Python keras.utils() Examples

def load_and_preprocess_data_3():
    # The data, shuffled and split between train and test sets:
    (X_train, y_train), (x_test, y_test) = cifar10.load_data()
    logging.debug('X_train shape: {}'.format(X_train.shape))
    logging.debug('train samples: {}'.format(X_train.shape[0]))
    logging.debug('test samples: {}'.format(x_test.shape[0]))

    # Convert class vectors to binary class matrices.
    y_train = keras.utils.to_categorical(y_train, num_classes)
    y_test = keras.utils.to_categorical(y_test, num_classes)

    X_train = X_train.astype('float32')
    x_test = x_test.astype('float32')
    X_train /= 255
    x_test /= 255

    input_shape = X_train[0].shape
    logging.debug('input_shape {}'.format(input_shape))
    input_shape = X_train.shape[1:]
    logging.debug('input_shape {}'.format(input_shape))

    return X_train, x_test, y_train, y_test, input_shape 

def replace_unknown_words(self, src_word_seq, trg_word_seq, hard_alignment, unk_symbol,
                              heuristic=0, mapping=None, verbose=0):
        """
        Replaces unknown words from the target sentence according to some heuristic.
        Borrowed from: https://github.com/sebastien-j/LV_groundhog/blob/master/experiments/nmt/replace_UNK.py
        :param src_word_seq: Source sentence words
        :param trg_word_seq: Hypothesis words
        :param hard_alignment: Target-Source alignments
        :param unk_symbol: Symbol in trg_word_seq to replace
        :param heuristic: Heuristic (0, 1, 2)
        :param mapping: External alignment dictionary
        :param verbose: Verbosity level
        :return: trg_word_seq with replaced unknown words
        """
        print "WARNING!: deprecated function, use utils.replace_unknown_words() instead"
        return replace_unknown_words(src_word_seq, trg_word_seq, hard_alignment, unk_symbol,
                                     heuristic=heuristic, mapping=mapping, verbose=verbose) 

def replace_unknown_words(self, src_word_seq, trg_word_seq, hard_alignment, unk_symbol,
                              heuristic=0, mapping=None, verbose=0):
        """
        Replaces unknown words from the target sentence according to some heuristic.
        Borrowed from: https://github.com/sebastien-j/LV_groundhog/blob/master/experiments/nmt/replace_UNK.py
        :param src_word_seq: Source sentence words
        :param trg_word_seq: Hypothesis words
        :param hard_alignment: Target-Source alignments
        :param unk_symbol: Symbol in trg_word_seq to replace
        :param heuristic: Heuristic (0, 1, 2)
        :param mapping: External alignment dictionary
        :param verbose: Verbosity level
        :return: trg_word_seq with replaced unknown words
        """
        print "WARNING!: deprecated function, use utils.replace_unknown_words() instead"
        return replace_unknown_words(src_word_seq, trg_word_seq, hard_alignment, unk_symbol,
                                     heuristic=heuristic, mapping=mapping, verbose=verbose) 

def __data_generation(self,list_files,labels):
        'Generates data containing batch_size samples' # X : (n_samples, *dim, n_channels)
        # Initialization

        X = np.empty((len(list_files),self.dim[0],self.dim[1],self.dim[2]))
        y = np.empty((len(list_files)),dtype=int)
     #   print(X.shape,y.shape)

        # Generate data
        k = -1 
        for i,f in enumerate(list_files):
            #      print(f)
            img = get_im_cv2(f,dim=self.dim[0])
            img = pre_process(img)
            label = labels[i]
            #label = keras.utils.np_utils.to_categorical(label,self.n_classes)
            X[i,] = img
            y[i,] = label
       # print(X.shape,y.shape)    
        return X,y 

def generate_samples(self, T, g_data, num, output_file):
        '''
        Generate sample sentences to output file
        # Arguments:
            T: int, max time steps
            g_data: SeqGAN.utils.GeneratorPretrainingGenerator
            num: int, number of sentences
            output_file: str, path
        '''
        sentences=[]
        for _ in range(num // self.B + 1):
            actions = self.sampling_sentence(T)
            actions_list = actions.tolist()
            for sentence_id in actions_list:
                sentence = [g_data.id2word[action] for action in sentence_id]
                sentences.append(sentence)
        output_str = ''
        for i in range(num):
            output_str += ' '.join(sentences[i]) + '\n'
        with open(output_file, 'w', encoding='utf-8') as f:
            f.write(output_str) 

def confusion_matrix(self, percentage=True, labeled=True):
        """Compute confusion matrix to evaluate the test accuracy of the classification"""
        if not self.classification:
            raise NotImplementedError("Confusion matrix works only when it is a classification problem")
        y_pred = self.model.predict_classes(self.X_test)[0]
        # invert from keras.utils.to_categorical
        y_test = np.array([ np.argmax(y, axis=None, out=None) for y in self.y_test[0] ])
        matrix = confusion_matrix(y_test, y_pred, labels=[self.emotions2int[e] for e in self.emotions]).astype(np.float32)
        if percentage:
            for i in range(len(matrix)):
                matrix[i] = matrix[i] / np.sum(matrix[i])
            # make it percentage
            matrix *= 100
        if labeled:
            matrix = pd.DataFrame(matrix, index=[ f"true_{e}" for e in self.emotions ],
                                    columns=[ f"predicted_{e}" for e in self.emotions ])
        return matrix 

def inject_tfkeras_modules(func):
    import tensorflow.keras as tfkeras
    @functools.wraps(func)
    def wrapper(*args, **kwargs):
        kwargs['backend'] = tfkeras.backend
        kwargs['layers'] = tfkeras.layers
        kwargs['models'] = tfkeras.models
        kwargs['utils'] = tfkeras.utils
        return func(*args, **kwargs)

    return wrapper 

def get_submodules_from_kwargs(kwargs):
    backend = keras.backend
    layers = keras.backend
    models = keras.models
    keras_utils = keras.utils

    return backend, layers, models, keras_utils 

def inject_keras_modules(func):
    import keras
    @functools.wraps(func)
    def wrapper(*args, **kwargs):
        kwargs['backend'] = keras.backend
        kwargs['layers'] = keras.layers
        kwargs['models'] = keras.models
        kwargs['utils'] = keras.utils
        return func(*args, **kwargs)

    return wrapper 

def get_preprocessing(name):
    preprocess_input = Backbones.get_preprocessing(name)
    # add bakcend, models, layers, utils submodules in kwargs
    preprocess_input = inject_global_submodules(preprocess_input)
    # delete other kwargs
    # keras-applications preprocessing raise an error if something
    # except `backend`, `layers`, `models`, `utils` passed in kwargs
    preprocess_input = filter_kwargs(preprocess_input)
    return preprocess_input 

def filter_kwargs(func):
    @functools.wraps(func)
    def wrapper(*args, **kwargs):
        new_kwargs = {k: v for k, v in kwargs.items() if k in ['backend', 'layers', 'models', 'utils']}
        return func(*args, **new_kwargs)

    return wrapper 

def inject_global_submodules(func):
    @functools.wraps(func)
    def wrapper(*args, **kwargs):
        kwargs['backend'] = _KERAS_BACKEND
        kwargs['layers'] = _KERAS_LAYERS
        kwargs['models'] = _KERAS_MODELS
        kwargs['utils'] = _KERAS_UTILS
        return func(*args, **kwargs)

    return wrapper 

def init_tfkeras_custom_objects():
    import tensorflow.keras as tfkeras
    from . import model

    custom_objects = {
        'swish': inject_tfkeras_modules(model.get_swish)(),
        'FixedDropout': inject_tfkeras_modules(model.get_dropout)()
    }

    tfkeras.utils.get_custom_objects().update(custom_objects) 

def inject_tfkeras_modules(func):
    import tensorflow.keras as tfkeras
    @functools.wraps(func)
    def wrapper(*args, **kwargs):
        kwargs['backend'] = tfkeras.backend
        kwargs['layers'] = tfkeras.layers
        kwargs['models'] = tfkeras.models
        kwargs['utils'] = tfkeras.utils
        return func(*args, **kwargs)

    return wrapper 

def get_submodules_from_kwargs(kwargs):
    backend = keras.backend
    layers = keras.backend
    models = keras.models
    keras_utils = keras.utils

    return backend, layers, models, keras_utils 

def init_tfkeras_custom_objects():
    import tensorflow.keras as tfkeras
    import efficientnet as model

    custom_objects = {
        'swish': inject_tfkeras_modules(model.get_swish)(),
        'FixedDropout': inject_tfkeras_modules(model.get_dropout)()
    }

    tfkeras.utils.get_custom_objects().update(custom_objects) 

def create_model(self):
        
        dat_input = Input(shape=(self.tdatlen,))
        com_input = Input(shape=(self.comlen,))
        sml_input = Input(shape=(self.smllen,))
        
        ee = Embedding(output_dim=self.embdims, input_dim=self.tdatvocabsize, mask_zero=False)(dat_input)
        se = Embedding(output_dim=self.smldims, input_dim=self.smlvocabsize, mask_zero=False)(sml_input)

        se_enc = CuDNNGRU(self.recdims, return_state=True, return_sequences=True)
        seout, state_sml = se_enc(se)

        enc = CuDNNGRU(self.recdims, return_state=True, return_sequences=True)
        encout, state_h = enc(ee, initial_state=state_sml)
        
        de = Embedding(output_dim=self.embdims, input_dim=self.comvocabsize, mask_zero=False)(com_input)
        dec = CuDNNGRU(self.recdims, return_sequences=True)
        decout = dec(de, initial_state=state_h)

        attn = dot([decout, encout], axes=[2, 2])
        attn = Activation('softmax')(attn)
        context = dot([attn, encout], axes=[2, 1])

        ast_attn = dot([decout, seout], axes=[2, 2])
        ast_attn = Activation('softmax')(ast_attn)
        ast_context = dot([ast_attn, seout], axes=[2, 1])

        context = concatenate([context, decout, ast_context])

        out = TimeDistributed(Dense(self.recdims, activation="relu"))(context)

        out = Flatten()(out)
        out = Dense(self.comvocabsize, activation="softmax")(out)
        
        model = Model(inputs=[dat_input, com_input, sml_input], outputs=out)

        if self.config['multigpu']:
            model = keras.utils.multi_gpu_model(model, gpus=2)
        
        model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
        return self.config, model 

def get_preds(model):
    size = model.input_shape[1]

    filename = os.path.join(os.path.dirname(__file__),
                            'data', '565727409_61693c5e14.jpg')

    batch = KE.preprocess_input(img_to_array(load_img(
                                filename, target_size=(size, size))))

    batch = np.expand_dims(batch, 0)

    pred = decode_predictions(model.predict(batch),
                              backend=K, utils=utils)

    return pred 

def inject_keras_modules(func):
    import keras
    @functools.wraps(func)
    def wrapper(*args, **kwargs):
        kwargs['backend'] = keras.backend
        kwargs['layers'] = keras.layers
        kwargs['models'] = keras.models
        kwargs['utils'] = keras.utils
        return func(*args, **kwargs)

    return wrapper 

def get_submodules_from_kwargs(kwargs):
    backend = kwargs.get('backend', _KERAS_BACKEND)
    layers = kwargs.get('layers', _KERAS_LAYERS)
    models = kwargs.get('models', _KERAS_MODELS)
    utils = kwargs.get('utils', _KERAS_UTILS)
    for key in kwargs.keys():
        if key not in ['backend', 'layers', 'models', 'utils']:
            raise TypeError('Invalid keyword argument: %s', key)
    return backend, layers, models, utils 

def decode_predictions_one_hot(self, preds, index2word, verbose=0):
        """
        Decodes predictions following a one-hot codification.
        :param preds: Predictions codified as one-hot vectors.
        :param index2word: Mapping from word indices into word characters.
        :param verbose: Verbosity level, by default 0.
        :return: List of decoded predictions
        """
        print "WARNING!: deprecated function, use utils.decode_predictions_one_hot() instead"
        return decode_predictions_one_hot(preds, index2word, verbose=verbose) 

def one_hot_2_indices(self, preds, pad_sequences=True, verbose=0):
        """
        Converts a one-hot codification into a index-based one
        :param preds: Predictions codified as one-hot vectors.
        :param verbose: Verbosity level, by default 0.
        :return: List of convertedpredictions
        """
        print "WARNING!: deprecated function, use utils.one_hot_2_indices() instead"
        return one_hot_2_indices(preds, pad_sequences=pad_sequences, verbose=verbose) 

def decode_predictions(self, preds, temperature, index2word, sampling_type, verbose=0):
        """
        Decodes predictions
        :param preds: Predictions codified as the output of a softmax activation function.
        :param temperature: Temperature for sampling.
        :param index2word: Mapping from word indices into word characters.
        :param sampling_type: 'max_likelihood' or 'multinomial'.
        :param verbose: Verbosity level, by default 0.
        :return: List of decoded predictions.
        """
        print "WARNING!: deprecated function, use utils.decode_predictions() instead"
        return decode_predictions(preds, temperature, index2word, sampling_type, verbose=verbose) 

def sampling(self, scores, sampling_type='max_likelihood', temperature=1.0):
        """
        Sampling words (each sample is drawn from a categorical distribution).
        Or picks up words that maximize the likelihood.
        :param scores: array of size #samples x #classes;
        every entry determines a score for sample i having class j
        :param sampling_type:
        :param temperature: Temperature for the predictions. The higher, the flatter probabilities. Hence more random outputs.
        :return: set of indices chosen as output, a vector of size #samples
        """
        print "WARNING!: deprecated function, use utils.sampling() instead"
        return sampling(scores, sampling_type=sampling_type, temperature=temperature) 

def sample(self, a, temperature=1.0):
        """
        Helper function to sample an index from a probability array
        :param a: Probability array
        :param temperature: The higher, the flatter probabilities. Hence more random outputs.
        :return:
        """

        print "WARNING!: deprecated function, use utils.sample() instead"
        return sample(a, temperature=temperature) 

def decode_predictions_one_hot(self, preds, index2word, verbose=0):
        """
        Decodes predictions following a one-hot codification.
        :param preds: Predictions codified as one-hot vectors.
        :param index2word: Mapping from word indices into word characters.
        :param verbose: Verbosity level, by default 0.
        :return: List of decoded predictions
        """
        print "WARNING!: deprecated function, use utils.decode_predictions_one_hot() instead"
        return decode_predictions_one_hot(preds, index2word, verbose=verbose) 

def decode_predictions_beam_search(self, preds, index2word, alphas=None, heuristic=0,
                                       x_text=None, unk_symbol='<unk>', pad_sequences=False,
                                       mapping=None, verbose=0):
        """
        Decodes predictions from the BeamSearch method.
        :param preds: Predictions codified as word indices.
        :param index2word: Mapping from word indices into word characters.
        :param pad_sequences: Whether we should make a zero-pad on the input sequence.
        :param verbose: Verbosity level, by default 0.
        :return: List of decoded predictions
        """
        print "WARNING!: deprecated function, use utils.decode_predictions_beam_search() instead"
        return decode_predictions_beam_search(preds, index2word, alphas=alphas, heuristic=heuristic,
                                              x_text=x_text, unk_symbol=unk_symbol, pad_sequences=pad_sequences,
                                              mapping=mapping, verbose=0) 

def model_mnist(logits=False, input_ph=None, img_rows=28, img_cols=28,
                nb_filters=64, nb_classes=10):
    warnings.warn("`utils_mnist.model_mnist` is deprecated. Switch to"
                  "`utils.cnn_model`. `utils_mnist.model_mnist` will "
                  "be removed after 2017-08-17.")
    return utils.cnn_model(logits=logits, input_ph=input_ph,
                           img_rows=img_rows, img_cols=img_cols,
                           nb_filters=nb_filters, nb_classes=nb_classes) 

def decode_predictions(self, preds, temperature, index2word, sampling_type, verbose=0):
        """
        Decodes predictions
        :param preds: Predictions codified as the output of a softmax activation function.
        :param temperature: Temperature for sampling.
        :param index2word: Mapping from word indices into word characters.
        :param sampling_type: 'max_likelihood' or 'multinomial'.
        :param verbose: Verbosity level, by default 0.
        :return: List of decoded predictions.
        """
        print "WARNING!: deprecated function, use utils.decode_predictions() instead"
        return decode_predictions(preds, temperature, index2word, sampling_type, verbose=verbose) 

def init_keras_custom_objects():
    import keras
    import efficientnet as model

    custom_objects = {
        'swish': inject_keras_modules(model.get_swish)(),
        'FixedDropout': inject_keras_modules(model.get_dropout)()
    }

    keras.utils.generic_utils.get_custom_objects().update(custom_objects)