of integers. Each item in texts can also be a list, in which case we assume each item of that list to be a token. Only top "num_words" most frequent words will be taken into account. Only words known by the tokenizer will be taken into account. # Arguments texts: A list of texts (strings). # Yields Yields individual sequences. """ num_words = self.num_words oov_token_index = self.word_index.get(self.oov_token) for text in texts: if self.char_level or isinstance(text, list): if self.lower: if isinstance(text, list): text = [text_elem.lower() for text_elem in text] else: text = text.lower() seq = text else: seq = text_to_word_sequence(text, self.filters, self.lower, self.split) vect = [] for w in seq: i = self.word_index.get(w) if i is not None: if num_words and i >= num_words: if oov_token_index is not None: vect.append(oov_token_index) else: vect.append(i) elif self.oov_token is not None: vect.append(oov_token_index) yield vect def sequences_to_texts(self, sequences): """Transforms each sequence into a list of text. Only top "num_words" most frequent words will be taken into account. Only words known by the tokenizer will be taken into account. # Arguments texts: A list of sequences (list of integers). # Returns A list of texts (strings) """ return list(self.sequences_to_texts_generator(sequences)) def sequences_to_texts_generator(self, sequences): """Transforms each sequence in `sequences` to a list of texts(strings). Each sequence has to a list of integers. In other words, sequences should be a list of sequences Only top "num_words" most frequent words will be taken into account. Only words known by the tokenizer will be taken into account. # Arguments texts: A list of sequences. # Yields Yields individual texts. """ num_words = self.num_words oov_token_index = self.word_index.get(self.oov_token) for seq in sequences: vect = [] for num in seq: word = self.index_word.get(num) if word is not None: if num_words and num >= num_words: if oov_token_index is not None: vect.append(self.index_word[oov_token_index]) else: vect.append(word) elif self.oov_token is not None: vect.append(self.index_word[oov_token_index]) vect = ' '.join(vect) yield vect def texts_to_matrix(self, texts, mode='binary'): """Convert a list of texts to a Numpy matrix. # Arguments texts: list of strings. mode: one of "binary", "count", "tfidf", "freq". # Returns A Numpy matrix. """ sequences = self.texts_to_sequences(texts) return self.sequences_to_matrix(sequences, mode=mode) def sequences_to_matrix(self, sequences, mode='binary'): """Converts a list of sequences into a Numpy matrix. # Arguments sequences: list of sequences (a sequence is a list of integer word indices). mode: one of "binary", "count", "tfidf", "freq" # Returns A Numpy matrix. # Raises ValueError: In case of invalid `mode` argument, or if the Tokenizer requires to be fit to sample data. """ if not self.num_words: if self.word_index: num_words = len(self.word_index) + 1 else: raise ValueError('Specify a dimension (num_words argument), ' 'or fit on some text data first.') else: num_words = self.num_words if mode == 'tfidf' and not self.document_count: raise ValueError('Fit the Tokenizer on some data ' 'before using tfidf mode.') x = np.zeros((len(sequences), num_words)) for i, seq in enumerate(sequences): if not seq: continue counts = defaultdict(int) for j in seq: if j >= num_words: continue counts[j] += 1 for j, c in list(counts.items()): if mode == 'count': x[i][j] = c elif mode == 'freq': x[i][j] = c / len(seq) elif mode == 'binary': x[i][j] = 1 elif mode == 'tfidf': # Use weighting scheme 2 in # https://en.wikipedia.org/wiki/Tf%E2%80%93idf tf = 1 + np.log(c) idf = np.log(1 + self.document_count / (1 + self.index_docs.get(j, 0))) x[i][j] = tf * idf else: raise ValueError('Unknown vectorization mode:', mode) return x def get_config(self): '''Returns the tokenizer configuration as Python dictionary. The word count dictionaries used by the tokenizer get serialized into plain JSON, so that the configuration can be read by other projects. # Returns A Python dictionary with the tokenizer configuration. ''' json_word_counts = json.dumps(self.word_counts) json_word_docs = json.dumps(self.word_docs) json_index_docs = json.dumps(self.index_docs) json_word_index = json.dumps(self.word_index) json_index_word = json.dumps(self.index_word) return { 'num_words': self.num_words, 'filters': self.filters, 'lower': self.lower, 'split': self.split, 'char_level': self.char_level, 'oov_token': self.oov_token, 'document_count': self.document_count, 'word_counts': json_word_counts, 'word_docs': json_word_docs, 'index_docs': json_index_docs, 'index_word': json_index_word, 'word_index': json_word_index } def to_json(self, **kwargs): """Returns a JSON string containing the tokenizer configuration. To load a tokenizer from a JSON string, use `keras.preprocessing.text.tokenizer_from_json(json_string)`. # Arguments **kwargs: Additional keyword arguments to be passed to `json.dumps()`. # Returns A JSON string containing the tokenizer configuration. """ config = self.get_config() tokenizer_config = { 'class_name': self.__class__.__name__, 'config': config } return json.dumps(tokenizer_config, **kwargs) def tokenizer_from_json(json_string): """Parses a JSON tokenizer configuration file and returns a tokenizer instance. # Arguments json_string: JSON string encoding a tokenizer configuration. # Returns A Keras Tokenizer instance """ tokenizer_config = json.loads(json_string) config = tokenizer_config.get('config') word_counts = json.loads(config.pop('word_counts')) word_docs = json.loads(config.pop('word_docs')) index_docs = json.loads(config.pop('index_docs')) # Integer indexing gets converted to strings with json.dumps() index_docs = {int(k): v for k, v in index_docs.items()} index_word = json.loads(config.pop('index_word')) index_word = {int(k): v for k, v in index_word.items()} word_index = json.loads(config.pop('word_index')) tokenizer = Tokenizer(**config) tokenizer.word_counts = word_counts tokenizer.word_docs = word_docs tokenizer.index_docs = index_docs tokenizer.word_index = word_index tokenizer.index_word = index_word return tokenizer Keras_Preprocessing-1.0.5/keras_preprocessing/image.py0000644000000000116100000027117413353510160022737 0ustar rooteng00000000000000"""Utilities for real-time data augmentation on image data. """ from __future__ import absolute_import from __future__ import division from __future__ import print_function import numpy as np import re from six.moves import range import os import threading import warnings import multiprocessing.pool from keras_preprocessing import get_keras_submodule try: IteratorType = get_keras_submodule('utils').Sequence except ImportError: IteratorType = object try: from PIL import ImageEnhance from PIL import Image as pil_image except ImportError: pil_image = None ImageEnhance = None try: import scipy # scipy.linalg cannot be accessed until explicitly imported from scipy import linalg # scipy.ndimage cannot be accessed until explicitly imported from scipy import ndimage except ImportError: scipy = None if pil_image is not None: _PIL_INTERPOLATION_METHODS = { 'nearest': pil_image.NEAREST, 'bilinear': pil_image.BILINEAR, 'bicubic': pil_image.BICUBIC, } # These methods were only introduced in version 3.4.0 (2016). if hasattr(pil_image, 'HAMMING'): _PIL_INTERPOLATION_METHODS['hamming'] = pil_image.HAMMING if hasattr(pil_image, 'BOX'): _PIL_INTERPOLATION_METHODS['box'] = pil_image.BOX # This method is new in version 1.1.3 (2013). if hasattr(pil_image, 'LANCZOS'): _PIL_INTERPOLATION_METHODS['lanczos'] = pil_image.LANCZOS def random_rotation(x, rg, row_axis=1, col_axis=2, channel_axis=0, fill_mode='nearest', cval=0.): """Performs a random rotation of a Numpy image tensor. # Arguments x: Input tensor. Must be 3D. rg: Rotation range, in degrees. row_axis: Index of axis for rows in the input tensor. col_axis: Index of axis for columns in the input tensor. channel_axis: Index of axis for channels in the input tensor. fill_mode: Points outside the boundaries of the input are filled according to the given mode (one of `{'constant', 'nearest', 'reflect', 'wrap'}`). cval: Value used for points outside the boundaries of the input if `mode='constant'`. # Returns Rotated Numpy image tensor. """ theta = np.random.uniform(-rg, rg) x = apply_affine_transform(x, theta=theta, channel_axis=channel_axis, fill_mode=fill_mode, cval=cval) return x def random_shift(x, wrg, hrg, row_axis=1, col_axis=2, channel_axis=0, fill_mode='nearest', cval=0.): """Performs a random spatial shift of a Numpy image tensor. # Arguments x: Input tensor. Must be 3D. wrg: Width shift range, as a float fraction of the width. hrg: Height shift range, as a float fraction of the height. row_axis: Index of axis for rows in the input tensor. col_axis: Index of axis for columns in the input tensor. channel_axis: Index of axis for channels in the input tensor. fill_mode: Points outside the boundaries of the input are filled according to the given mode (one of `{'constant', 'nearest', 'reflect', 'wrap'}`). cval: Value used for points outside the boundaries of the input if `mode='constant'`. # Returns Shifted Numpy image tensor. """ h, w = x.shape[row_axis], x.shape[col_axis] tx = np.random.uniform(-hrg, hrg) * h ty = np.random.uniform(-wrg, wrg) * w x = apply_affine_transform(x, tx=tx, ty=ty, channel_axis=channel_axis, fill_mode=fill_mode, cval=cval) return x def random_shear(x, intensity, row_axis=1, col_axis=2, channel_axis=0, fill_mode='nearest', cval=0.): """Performs a random spatial shear of a Numpy image tensor. # Arguments x: Input tensor. Must be 3D. intensity: Transformation intensity in degrees. row_axis: Index of axis for rows in the input tensor. col_axis: Index of axis for columns in the input tensor. channel_axis: Index of axis for channels in the input tensor. fill_mode: Points outside the boundaries of the input are filled according to the given mode (one of `{'constant', 'nearest', 'reflect', 'wrap'}`). cval: Value used for points outside the boundaries of the input if `mode='constant'`. # Returns Sheared Numpy image tensor. """ shear = np.random.uniform(-intensity, intensity) x = apply_affine_transform(x, shear=shear, channel_axis=channel_axis, fill_mode=fill_mode, cval=cval) return x def random_zoom(x, zoom_range, row_axis=1, col_axis=2, channel_axis=0, fill_mode='nearest', cval=0.): """Performs a random spatial zoom of a Numpy image tensor. # Arguments x: Input tensor. Must be 3D. zoom_range: Tuple of floats; zoom range for width and height. row_axis: Index of axis for rows in the input tensor. col_axis: Index of axis for columns in the input tensor. channel_axis: Index of axis for channels in the input tensor. fill_mode: Points outside the boundaries of the input are filled according to the given mode (one of `{'constant', 'nearest', 'reflect', 'wrap'}`). cval: Value used for points outside the boundaries of the input if `mode='constant'`. # Returns Zoomed Numpy image tensor. # Raises ValueError: if `zoom_range` isn't a tuple. """ if len(zoom_range) != 2: raise ValueError('`zoom_range` should be a tuple or list of two' ' floats. Received: %s' % (zoom_range,)) if zoom_range[0] == 1 and zoom_range[1] == 1: zx, zy = 1, 1 else: zx, zy = np.random.uniform(zoom_range[0], zoom_range[1], 2) x = apply_affine_transform(x, zx=zx, zy=zy, channel_axis=channel_axis, fill_mode=fill_mode, cval=cval) return x def apply_channel_shift(x, intensity, channel_axis=0): """Performs a channel shift. # Arguments x: Input tensor. Must be 3D. intensity: Transformation intensity. channel_axis: Index of axis for channels in the input tensor. # Returns Numpy image tensor. """ x = np.rollaxis(x, channel_axis, 0) min_x, max_x = np.min(x), np.max(x) channel_images = [ np.clip(x_channel + intensity, min_x, max_x) for x_channel in x] x = np.stack(channel_images, axis=0) x = np.rollaxis(x, 0, channel_axis + 1) return x def random_channel_shift(x, intensity_range, channel_axis=0): """Performs a random channel shift. # Arguments x: Input tensor. Must be 3D. intensity_range: Transformation intensity. channel_axis: Index of axis for channels in the input tensor. # Returns Numpy image tensor. """ intensity = np.random.uniform(-intensity_range, intensity_range) return apply_channel_shift(x, intensity, channel_axis=channel_axis) def apply_brightness_shift(x, brightness): """Performs a brightness shift. # Arguments x: Input tensor. Must be 3D. brightness: Float. The new brightness value. channel_axis: Index of axis for channels in the input tensor. # Returns Numpy image tensor. # Raises ValueError if `brightness_range` isn't a tuple. """ if ImageEnhance is None: raise ImportError('Using brightness shifts requires PIL. ' 'Install PIL or Pillow.') x = array_to_img(x) x = imgenhancer_Brightness = ImageEnhance.Brightness(x) x = imgenhancer_Brightness.enhance(brightness) x = img_to_array(x) return x def random_brightness(x, brightness_range): """Performs a random brightness shift. # Arguments x: Input tensor. Must be 3D. brightness_range: Tuple of floats; brightness range. channel_axis: Index of axis for channels in the input tensor. # Returns Numpy image tensor. # Raises ValueError if `brightness_range` isn't a tuple. """ if len(brightness_range) != 2: raise ValueError( '`brightness_range should be tuple or list of two floats. ' 'Received: %s' % (brightness_range,)) u = np.random.uniform(brightness_range[0], brightness_range[1]) return apply_brightness_shift(x, u) def transform_matrix_offset_center(matrix, x, y): o_x = float(x) / 2 + 0.5 o_y = float(y) / 2 + 0.5 offset_matrix = np.array([[1, 0, o_x], [0, 1, o_y], [0, 0, 1]]) reset_matrix = np.array([[1, 0, -o_x], [0, 1, -o_y], [0, 0, 1]]) transform_matrix = np.dot(np.dot(offset_matrix, matrix), reset_matrix) return transform_matrix def apply_affine_transform(x, theta=0, tx=0, ty=0, shear=0, zx=1, zy=1, row_axis=0, col_axis=1, channel_axis=2, fill_mode='nearest', cval=0.): """Applies an affine transformation specified by the parameters given. # Arguments x: 2D numpy array, single image. theta: Rotation angle in degrees. tx: Width shift. ty: Heigh shift. shear: Shear angle in degrees. zx: Zoom in x direction. zy: Zoom in y direction row_axis: Index of axis for rows in the input image. col_axis: Index of axis for columns in the input image. channel_axis: Index of axis for channels in the input image. fill_mode: Points outside the boundaries of the input are filled according to the given mode (one of `{'constant', 'nearest', 'reflect', 'wrap'}`). cval: Value used for points outside the boundaries of the input if `mode='constant'`. # Returns The transformed version of the input. """ if scipy is None: raise ImportError('Image transformations require SciPy. ' 'Install SciPy.') transform_matrix = None if theta != 0: theta = np.deg2rad(theta) rotation_matrix = np.array([[np.cos(theta), -np.sin(theta), 0], [np.sin(theta), np.cos(theta), 0], [0, 0, 1]]) transform_matrix = rotation_matrix if tx != 0 or ty != 0: shift_matrix = np.array([[1, 0, tx], [0, 1, ty], [0, 0, 1]]) if transform_matrix is None: transform_matrix = shift_matrix else: transform_matrix = np.dot(transform_matrix, shift_matrix) if shear != 0: shear = np.deg2rad(shear) shear_matrix = np.array([[1, -np.sin(shear), 0], [0, np.cos(shear), 0], [0, 0, 1]]) if transform_matrix is None: transform_matrix = shear_matrix else: transform_matrix = np.dot(transform_matrix, shear_matrix) if zx != 1 or zy != 1: zoom_matrix = np.array([[zx, 0, 0], [0, zy, 0], [0, 0, 1]]) if transform_matrix is None: transform_matrix = zoom_matrix else: transform_matrix = np.dot(transform_matrix, zoom_matrix) if transform_matrix is not None: h, w = x.shape[row_axis], x.shape[col_axis] transform_matrix = transform_matrix_offset_center( transform_matrix, h, w) x = np.rollaxis(x, channel_axis, 0) final_affine_matrix = transform_matrix[:2, :2] final_offset = transform_matrix[:2, 2] channel_images = [scipy.ndimage.interpolation.affine_transform( x_channel, final_affine_matrix, final_offset, order=1, mode=fill_mode, cval=cval) for x_channel in x] x = np.stack(channel_images, axis=0) x = np.rollaxis(x, 0, channel_axis + 1) return x def flip_axis(x, axis): x = np.asarray(x).swapaxes(axis, 0) x = x[::-1, ...] x = x.swapaxes(0, axis) return x def array_to_img(x, data_format='channels_last', scale=True, dtype='float32'): """Converts a 3D Numpy array to a PIL Image instance. # Arguments x: Input Numpy array. data_format: Image data format. either "channels_first" or "channels_last". scale: Whether to rescale image values to be within `[0, 255]`. dtype: Dtype to use. # Returns A PIL Image instance. # Raises ImportError: if PIL is not available. ValueError: if invalid `x` or `data_format` is passed. """ if pil_image is None: raise ImportError('Could not import PIL.Image. ' 'The use of `array_to_img` requires PIL.') x = np.asarray(x, dtype=dtype) if x.ndim != 3: raise ValueError('Expected image array to have rank 3 (single image). ' 'Got array with shape: %s' % (x.shape,)) if data_format not in {'channels_first', 'channels_last'}: raise ValueError('Invalid data_format: %s' % data_format) # Original Numpy array x has format (height, width, channel) # or (channel, height, width) # but target PIL image has format (width, height, channel) if data_format == 'channels_first': x = x.transpose(1, 2, 0) if scale: x = x + max(-np.min(x), 0) x_max = np.max(x) if x_max != 0: x /= x_max x *= 255 if x.shape[2] == 4: # RGBA return pil_image.fromarray(x.astype('uint8'), 'RGBA') elif x.shape[2] == 3: # RGB return pil_image.fromarray(x.astype('uint8'), 'RGB') elif x.shape[2] == 1: # grayscale return pil_image.fromarray(x[:, :, 0].astype('uint8'), 'L') else: raise ValueError('Unsupported channel number: %s' % (x.shape[2],)) def img_to_array(img, data_format='channels_last', dtype='float32'): """Converts a PIL Image instance to a Numpy array. # Arguments img: PIL Image instance. data_format: Image data format, either "channels_first" or "channels_last". dtype: Dtype to use for the returned array. # Returns A 3D Numpy array. # Raises ValueError: if invalid `img` or `data_format` is passed. """ if data_format not in {'channels_first', 'channels_last'}: raise ValueError('Unknown data_format: %s' % data_format) # Numpy array x has format (height, width, channel) # or (channel, height, width) # but original PIL image has format (width, height, channel) x = np.asarray(img, dtype=dtype) if len(x.shape) == 3: if data_format == 'channels_first': x = x.transpose(2, 0, 1) elif len(x.shape) == 2: if data_format == 'channels_first': x = x.reshape((1, x.shape[0], x.shape[1])) else: x = x.reshape((x.shape[0], x.shape[1], 1)) else: raise ValueError('Unsupported image shape: %s' % (x.shape,)) return x def save_img(path, x, data_format='channels_last', file_format=None, scale=True, **kwargs): """Saves an image stored as a Numpy array to a path or file object. # Arguments path: Path or file object. x: Numpy array. data_format: Image data format, either "channels_first" or "channels_last". file_format: Optional file format override. If omitted, the format to use is determined from the filename extension. If a file object was used instead of a filename, this parameter should always be used. scale: Whether to rescale image values to be within `[0, 255]`. **kwargs: Additional keyword arguments passed to `PIL.Image.save()`. """ img = array_to_img(x, data_format=data_format, scale=scale) if img.mode == 'RGBA' and (file_format == 'jpg' or file_format == 'jpeg'): warnings.warn('The JPG format does not support ' 'RGBA images, converting to RGB.') img = img.convert('RGB') img.save(path, format=file_format, **kwargs) def load_img(path, grayscale=False, color_mode='rgb', target_size=None, interpolation='nearest'): """Loads an image into PIL format. # Arguments path: Path to image file. color_mode: One of "grayscale", "rbg", "rgba". Default: "rgb". The desired image format. target_size: Either `None` (default to original size) or tuple of ints `(img_height, img_width)`. interpolation: Interpolation method used to resample the image if the target size is different from that of the loaded image. Supported methods are "nearest", "bilinear", and "bicubic". If PIL version 1.1.3 or newer is installed, "lanczos" is also supported. If PIL version 3.4.0 or newer is installed, "box" and "hamming" are also supported. By default, "nearest" is used. # Returns A PIL Image instance. # Raises ImportError: if PIL is not available. ValueError: if interpolation method is not supported. """ if grayscale is True: warnings.warn('grayscale is deprecated. Please use ' 'color_mode = "grayscale"') color_mode = 'grayscale' if pil_image is None: raise ImportError('Could not import PIL.Image. ' 'The use of `array_to_img` requires PIL.') img = pil_image.open(path) if color_mode == 'grayscale': if img.mode != 'L': img = img.convert('L') elif color_mode == 'rgba': if img.mode != 'RGBA': img = img.convert('RGBA') elif color_mode == 'rgb': if img.mode != 'RGB': img = img.convert('RGB') else: raise ValueError('color_mode must be "grayscale", "rbg", or "rgba"') if target_size is not None: width_height_tuple = (target_size[1], target_size[0]) if img.size != width_height_tuple: if interpolation not in _PIL_INTERPOLATION_METHODS: raise ValueError( 'Invalid interpolation method {} specified. Supported ' 'methods are {}'.format( interpolation, ", ".join(_PIL_INTERPOLATION_METHODS.keys()))) resample = _PIL_INTERPOLATION_METHODS[interpolation] img = img.resize(width_height_tuple, resample) return img def list_pictures(directory, ext='jpg|jpeg|bmp|png|ppm'): return [os.path.join(root, f) for root, _, files in os.walk(directory) for f in files if re.match(r'([\w]+\.(?:' + ext + '))', f.lower())] class ImageDataGenerator(object): """Generate batches of tensor image data with real-time data augmentation. The data will be looped over (in batches). # Arguments featurewise_center: Boolean. Set input mean to 0 over the dataset, feature-wise. samplewise_center: Boolean. Set each sample mean to 0. featurewise_std_normalization: Boolean. Divide inputs by std of the dataset, feature-wise. samplewise_std_normalization: Boolean. Divide each input by its std. zca_epsilon: epsilon for ZCA whitening. Default is 1e-6. zca_whitening: Boolean. Apply ZCA whitening. rotation_range: Int. Degree range for random rotations. width_shift_range: Float, 1-D array-like or int - float: fraction of total width, if < 1, or pixels if >= 1. - 1-D array-like: random elements from the array. - int: integer number of pixels from interval `(-width_shift_range, +width_shift_range)` - With `width_shift_range=2` possible values are integers `[-1, 0, +1]`, same as with `width_shift_range=[-1, 0, +1]`, while with `width_shift_range=1.0` possible values are floats in the interval [-1.0, +1.0). height_shift_range: Float, 1-D array-like or int - float: fraction of total height, if < 1, or pixels if >= 1. - 1-D array-like: random elements from the array. - int: integer number of pixels from interval `(-height_shift_range, +height_shift_range)` - With `height_shift_range=2` possible values are integers `[-1, 0, +1]`, same as with `height_shift_range=[-1, 0, +1]`, while with `height_shift_range=1.0` possible values are floats in the interval [-1.0, +1.0). brightness_range: Tuple or list of two floats. Range for picking a brightness shift value from. shear_range: Float. Shear Intensity (Shear angle in counter-clockwise direction in degrees) zoom_range: Float or [lower, upper]. Range for random zoom. If a float, `[lower, upper] = [1-zoom_range, 1+zoom_range]`. channel_shift_range: Float. Range for random channel shifts. fill_mode: One of {"constant", "nearest", "reflect" or "wrap"}. Default is 'nearest'. Points outside the boundaries of the input are filled according to the given mode: - 'constant': kkkkkkkk|abcd|kkkkkkkk (cval=k) - 'nearest': aaaaaaaa|abcd|dddddddd - 'reflect': abcddcba|abcd|dcbaabcd - 'wrap': abcdabcd|abcd|abcdabcd cval: Float or Int. Value used for points outside the boundaries when `fill_mode = "constant"`. horizontal_flip: Boolean. Randomly flip inputs horizontally. vertical_flip: Boolean. Randomly flip inputs vertically. rescale: rescaling factor. Defaults to None. If None or 0, no rescaling is applied, otherwise we multiply the data by the value provided (after applying all other transformations). preprocessing_function: function that will be implied on each input. The function will run after the image is resized and augmented. The function should take one argument: one image (Numpy tensor with rank 3), and should output a Numpy tensor with the same shape. data_format: Image data format, either "channels_first" or "channels_last". "channels_last" mode means that the images should have shape `(samples, height, width, channels)`, "channels_first" mode means that the images should have shape `(samples, channels, height, width)`. It defaults to the `image_data_format` value found in your Keras config file at `~/.keras/keras.json`. If you never set it, then it will be "channels_last". validation_split: Float. Fraction of images reserved for validation (strictly between 0 and 1). dtype: Dtype to use for the generated arrays. # Examples Example of using `.flow(x, y)`: ```python (x_train, y_train), (x_test, y_test) = cifar10.load_data() y_train = np_utils.to_categorical(y_train, num_classes) y_test = np_utils.to_categorical(y_test, num_classes) datagen = ImageDataGenerator( featurewise_center=True, featurewise_std_normalization=True, rotation_range=20, width_shift_range=0.2, height_shift_range=0.2, horizontal_flip=True) # compute quantities required for featurewise normalization # (std, mean, and principal components if ZCA whitening is applied) datagen.fit(x_train) # fits the model on batches with real-time data augmentation: model.fit_generator(datagen.flow(x_train, y_train, batch_size=32), steps_per_epoch=len(x_train) / 32, epochs=epochs) # here's a more "manual" example for e in range(epochs): print('Epoch', e) batches = 0 for x_batch, y_batch in datagen.flow(x_train, y_train, batch_size=32): model.fit(x_batch, y_batch) batches += 1 if batches >= len(x_train) / 32: # we need to break the loop by hand because # the generator loops indefinitely break ``` Example of using `.flow_from_directory(directory)`: ```python train_datagen = ImageDataGenerator( rescale=1./255, shear_range=0.2, zoom_range=0.2, horizontal_flip=True) test_datagen = ImageDataGenerator(rescale=1./255) train_generator = train_datagen.flow_from_directory( 'data/train', target_size=(150, 150), batch_size=32, class_mode='binary') validation_generator = test_datagen.flow_from_directory( 'data/validation', target_size=(150, 150), batch_size=32, class_mode='binary') model.fit_generator( train_generator, steps_per_epoch=2000, epochs=50, validation_data=validation_generator, validation_steps=800) ``` Example of transforming images and masks together. ```python # we create two instances with the same arguments data_gen_args = dict(featurewise_center=True, featurewise_std_normalization=True, rotation_range=90, width_shift_range=0.1, height_shift_range=0.1, zoom_range=0.2) image_datagen = ImageDataGenerator(**data_gen_args) mask_datagen = ImageDataGenerator(**data_gen_args) # Provide the same seed and keyword arguments to the fit and flow methods seed = 1 image_datagen.fit(images, augment=True, seed=seed) mask_datagen.fit(masks, augment=True, seed=seed) image_generator = image_datagen.flow_from_directory( 'data/images', class_mode=None, seed=seed) mask_generator = mask_datagen.flow_from_directory( 'data/masks', class_mode=None, seed=seed) # combine generators into one which yields image and masks train_generator = zip(image_generator, mask_generator) model.fit_generator( train_generator, steps_per_epoch=2000, epochs=50) ``` Example of using ```.flow_from_dataframe(dataframe, directory, x_col, y_col, has_ext)```: ```python train_df = pandas.read_csv("./train.csv") valid_df = pandas.read_csv("./valid.csv") train_datagen = ImageDataGenerator( rescale=1./255, shear_range=0.2, zoom_range=0.2, horizontal_flip=True) test_datagen = ImageDataGenerator(rescale=1./255) train_generator = train_datagen.flow_from_dataframe( dataframe=train_df, directory='data/train', x_col="filename", y_col="class", has_ext=True, target_size=(150, 150), batch_size=32, class_mode='binary') validation_generator = test_datagen.flow_from_dataframe( dataframe=valid_df, directory='data/validation', x_col="filename", y_col="class", has_ext=True, target_size=(150, 150), batch_size=32, class_mode='binary') model.fit_generator( train_generator, steps_per_epoch=2000, epochs=50, validation_data=validation_generator, validation_steps=800) ``` """ def __init__(self, featurewise_center=False, samplewise_center=False, featurewise_std_normalization=False, samplewise_std_normalization=False, zca_whitening=False, zca_epsilon=1e-6, rotation_range=0, width_shift_range=0., height_shift_range=0., brightness_range=None, shear_range=0., zoom_range=0., channel_shift_range=0., fill_mode='nearest', cval=0., horizontal_flip=False, vertical_flip=False, rescale=None, preprocessing_function=None, data_format='channels_last', validation_split=0.0, dtype='float32'): self.featurewise_center = featurewise_center self.samplewise_center = samplewise_center self.featurewise_std_normalization = featurewise_std_normalization self.samplewise_std_normalization = samplewise_std_normalization self.zca_whitening = zca_whitening self.zca_epsilon = zca_epsilon self.rotation_range = rotation_range self.width_shift_range = width_shift_range self.height_shift_range = height_shift_range self.brightness_range = brightness_range self.shear_range = shear_range self.zoom_range = zoom_range self.channel_shift_range = channel_shift_range self.fill_mode = fill_mode self.cval = cval self.horizontal_flip = horizontal_flip self.vertical_flip = vertical_flip self.rescale = rescale self.preprocessing_function = preprocessing_function self.dtype = dtype if data_format not in {'channels_last', 'channels_first'}: raise ValueError( '`data_format` should be `"channels_last"` ' '(channel after row and column) or ' '`"channels_first"` (channel before row and column). ' 'Received: %s' % data_format) self.data_format = data_format if data_format == 'channels_first': self.channel_axis = 1 self.row_axis = 2 self.col_axis = 3 if data_format == 'channels_last': self.channel_axis = 3 self.row_axis = 1 self.col_axis = 2 if validation_split and not 0 < validation_split < 1: raise ValueError( '`validation_split` must be strictly between 0 and 1. ' ' Received: %s' % validation_split) self._validation_split = validation_split self.mean = None self.std = None self.principal_components = None if np.isscalar(zoom_range): self.zoom_range = [1 - zoom_range, 1 + zoom_range] elif len(zoom_range) == 2: self.zoom_range = [zoom_range[0], zoom_range[1]] else: raise ValueError('`zoom_range` should be a float or ' 'a tuple or list of two floats. ' 'Received: %s' % (zoom_range,)) if zca_whitening: if not featurewise_center: self.featurewise_center = True warnings.warn('This ImageDataGenerator specifies ' '`zca_whitening`, which overrides ' 'setting of `featurewise_center`.') if featurewise_std_normalization: self.featurewise_std_normalization = False warnings.warn('This ImageDataGenerator specifies ' '`zca_whitening` ' 'which overrides setting of' '`featurewise_std_normalization`.') if featurewise_std_normalization: if not featurewise_center: self.featurewise_center = True warnings.warn('This ImageDataGenerator specifies ' '`featurewise_std_normalization`, ' 'which overrides setting of ' '`featurewise_center`.') if samplewise_std_normalization: if not samplewise_center: self.samplewise_center = True warnings.warn('This ImageDataGenerator specifies ' '`samplewise_std_normalization`, ' 'which overrides setting of ' '`samplewise_center`.') def flow(self, x, y=None, batch_size=32, shuffle=True, sample_weight=None, seed=None, save_to_dir=None, save_prefix='', save_format='png', subset=None): """Takes data & label arrays, generates batches of augmented data. # Arguments x: Input data. Numpy array of rank 4 or a tuple. If tuple, the first element should contain the images and the second element another numpy array or a list of numpy arrays that gets passed to the output without any modifications. Can be used to feed the model miscellaneous data along with the images. In case of grayscale data, the channels axis of the image array should have value 1, in case of RGB data, it should have value 3, and in case of RGBA data, it should have value 4. y: Labels. batch_size: Int (default: 32). shuffle: Boolean (default: True). sample_weight: Sample weights. seed: Int (default: None). save_to_dir: None or str (default: None). This allows you to optionally specify a directory to which to save the augmented pictures being generated (useful for visualizing what you are doing). save_prefix: Str (default: `''`). Prefix to use for filenames of saved pictures (only relevant if `save_to_dir` is set). save_format: one of "png", "jpeg" (only relevant if `save_to_dir` is set). Default: "png". subset: Subset of data (`"training"` or `"validation"`) if `validation_split` is set in `ImageDataGenerator`. # Returns An `Iterator` yielding tuples of `(x, y)` where `x` is a numpy array of image data (in the case of a single image input) or a list of numpy arrays (in the case with additional inputs) and `y` is a numpy array of corresponding labels. If 'sample_weight' is not None, the yielded tuples are of the form `(x, y, sample_weight)`. If `y` is None, only the numpy array `x` is returned. """ return NumpyArrayIterator( x, y, self, batch_size=batch_size, shuffle=shuffle, sample_weight=sample_weight, seed=seed, data_format=self.data_format, save_to_dir=save_to_dir, save_prefix=save_prefix, save_format=save_format, subset=subset) def flow_from_directory(self, directory, target_size=(256, 256), color_mode='rgb', classes=None, class_mode='categorical', batch_size=32, shuffle=True, seed=None, save_to_dir=None, save_prefix='', save_format='png', follow_links=False, subset=None, interpolation='nearest'): """Takes the path to a directory & generates batches of augmented data. # Arguments directory: Path to the target directory. It should contain one subdirectory per class. Any PNG, JPG, BMP, PPM or TIF images inside each of the subdirectories directory tree will be included in the generator. See [this script]( https://gist.github.com/fchollet/0830affa1f7f19fd47b06d4cf89ed44d) for more details. target_size: Tuple of integers `(height, width)`, default: `(256, 256)`. The dimensions to which all images found will be resized. color_mode: One of "grayscale", "rbg", "rgba". Default: "rgb". Whether the images will be converted to have 1, 3, or 4 channels. classes: Optional list of class subdirectories (e.g. `['dogs', 'cats']`). Default: None. If not provided, the list of classes will be automatically inferred from the subdirectory names/structure under `directory`, where each subdirectory will be treated as a different class (and the order of the classes, which will map to the label indices, will be alphanumeric). The dictionary containing the mapping from class names to class indices can be obtained via the attribute `class_indices`. class_mode: One of "categorical", "binary", "sparse", "input", or None. Default: "categorical". Determines the type of label arrays that are returned: - "categorical" will be 2D one-hot encoded labels, - "binary" will be 1D binary labels, "sparse" will be 1D integer labels, - "input" will be images identical to input images (mainly used to work with autoencoders). - If None, no labels are returned (the generator will only yield batches of image data, which is useful to use with `model.predict_generator()`, `model.evaluate_generator()`, etc.). Please note that in case of class_mode None, the data still needs to reside in a subdirectory of `directory` for it to work correctly. batch_size: Size of the batches of data (default: 32). shuffle: Whether to shuffle the data (default: True) seed: Optional random seed for shuffling and transformations. save_to_dir: None or str (default: None). This allows you to optionally specify a directory to which to save the augmented pictures being generated (useful for visualizing what you are doing). save_prefix: Str. Prefix to use for filenames of saved pictures (only relevant if `save_to_dir` is set). save_format: One of "png", "jpeg" (only relevant if `save_to_dir` is set). Default: "png". follow_links: Whether to follow symlinks inside class subdirectories (default: False). subset: Subset of data (`"training"` or `"validation"`) if `validation_split` is set in `ImageDataGenerator`. interpolation: Interpolation method used to resample the image if the target size is different from that of the loaded image. Supported methods are `"nearest"`, `"bilinear"`, and `"bicubic"`. If PIL version 1.1.3 or newer is installed, `"lanczos"` is also supported. If PIL version 3.4.0 or newer is installed, `"box"` and `"hamming"` are also supported. By default, `"nearest"` is used. # Returns A `DirectoryIterator` yielding tuples of `(x, y)` where `x` is a numpy array containing a batch of images with shape `(batch_size, *target_size, channels)` and `y` is a numpy array of corresponding labels. """ return DirectoryIterator( directory, self, target_size=target_size, color_mode=color_mode, classes=classes, class_mode=class_mode, data_format=self.data_format, batch_size=batch_size, shuffle=shuffle, seed=seed, save_to_dir=save_to_dir, save_prefix=save_prefix, save_format=save_format, follow_links=follow_links, subset=subset, interpolation=interpolation) def flow_from_dataframe(self, dataframe, directory, x_col="filename", y_col="class", has_ext=True, target_size=(256, 256), color_mode='rgb', classes=None, class_mode='categorical', batch_size=32, shuffle=True, seed=None, save_to_dir=None, save_prefix='', save_format='png', subset=None, interpolation='nearest'): """Takes the dataframe and the path to a directory and generates batches of augmented/normalized data. # A simple tutorial can be found at: http://bit.ly/keras_flow_from_dataframe # Arguments dataframe: Pandas dataframe containing the filenames of the images in a column and classes in another or column/s that can be fed as raw target data. directory: string, path to the target directory that contains all the images mapped in the dataframe. x_col: string, column in the dataframe that contains the filenames of the target images. y_col: string or list of strings,columns in the dataframe that will be the target data. has_ext: bool, True if filenames in dataframe[x_col] has filename extensions,else False. target_size: tuple of integers `(height, width)`, default: `(256, 256)`. The dimensions to which all images found will be resized. color_mode: one of "grayscale", "rbg". Default: "rgb". Whether the images will be converted to have 1 or 3 color channels. classes: optional list of classes (e.g. `['dogs', 'cats']`). Default: None. If not provided, the list of classes will be automatically inferred from the y_col, which will map to the label indices, will be alphanumeric). The dictionary containing the mapping from class names to class indices can be obtained via the attribute `class_indices`. class_mode: one of "categorical", "binary", "sparse", "input", "other" or None. Default: "categorical". Determines the type of label arrays that are returned: - `"categorical"` will be 2D one-hot encoded labels, - `"binary"` will be 1D binary labels, - `"sparse"` will be 1D integer labels, - `"input"` will be images identical to input images (mainly used to work with autoencoders). - `"other"` will be numpy array of y_col data - None, no labels are returned (the generator will only yield batches of image data, which is useful to use `model.predict_generator()`, `model.evaluate_generator()`, etc.). batch_size: size of the batches of data (default: 32). shuffle: whether to shuffle the data (default: True) seed: optional random seed for shuffling and transformations. save_to_dir: None or str (default: None). This allows you to optionally specify a directory to which to save the augmented pictures being generated (useful for visualizing what you are doing). save_prefix: str. Prefix to use for filenames of saved pictures (only relevant if `save_to_dir` is set). save_format: one of "png", "jpeg" (only relevant if `save_to_dir` is set). Default: "png". follow_links: whether to follow symlinks inside class subdirectories (default: False). subset: Subset of data (`"training"` or `"validation"`) if `validation_split` is set in `ImageDataGenerator`. interpolation: Interpolation method used to resample the image if the target size is different from that of the loaded image. Supported methods are `"nearest"`, `"bilinear"`, and `"bicubic"`. If PIL version 1.1.3 or newer is installed, `"lanczos"` is also supported. If PIL version 3.4.0 or newer is installed, `"box"` and `"hamming"` are also supported. By default, `"nearest"` is used. # Returns A DataFrameIterator yielding tuples of `(x, y)` where `x` is a numpy array containing a batch of images with shape `(batch_size, *target_size, channels)` and `y` is a numpy array of corresponding labels. """ return DataFrameIterator(dataframe, directory, self, x_col=x_col, y_col=y_col, has_ext=has_ext, target_size=target_size, color_mode=color_mode, classes=classes, class_mode=class_mode, data_format=self.data_format, batch_size=batch_size, shuffle=shuffle, seed=seed, save_to_dir=save_to_dir, save_prefix=save_prefix, save_format=save_format, subset=subset, interpolation=interpolation) def standardize(self, x): """Applies the normalization configuration to a batch of inputs. # Arguments x: Batch of inputs to be normalized. # Returns The inputs, normalized. """ if self.preprocessing_function: x = self.preprocessing_function(x) if self.rescale: x *= self.rescale if self.samplewise_center: x -= np.mean(x, keepdims=True) if self.samplewise_std_normalization: x /= (np.std(x, keepdims=True) + 1e-6) if self.featurewise_center: if self.mean is not None: x -= self.mean else: warnings.warn('This ImageDataGenerator specifies ' '`featurewise_center`, but it hasn\'t ' 'been fit on any training data. Fit it ' 'first by calling `.fit(numpy_data)`.') if self.featurewise_std_normalization: if self.std is not None: x /= (self.std + 1e-6) else: warnings.warn('This ImageDataGenerator specifies ' '`featurewise_std_normalization`, ' 'but it hasn\'t ' 'been fit on any training data. Fit it ' 'first by calling `.fit(numpy_data)`.') if self.zca_whitening: if self.principal_components is not None: flatx = np.reshape(x, (-1, np.prod(x.shape[-3:]))) whitex = np.dot(flatx, self.principal_components) x = np.reshape(whitex, x.shape) else: warnings.warn('This ImageDataGenerator specifies ' '`zca_whitening`, but it hasn\'t ' 'been fit on any training data. Fit it ' 'first by calling `.fit(numpy_data)`.') return x def get_random_transform(self, img_shape, seed=None): """Generates random parameters for a transformation. # Arguments seed: Random seed. img_shape: Tuple of integers. Shape of the image that is transformed. # Returns A dictionary containing randomly chosen parameters describing the transformation. """ img_row_axis = self.row_axis - 1 img_col_axis = self.col_axis - 1 if seed is not None: np.random.seed(seed) if self.rotation_range: theta = np.random.uniform( -self.rotation_range, self.rotation_range) else: theta = 0 if self.height_shift_range: try: # 1-D array-like or int tx = np.random.choice(self.height_shift_range) tx *= np.random.choice([-1, 1]) except ValueError: # floating point tx = np.random.uniform(-self.height_shift_range, self.height_shift_range) if np.max(self.height_shift_range) < 1: tx *= img_shape[img_row_axis] else: tx = 0 if self.width_shift_range: try: # 1-D array-like or int ty = np.random.choice(self.width_shift_range) ty *= np.random.choice([-1, 1]) except ValueError: # floating point ty = np.random.uniform(-self.width_shift_range, self.width_shift_range) if np.max(self.width_shift_range) < 1: ty *= img_shape[img_col_axis] else: ty = 0 if self.shear_range: shear = np.random.uniform( -self.shear_range, self.shear_range) else: shear = 0 if self.zoom_range[0] == 1 and self.zoom_range[1] == 1: zx, zy = 1, 1 else: zx, zy = np.random.uniform( self.zoom_range[0], self.zoom_range[1], 2) flip_horizontal = (np.random.random() < 0.5) * self.horizontal_flip flip_vertical = (np.random.random() < 0.5) * self.vertical_flip channel_shift_intensity = None if self.channel_shift_range != 0: channel_shift_intensity = np.random.uniform(-self.channel_shift_range, self.channel_shift_range) brightness = None if self.brightness_range is not None: if len(self.brightness_range) != 2: raise ValueError( '`brightness_range should be tuple or list of two floats. ' 'Received: %s' % (self.brightness_range,)) brightness = np.random.uniform(self.brightness_range[0], self.brightness_range[1]) transform_parameters = {'theta': theta, 'tx': tx, 'ty': ty, 'shear': shear, 'zx': zx, 'zy': zy, 'flip_horizontal': flip_horizontal, 'flip_vertical': flip_vertical, 'channel_shift_intensity': channel_shift_intensity, 'brightness': brightness} return transform_parameters def apply_transform(self, x, transform_parameters): """Applies a transformation to an image according to given parameters. # Arguments x: 3D tensor, single image. transform_parameters: Dictionary with string - parameter pairs describing the transformation. Currently, the following parameters from the dictionary are used: - `'theta'`: Float. Rotation angle in degrees. - `'tx'`: Float. Shift in the x direction. - `'ty'`: Float. Shift in the y direction. - `'shear'`: Float. Shear angle in degrees. - `'zx'`: Float. Zoom in the x direction. - `'zy'`: Float. Zoom in the y direction. - `'flip_horizontal'`: Boolean. Horizontal flip. - `'flip_vertical'`: Boolean. Vertical flip. - `'channel_shift_intencity'`: Float. Channel shift intensity. - `'brightness'`: Float. Brightness shift intensity. # Returns A transformed version of the input (same shape). """ # x is a single image, so it doesn't have image number at index 0 img_row_axis = self.row_axis - 1 img_col_axis = self.col_axis - 1 img_channel_axis = self.channel_axis - 1 x = apply_affine_transform(x, transform_parameters.get('theta', 0), transform_parameters.get('tx', 0), transform_parameters.get('ty', 0), transform_parameters.get('shear', 0), transform_parameters.get('zx', 1), transform_parameters.get('zy', 1), row_axis=img_row_axis, col_axis=img_col_axis, channel_axis=img_channel_axis, fill_mode=self.fill_mode, cval=self.cval) if transform_parameters.get('channel_shift_intensity') is not None: x = apply_channel_shift(x, transform_parameters['channel_shift_intensity'], img_channel_axis) if transform_parameters.get('flip_horizontal', False): x = flip_axis(x, img_col_axis) if transform_parameters.get('flip_vertical', False): x = flip_axis(x, img_row_axis) if transform_parameters.get('brightness') is not None: x = apply_brightness_shift(x, transform_parameters['brightness']) return x def random_transform(self, x, seed=None): """Applies a random transformation to an image. # Arguments x: 3D tensor, single image. seed: Random seed. # Returns A randomly transformed version of the input (same shape). """ params = self.get_random_transform(x.shape, seed) return self.apply_transform(x, params) def fit(self, x, augment=False, rounds=1, seed=None): """Fits the data generator to some sample data. This computes the internal data stats related to the data-dependent transformations, based on an array of sample data. Only required if `featurewise_center` or `featurewise_std_normalization` or `zca_whitening` are set to True. # Arguments x: Sample data. Should have rank 4. In case of grayscale data, the channels axis should have value 1, in case of RGB data, it should have value 3, and in case of RGBA data, it should have value 4. augment: Boolean (default: False). Whether to fit on randomly augmented samples. rounds: Int (default: 1). If using data augmentation (`augment=True`), this is how many augmentation passes over the data to use. seed: Int (default: None). Random seed. """ x = np.asarray(x, dtype=self.dtype) if x.ndim != 4: raise ValueError('Input to `.fit()` should have rank 4. ' 'Got array with shape: ' + str(x.shape)) if x.shape[self.channel_axis] not in {1, 3, 4}: warnings.warn( 'Expected input to be images (as Numpy array) ' 'following the data format convention "' + self.data_format + '" (channels on axis ' + str(self.channel_axis) + '), i.e. expected ' 'either 1, 3 or 4 channels on axis ' + str(self.channel_axis) + '. ' 'However, it was passed an array with shape ' + str(x.shape) + ' (' + str(x.shape[self.channel_axis]) + ' channels).') if seed is not None: np.random.seed(seed) x = np.copy(x) if augment: ax = np.zeros( tuple([rounds * x.shape[0]] + list(x.shape)[1:]), dtype=self.dtype) for r in range(rounds): for i in range(x.shape[0]): ax[i + r * x.shape[0]] = self.random_transform(x[i]) x = ax if self.featurewise_center: self.mean = np.mean(x, axis=(0, self.row_axis, self.col_axis)) broadcast_shape = [1, 1, 1] broadcast_shape[self.channel_axis - 1] = x.shape[self.channel_axis] self.mean = np.reshape(self.mean, broadcast_shape) x -= self.mean if self.featurewise_std_normalization: self.std = np.std(x, axis=(0, self.row_axis, self.col_axis)) broadcast_shape = [1, 1, 1] broadcast_shape[self.channel_axis - 1] = x.shape[self.channel_axis] self.std = np.reshape(self.std, broadcast_shape) x /= (self.std + 1e-6) if self.zca_whitening: if scipy is None: raise ImportError('Using zca_whitening requires SciPy. ' 'Install SciPy.') flat_x = np.reshape( x, (x.shape[0], x.shape[1] * x.shape[2] * x.shape[3])) sigma = np.dot(flat_x.T, flat_x) / flat_x.shape[0] u, s, _ = scipy.linalg.svd(sigma) s_inv = 1. / np.sqrt(s[np.newaxis] + self.zca_epsilon) self.principal_components = (u * s_inv).dot(u.T) class Iterator(IteratorType): """Base class for image data iterators. Every `Iterator` must implement the `_get_batches_of_transformed_samples` method. # Arguments n: Integer, total number of samples in the dataset to loop over. batch_size: Integer, size of a batch. shuffle: Boolean, whether to shuffle the data between epochs. seed: Random seeding for data shuffling. """ def __init__(self, n, batch_size, shuffle, seed): self.n = n self.batch_size = batch_size self.seed = seed self.shuffle = shuffle self.batch_index = 0 self.total_batches_seen = 0 self.lock = threading.Lock() self.index_array = None self.index_generator = self._flow_index() def _set_index_array(self): self.index_array = np.arange(self.n) if self.shuffle: self.index_array = np.random.permutation(self.n) def __getitem__(self, idx): if idx >= len(self): raise ValueError('Asked to retrieve element {idx}, ' 'but the Sequence ' 'has length {length}'.format(idx=idx, length=len(self))) if self.seed is not None: np.random.seed(self.seed + self.total_batches_seen) self.total_batches_seen += 1 if self.index_array is None: self._set_index_array() index_array = self.index_array[self.batch_size * idx: self.batch_size * (idx + 1)] return self._get_batches_of_transformed_samples(index_array) def common_init(self, image_data_generator, target_size, color_mode, data_format, save_to_dir, save_prefix, save_format, subset, interpolation): self.image_data_generator = image_data_generator self.target_size = tuple(target_size) if color_mode not in {'rgb', 'rgba', 'grayscale'}: raise ValueError('Invalid color mode:', color_mode, '; expected "rgb", "rgba", or "grayscale".') self.color_mode = color_mode self.data_format = data_format if self.color_mode == 'rgba': if self.data_format == 'channels_last': self.image_shape = self.target_size + (4,) else: self.image_shape = (4,) + self.target_size elif self.color_mode == 'rgb': if self.data_format == 'channels_last': self.image_shape = self.target_size + (3,) else: self.image_shape = (3,) + self.target_size else: if self.data_format == 'channels_last': self.image_shape = self.target_size + (1,) else: self.image_shape = (1,) + self.target_size self.save_to_dir = save_to_dir self.save_prefix = save_prefix self.save_format = save_format self.interpolation = interpolation if subset is not None: validation_split = self.image_data_generator._validation_split if subset == 'validation': split = (0, validation_split) elif subset == 'training': split = (validation_split, 1) else: raise ValueError( 'Invalid subset name: %s;' 'expected "training" or "validation"' % (subset,)) else: split = None self.split = split self.subset = subset def __len__(self): return (self.n + self.batch_size - 1) // self.batch_size # round up def on_epoch_end(self): self._set_index_array() def reset(self): self.batch_index = 0 def _flow_index(self): # Ensure self.batch_index is 0. self.reset() while 1: if self.seed is not None: np.random.seed(self.seed + self.total_batches_seen) if self.batch_index == 0: self._set_index_array() current_index = (self.batch_index * self.batch_size) % self.n if self.n > current_index + self.batch_size: self.batch_index += 1 else: self.batch_index = 0 self.total_batches_seen += 1 yield self.index_array[current_index: current_index + self.batch_size] def __iter__(self): # Needed if we want to do something like: # for x, y in data_gen.flow(...): return self def __next__(self, *args, **kwargs): return self.next(*args, **kwargs) def _get_batches_of_transformed_samples(self, index_array): """Gets a batch of transformed samples. # Arguments index_array: Array of sample indices to include in batch. # Returns A batch of transformed samples. """ raise NotImplementedError class NumpyArrayIterator(Iterator): """Iterator yielding data from a Numpy array. # Arguments x: Numpy array of input data or tuple. If tuple, the second elements is either another numpy array or a list of numpy arrays, each of which gets passed through as an output without any modifications. y: Numpy array of targets data. image_data_generator: Instance of `ImageDataGenerator` to use for random transformations and normalization. batch_size: Integer, size of a batch. shuffle: Boolean, whether to shuffle the data between epochs. sample_weight: Numpy array of sample weights. seed: Random seed for data shuffling. data_format: String, one of `channels_first`, `channels_last`. save_to_dir: Optional directory where to save the pictures being yielded, in a viewable format. This is useful for visualizing the random transformations being applied, for debugging purposes. save_prefix: String prefix to use for saving sample images (if `save_to_dir` is set). save_format: Format to use for saving sample images (if `save_to_dir` is set). subset: Subset of data (`"training"` or `"validation"`) if validation_split is set in ImageDataGenerator. dtype: Dtype to use for the generated arrays. """ def __init__(self, x, y, image_data_generator, batch_size=32, shuffle=False, sample_weight=None, seed=None, data_format='channels_last', save_to_dir=None, save_prefix='', save_format='png', subset=None, dtype='float32'): self.dtype = dtype if (type(x) is tuple) or (type(x) is list): if type(x[1]) is not list: x_misc = [np.asarray(x[1])] else: x_misc = [np.asarray(xx) for xx in x[1]] x = x[0] for xx in x_misc: if len(x) != len(xx): raise ValueError( 'All of the arrays in `x` ' 'should have the same length. ' 'Found a pair with: len(x[0]) = %s, len(x[?]) = %s' % (len(x), len(xx))) else: x_misc = [] if y is not None and len(x) != len(y): raise ValueError('`x` (images tensor) and `y` (labels) ' 'should have the same length. ' 'Found: x.shape = %s, y.shape = %s' % (np.asarray(x).shape, np.asarray(y).shape)) if sample_weight is not None and len(x) != len(sample_weight): raise ValueError('`x` (images tensor) and `sample_weight` ' 'should have the same length. ' 'Found: x.shape = %s, sample_weight.shape = %s' % (np.asarray(x).shape, np.asarray(sample_weight).shape)) if subset is not None: if subset not in {'training', 'validation'}: raise ValueError('Invalid subset name:', subset, '; expected "training" or "validation".') split_idx = int(len(x) * image_data_generator._validation_split) if not np.array_equal( np.unique(y[:split_idx]), np.unique(y[split_idx:])): raise ValueError('Training and validation subsets ' 'have different number of classes after ' 'the split. If your numpy arrays are ' 'sorted by the label, you might want ' 'to shuffle them.') if subset == 'validation': x = x[:split_idx] x_misc = [np.asarray(xx[:split_idx]) for xx in x_misc] if y is not None: y = y[:split_idx] else: x = x[split_idx:] x_misc = [np.asarray(xx[split_idx:]) for xx in x_misc] if y is not None: y = y[split_idx:] self.x = np.asarray(x, dtype=self.dtype) self.x_misc = x_misc if self.x.ndim != 4: raise ValueError('Input data in `NumpyArrayIterator` ' 'should have rank 4. You passed an array ' 'with shape', self.x.shape) channels_axis = 3 if data_format == 'channels_last' else 1 if self.x.shape[channels_axis] not in {1, 3, 4}: warnings.warn('NumpyArrayIterator is set to use the ' 'data format convention "' + data_format + '" ' '(channels on axis ' + str(channels_axis) + '), i.e. expected either 1, 3, or 4 ' 'channels on axis ' + str(channels_axis) + '. ' 'However, it was passed an array with shape ' + str(self.x.shape) + ' (' + str(self.x.shape[channels_axis]) + ' channels).') if y is not None: self.y = np.asarray(y) else: self.y = None if sample_weight is not None: self.sample_weight = np.asarray(sample_weight) else: self.sample_weight = None self.image_data_generator = image_data_generator self.data_format = data_format self.save_to_dir = save_to_dir self.save_prefix = save_prefix self.save_format = save_format super(NumpyArrayIterator, self).__init__(x.shape[0], batch_size, shuffle, seed) def _get_batches_of_transformed_samples(self, index_array): batch_x = np.zeros(tuple([len(index_array)] + list(self.x.shape)[1:]), dtype=self.dtype) for i, j in enumerate(index_array): x = self.x[j] params = self.image_data_generator.get_random_transform(x.shape) x = self.image_data_generator.apply_transform( x.astype(self.dtype), params) x = self.image_data_generator.standardize(x) batch_x[i] = x if self.save_to_dir: for i, j in enumerate(index_array): img = array_to_img(batch_x[i], self.data_format, scale=True) fname = '{prefix}_{index}_{hash}.{format}'.format( prefix=self.save_prefix, index=j, hash=np.random.randint(1e4), format=self.save_format) img.save(os.path.join(self.save_to_dir, fname)) batch_x_miscs = [xx[index_array] for xx in self.x_misc] output = (batch_x if batch_x_miscs == [] else [batch_x] + batch_x_miscs,) if self.y is None: return output[0] output += (self.y[index_array],) if self.sample_weight is not None: output += (self.sample_weight[index_array],) return output def next(self): """For python 2.x. # Returns The next batch. """ # Keeps under lock only the mechanism which advances # the indexing of each batch. with self.lock: index_array = next(self.index_generator) # The transformation of images is not under thread lock # so it can be done in parallel return self._get_batches_of_transformed_samples(index_array) def _iter_valid_files(directory, white_list_formats, follow_links): """Iterates on files with extension in `white_list_formats` contained in `directory`. # Arguments directory: Absolute path to the directory containing files to be counted white_list_formats: Set of strings containing allowed extensions for the files to be counted. follow_links: Boolean. # Yields Tuple of (root, filename) with extension in `white_list_formats`. """ def _recursive_list(subpath): return sorted(os.walk(subpath, followlinks=follow_links), key=lambda x: x[0]) for root, _, files in _recursive_list(directory): for fname in sorted(files): for extension in white_list_formats: if fname.lower().endswith('.tiff'): warnings.warn('Using \'.tiff\' files with multiple bands ' 'will cause distortion. ' 'Please verify your output.') if fname.lower().endswith('.' + extension): yield root, fname def _list_valid_filenames_in_directory(directory, white_list_formats, split, class_indices, follow_links, df=False): """Lists paths of files in `subdir` with extensions in `white_list_formats`. # Arguments directory: absolute path to a directory containing the files to list. The directory name is used as class label and must be a key of `class_indices`. white_list_formats: set of strings containing allowed extensions for the files to be counted. split: tuple of floats (e.g. `(0.2, 0.6)`) to only take into account a certain fraction of files in each directory. E.g.: `segment=(0.6, 1.0)` would only account for last 40 percent of images in each directory. class_indices: dictionary mapping a class name to its index. follow_links: boolean. df: boolean # Returns classes: a list of class indices(returns only if `df=False`) filenames: if `df=False`,returns the path of valid files in `directory`, relative from `directory`'s parent (e.g., if `directory` is "dataset/class1", the filenames will be `["class1/file1.jpg", "class1/file2.jpg", ...]`). if `df=True`, returns only the filenames that are found inside the provided directory (e.g., if `directory` is "dataset/", the filenames will be `["file1.jpg", "file2.jpg", ...]`). """ dirname = os.path.basename(directory) if split: num_files = len(list( _iter_valid_files(directory, white_list_formats, follow_links))) start, stop = int(split[0] * num_files), int(split[1] * num_files) valid_files = list( _iter_valid_files( directory, white_list_formats, follow_links))[start: stop] else: valid_files = _iter_valid_files( directory, white_list_formats, follow_links) if df: filenames = [] for root, fname in valid_files: filenames.append(os.path.basename(fname)) return filenames classes = [] filenames = [] for root, fname in valid_files: classes.append(class_indices[dirname]) absolute_path = os.path.join(root, fname) relative_path = os.path.join( dirname, os.path.relpath(absolute_path, directory)) filenames.append(relative_path) return classes, filenames class DirectoryIterator(Iterator): """Iterator capable of reading images from a directory on disk. # Arguments directory: Path to the directory to read images from. Each subdirectory in this directory will be considered to contain images from one class, or alternatively you could specify class subdirectories via the `classes` argument. image_data_generator: Instance of `ImageDataGenerator` to use for random transformations and normalization. target_size: tuple of integers, dimensions to resize input images to. color_mode: One of `"rgb"`, `"rgba"`, `"grayscale"`. Color mode to read images. classes: Optional list of strings, names of subdirectories containing images from each class (e.g. `["dogs", "cats"]`). It will be computed automatically if not set. class_mode: Mode for yielding the targets: `"binary"`: binary targets (if there are only two classes), `"categorical"`: categorical targets, `"sparse"`: integer targets, `"input"`: targets are images identical to input images (mainly used to work with autoencoders), `None`: no targets get yielded (only input images are yielded). batch_size: Integer, size of a batch. shuffle: Boolean, whether to shuffle the data between epochs. seed: Random seed for data shuffling. data_format: String, one of `channels_first`, `channels_last`. save_to_dir: Optional directory where to save the pictures being yielded, in a viewable format. This is useful for visualizing the random transformations being applied, for debugging purposes. save_prefix: String prefix to use for saving sample images (if `save_to_dir` is set). save_format: Format to use for saving sample images (if `save_to_dir` is set). subset: Subset of data (`"training"` or `"validation"`) if validation_split is set in ImageDataGenerator. interpolation: Interpolation method used to resample the image if the target size is different from that of the loaded image. Supported methods are "nearest", "bilinear", and "bicubic". If PIL version 1.1.3 or newer is installed, "lanczos" is also supported. If PIL version 3.4.0 or newer is installed, "box" and "hamming" are also supported. By default, "nearest" is used. dtype: Dtype to use for generated arrays. """ def __init__(self, directory, image_data_generator, target_size=(256, 256), color_mode='rgb', classes=None, class_mode='categorical', batch_size=32, shuffle=True, seed=None, data_format='channels_last', save_to_dir=None, save_prefix='', save_format='png', follow_links=False, subset=None, interpolation='nearest', dtype='float32'): super(DirectoryIterator, self).common_init(image_data_generator, target_size, color_mode, data_format, save_to_dir, save_prefix, save_format, subset, interpolation) self.directory = directory self.classes = classes if class_mode not in {'categorical', 'binary', 'sparse', 'input', None}: raise ValueError('Invalid class_mode:', class_mode, '; expected one of "categorical", ' '"binary", "sparse", "input"' ' or None.') self.class_mode = class_mode self.dtype = dtype white_list_formats = {'png', 'jpg', 'jpeg', 'bmp', 'ppm', 'tif', 'tiff'} # First, count the number of samples and classes. self.samples = 0 if not classes: classes = [] for subdir in sorted(os.listdir(directory)): if os.path.isdir(os.path.join(directory, subdir)): classes.append(subdir) self.num_classes = len(classes) self.class_indices = dict(zip(classes, range(len(classes)))) pool = multiprocessing.pool.ThreadPool() # Second, build an index of the images # in the different class subfolders. results = [] self.filenames = [] i = 0 for dirpath in (os.path.join(directory, subdir) for subdir in classes): results.append( pool.apply_async(_list_valid_filenames_in_directory, (dirpath, white_list_formats, self.split, self.class_indices, follow_links))) classes_list = [] for res in results: classes, filenames = res.get() classes_list.append(classes) self.filenames += filenames self.samples = len(self.filenames) self.classes = np.zeros((self.samples,), dtype='int32') for classes in classes_list: self.classes[i:i + len(classes)] = classes i += len(classes) print('Found %d images belonging to %d classes.' % (self.samples, self.num_classes)) pool.close() pool.join() super(DirectoryIterator, self).__init__(self.samples, batch_size, shuffle, seed) def _get_batches_of_transformed_samples(self, index_array): batch_x = np.zeros( (len(index_array),) + self.image_shape, dtype=self.dtype) # build batch of image data for i, j in enumerate(index_array): fname = self.filenames[j] img = load_img(os.path.join(self.directory, fname), color_mode=self.color_mode, target_size=self.target_size, interpolation=self.interpolation) x = img_to_array(img, data_format=self.data_format) # Pillow images should be closed after `load_img`, # but not PIL images. if hasattr(img, 'close'): img.close() params = self.image_data_generator.get_random_transform(x.shape) x = self.image_data_generator.apply_transform(x, params) x = self.image_data_generator.standardize(x) batch_x[i] = x # optionally save augmented images to disk for debugging purposes if self.save_to_dir: for i, j in enumerate(index_array): img = array_to_img(batch_x[i], self.data_format, scale=True) fname = '{prefix}_{index}_{hash}.{format}'.format( prefix=self.save_prefix, index=j, hash=np.random.randint(1e7), format=self.save_format) img.save(os.path.join(self.save_to_dir, fname)) # build batch of labels if self.class_mode == 'input': batch_y = batch_x.copy() elif self.class_mode == 'sparse': batch_y = self.classes[index_array] elif self.class_mode == 'binary': batch_y = self.classes[index_array].astype(self.dtype) elif self.class_mode == 'categorical': batch_y = np.zeros( (len(batch_x), self.num_classes), dtype=self.dtype) for i, label in enumerate(self.classes[index_array]): batch_y[i, label] = 1. else: return batch_x return batch_x, batch_y def next(self): """For python 2.x. # Returns The next batch. """ with self.lock: index_array = next(self.index_generator) # The transformation of images is not under thread lock # so it can be done in parallel return self._get_batches_of_transformed_samples(index_array) class DataFrameIterator(Iterator): """Iterator capable of reading images from a directory on disk through a dataframe. # Arguments dataframe: Pandas dataframe containing the filenames of the images in a column and classes in another or column/s that can be fed as raw target data. directory: Path to the directory to read images from. Each subdirectory in this directory will be considered to contain images from one class, or alternatively you could specify class subdirectories via the `classes` argument. if used with dataframe,this will be the directory to under which all the images are present. image_data_generator: Instance of `ImageDataGenerator` to use for random transformations and normalization. x_col: Column in dataframe that contains all the filenames. y_col: Column/s in dataframe that has the target data. has_ext: bool, Whether the filenames in x_col has extensions or not. target_size: tuple of integers, dimensions to resize input images to. color_mode: One of `"rgb"`, `"rgba"`, `"grayscale"`. Color mode to read images. classes: Optional list of strings, names of each class (e.g. `["dogs", "cats"]`). It will be computed automatically if not set. class_mode: Mode for yielding the targets: `"binary"`: binary targets (if there are only two classes), `"categorical"`: categorical targets, `"sparse"`: integer targets, `"input"`: targets are images identical to input images (mainly used to work with autoencoders), `"other"`: targets are the data(numpy array) of y_col data `None`: no targets get yielded (only input images are yielded). batch_size: Integer, size of a batch. shuffle: Boolean, whether to shuffle the data between epochs. seed: Random seed for data shuffling. data_format: String, one of `channels_first`, `channels_last`. save_to_dir: Optional directory where to save the pictures being yielded, in a viewable format. This is useful for visualizing the random transformations being applied, for debugging purposes. save_prefix: String prefix to use for saving sample images (if `save_to_dir` is set). save_format: Format to use for saving sample images (if `save_to_dir` is set). subset: Subset of data (`"training"` or `"validation"`) if validation_split is set in ImageDataGenerator. interpolation: Interpolation method used to resample the image if the target size is different from that of the loaded image. Supported methods are "nearest", "bilinear", and "bicubic". If PIL version 1.1.3 or newer is installed, "lanczos" is also supported. If PIL version 3.4.0 or newer is installed, "box" and "hamming" are also supported. By default, "nearest" is used. """ def __init__(self, dataframe, directory, image_data_generator, x_col="filenames", y_col="class", has_ext=True, target_size=(256, 256), color_mode='rgb', classes=None, class_mode='categorical', batch_size=32, shuffle=True, seed=None, data_format=None, save_to_dir=None, save_prefix='', save_format='png', follow_links=False, subset=None, interpolation='nearest', dtype='float32'): super(DataFrameIterator, self).common_init(image_data_generator, target_size, color_mode, data_format, save_to_dir, save_prefix, save_format, subset, interpolation) try: import pandas as pd except ImportError: raise ImportError('Install pandas to use flow_from_dataframe.') if type(x_col) != str: raise ValueError("x_col must be a string.") if type(has_ext) != bool: raise ValueError("has_ext must be either True if filenames in" " x_col has extensions,else False.") self.df = dataframe.drop_duplicates(x_col) self.df[x_col] = self.df[x_col].astype(str) self.directory = directory self.classes = classes if class_mode not in {'categorical', 'binary', 'sparse', 'input', 'other', None}: raise ValueError('Invalid class_mode:', class_mode, '; expected one of "categorical", ' '"binary", "sparse", "input"' '"other" or None.') self.class_mode = class_mode self.dtype = dtype white_list_formats = {'png', 'jpg', 'jpeg', 'bmp', 'ppm', 'tif', 'tiff'} # First, count the number of samples and classes. self.samples = 0 if not classes: classes = [] if class_mode not in ["other", "input", None]: classes = list(self.df[y_col].unique()) else: if class_mode in ["other", "input", None]: raise ValueError('classes cannot be set if class_mode' ' is either "other" or "input" or None.') self.num_classes = len(classes) self.class_indices = dict(zip(classes, range(len(classes)))) # Second, build an index of the images. self.filenames = [] self.classes = np.zeros((self.samples,), dtype='int32') filenames = _list_valid_filenames_in_directory( directory, white_list_formats, self.split, class_indices=self.class_indices, follow_links=follow_links, df=True) if has_ext: ext_exist = False for ext in white_list_formats: if self.df.loc[0, x_col].endswith("." + ext): ext_exist = True break if not ext_exist: raise ValueError('has_ext is set to True but' ' extension not found in x_col') temp_df = pd.DataFrame({x_col: filenames}, dtype=str) temp_df = self.df.merge(temp_df, how='right', on=x_col) temp_df = temp_df.set_index(x_col) temp_df = temp_df.reindex(filenames) temp_df = temp_df.dropna() self.filenames = list(temp_df.index) else: without_ext_with = {f[:-1 * (len(f.split(".")[-1]) + 1)]: f for f in filenames} filenames_without_ext = [f[:-1 * (len(f.split(".")[-1]) + 1)] for f in filenames] temp_df = pd.DataFrame({x_col: filenames_without_ext}, dtype=str) temp_df = self.df.merge(temp_df, how='right', on=x_col) temp_df = temp_df.set_index(x_col) temp_df = temp_df.reindex(filenames_without_ext) temp_df = temp_df.dropna() self.filenames = [without_ext_with[f] for f in temp_df.index] self.df = temp_df.copy() if class_mode not in ["other", "input", None]: classes = temp_df[y_col].values self.classes = np.array([self.class_indices[cls] for cls in classes]) elif class_mode == "other": self.data = self.df[y_col].values if type(y_col) == str: y_col = [y_col] if "object" in list(self.df[y_col].dtypes): raise TypeError("y_col column/s must be numeric datatypes.") self.samples = len(self.filenames) if self.num_classes > 0: print('Found %d images belonging to %d classes.' % (self.samples, self.num_classes)) else: print('Found %d images.' % self.samples) super(DataFrameIterator, self).__init__(self.samples, batch_size, shuffle, seed) def _get_batches_of_transformed_samples(self, index_array): batch_x = np.zeros( (len(index_array),) + self.image_shape, dtype=self.dtype) # build batch of image data for i, j in enumerate(index_array): fname = self.filenames[j] img = load_img(os.path.join(self.directory, fname), color_mode=self.color_mode, target_size=self.target_size, interpolation=self.interpolation) x = img_to_array(img, data_format=self.data_format) # Pillow images should be closed after `load_img`, # but not PIL images. if hasattr(img, 'close'): img.close() params = self.image_data_generator.get_random_transform(x.shape) x = self.image_data_generator.apply_transform(x, params) x = self.image_data_generator.standardize(x) batch_x[i] = x # optionally save augmented images to disk for debugging purposes if self.save_to_dir: for i, j in enumerate(index_array): img = array_to_img(batch_x[i], self.data_format, scale=True) fname = '{prefix}_{index}_{hash}.{format}'.format( prefix=self.save_prefix, index=j, hash=np.random.randint(1e7), format=self.save_format) img.save(os.path.join(self.save_to_dir, fname)) # build batch of labels if self.class_mode == 'input': batch_y = batch_x.copy() elif self.class_mode == 'sparse': batch_y = self.classes[index_array] elif self.class_mode == 'binary': batch_y = self.classes[index_array].astype(self.dtype) elif self.class_mode == 'categorical': batch_y = np.zeros( (len(batch_x), self.num_classes), dtype=self.dtype) for i, label in enumerate(self.classes[index_array]): batch_y[i, label] = 1. elif self.class_mode == 'other': batch_y = self.data[index_array] else: return batch_x return batch_x, batch_y def next(self): """For python 2.x. # Returns The next batch. """ with self.lock: index_array = next(self.index_generator) # The transformation of images is not under thread lock # so it can be done in parallel return self._get_batches_of_transformed_samples(index_array) Keras_Preprocessing-1.0.5/README.md0000644000000000116100000000117013303633532016501 0ustar rooteng00000000000000# Keras Preprocessing [![Build Status](https://travis-ci.org/keras-team/keras-preprocessing.svg?branch=master)](https://travis-ci.org/keras-team/keras-preprocessing) Keras Preprocessing is the data preprocessing and data augmentation module of the Keras deep learning library. It provides utilities for working with image data, text data, and sequence data. Read the documentation at: https://keras.io/ Keras Preprocessing may be imported directly from an up-to-date installation of Keras: ``` from keras import preprocessing ``` Keras Preprocessing is compatible with Python 2.7-3.6 and is distributed under the MIT license. Keras_Preprocessing-1.0.5/setup.py0000644000000000116100000000356713353522226016752 0ustar rooteng00000000000000from setuptools import setup from setuptools import find_packages long_description = ''' Keras Preprocessing is the data preprocessing and data augmentation module of the Keras deep learning library. It provides utilities for working with image data, text data, and sequence data. Read the documentation at: https://keras.io/ Keras Preprocessing may be imported directly from an up-to-date installation of Keras: ``` from keras import preprocessing ``` Keras Preprocessing is compatible with Python 2.7-3.6 and is distributed under the MIT license. ''' setup(name='Keras_Preprocessing', version='1.0.5', description='Easy data preprocessing and data augmentation ' 'for deep learning models', long_description=long_description, author='Keras Team', url='https://github.com/keras-team/keras-preprocessing', download_url='https://github.com/keras-team/' 'keras-preprocessing/tarball/1.0.5', license='MIT', install_requires=['numpy>=1.9.1', 'six>=1.9.0'], extras_require={ 'tests': ['pytest', 'pytest-pep8', 'pytest-xdist', 'pytest-cov'], 'image': ['scipy>=0.14'], }, classifiers=[ 'Development Status :: 5 - Production/Stable', 'Intended Audience :: Developers', 'Intended Audience :: Education', 'Intended Audience :: Science/Research', 'License :: OSI Approved :: MIT License', 'Programming Language :: Python :: 2', 'Programming Language :: Python :: 2.7', 'Programming Language :: Python :: 3', 'Programming Language :: Python :: 3.6', 'Topic :: Software Development :: Libraries', 'Topic :: Software Development :: Libraries :: Python Modules' ], packages=find_packages()) Keras_Preprocessing-1.0.5/setup.cfg0000644000000000116100000000004613353522261017045 0ustar rooteng00000000000000[egg_info] tag_build = tag_date = 0