Python tensorflow.python.keras.utils.to_categorical() Examples

The following are 7 code examples of tensorflow.python.keras.utils.to_categorical(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module tensorflow.python.keras.utils , or try the search function .
Example #1
Source File: train_variable_length_seq.py    From attention_keras with MIT License 6 votes vote down vote up 
def train(full_model, en_seq, fr_seq, batch_size, n_epochs=10):
    """ Training the model """

    for ep in range(n_epochs):
        losses = []
        for bi in range(0, en_seq.shape[0] - batch_size, batch_size):

            en_onehot_seq = to_categorical(en_seq[bi:bi + batch_size, :], num_classes=en_vsize)
            fr_onehot_seq = to_categorical(fr_seq[bi:bi + batch_size, :], num_classes=fr_vsize)

            full_model.train_on_batch([en_onehot_seq, fr_onehot_seq[:, :-1, :]], fr_onehot_seq[:, 1:, :])

            l = full_model.evaluate([en_onehot_seq, fr_onehot_seq[:, :-1, :]], fr_onehot_seq[:, 1:, :],
                                    batch_size=batch_size, verbose=0)

            losses.append(l)
        if (ep + 1) % 1 == 0:
            logger.info("Loss in epoch {}: {}".format(ep + 1, np.mean(losses)))
Example #2
Source File: train.py    From attention_keras with MIT License 6 votes vote down vote up 
def train(full_model, en_seq, fr_seq, batch_size, n_epochs=10):
    """ Training the model """

    for ep in range(n_epochs):
        losses = []
        for bi in range(0, en_seq.shape[0] - batch_size, batch_size):

            en_onehot_seq = to_categorical(en_seq[bi:bi + batch_size, :], num_classes=en_vsize)
            fr_onehot_seq = to_categorical(fr_seq[bi:bi + batch_size, :], num_classes=fr_vsize)

            full_model.train_on_batch([en_onehot_seq, fr_onehot_seq[:, :-1, :]], fr_onehot_seq[:, 1:, :])

            l = full_model.evaluate([en_onehot_seq, fr_onehot_seq[:, :-1, :]], fr_onehot_seq[:, 1:, :],
                                    batch_size=batch_size, verbose=0)

            losses.append(l)
        if (ep + 1) % 1 == 0:
            logger.info("Loss in epoch {}: {}".format(ep + 1, np.mean(losses)))
Example #3
Source File: train.py    From attention_keras with MIT License 6 votes vote down vote up 
def train(full_model, en_seq, fr_seq, batch_size, n_epochs=10):
    """ Training the model """

    for ep in range(n_epochs):
        losses = []
        for bi in range(0, en_seq.shape[0] - batch_size, batch_size):

            en_onehot_seq = to_categorical(en_seq[bi:bi + batch_size, :], num_classes=en_vsize)
            fr_onehot_seq = to_categorical(fr_seq[bi:bi + batch_size, :], num_classes=fr_vsize)

            full_model.train_on_batch([en_onehot_seq, fr_onehot_seq[:, :-1, :]], fr_onehot_seq[:, 1:, :])

            l = full_model.evaluate([en_onehot_seq, fr_onehot_seq[:, :-1, :]], fr_onehot_seq[:, 1:, :],
                                    batch_size=batch_size, verbose=0)

            losses.append(l)
        if (ep + 1) % 1 == 0:
            logger.info("Loss in epoch {}: {}".format(ep + 1, np.mean(losses)))
Example #4
Source File: default_processor.py    From text2vec with Apache License 2.0 5 votes vote down vote up 
def process_y_dataset(self,
                          data: List[str],
                          max_len: Optional[int] = None,
                          subset: Optional[List[int]] = None) -> np.ndarray:
        from tensorflow.python.keras.utils import to_categorical
        if subset is not None:
            target = get_list_subset(data, subset)
        else:
            target = data
        if self.multi_label:
            return self.multi_label_binarizer.fit_transform(target)
        else:
            numerized_samples = self.numerize_label_sequences(target)
            return to_categorical(numerized_samples, len(self.label2idx))
Example #5
Source File: dataset.py    From speaker-recognition-3d-cnn with MIT License 5 votes vote down vote up 
def return_format_keras(_dict, _mapping, num_classes):
    ret_ = list()
    for speaker, files in _dict.items():
        for file in files:
            spk = _mapping.index(speaker)
            feat = file
            ret_.append([feat, to_categorical(spk, num_classes)])

    return map(list, zip(*ret_))
Example #6
Source File: train_variable_length_seq.py    From attention_keras with MIT License 5 votes vote down vote up 
def infer_nmt(encoder_model, decoder_model, test_en_seq, en_vsize, fr_vsize):
    """
    Infer logic
    :param encoder_model: keras.Model
    :param decoder_model: keras.Model
    :param test_en_seq: sequence of word ids
    :param en_vsize: int
    :param fr_vsize: int
    :return:
    """

    test_fr_seq = sents2sequences(fr_tokenizer, ['sos'], fr_vsize)
    test_en_onehot_seq = to_categorical(test_en_seq, num_classes=en_vsize)
    test_fr_onehot_seq = np.expand_dims(to_categorical(test_fr_seq, num_classes=fr_vsize), 1)

    enc_outs, enc_last_state = encoder_model.predict(test_en_onehot_seq)
    dec_state = enc_last_state
    attention_weights = []
    fr_text = ''
    for i in range(20):

        dec_out, attention, dec_state = decoder_model.predict([enc_outs, dec_state, test_fr_onehot_seq])
        dec_ind = np.argmax(dec_out, axis=-1)[0, 0]

        if dec_ind == 0:
            break
        test_fr_seq = sents2sequences(fr_tokenizer, [fr_index2word[dec_ind]], fr_vsize)
        test_fr_onehot_seq = np.expand_dims(to_categorical(test_fr_seq, num_classes=fr_vsize), 1)

        attention_weights.append((dec_ind, attention))
        fr_text += fr_index2word[dec_ind] + ' '

    return fr_text, attention_weights
Example #7
Source File: train.py    From attention_keras with MIT License 5 votes vote down vote up 
def infer_nmt(encoder_model, decoder_model, test_en_seq, en_vsize, fr_vsize):
    """
    Infer logic
    :param encoder_model: keras.Model
    :param decoder_model: keras.Model
    :param test_en_seq: sequence of word ids
    :param en_vsize: int
    :param fr_vsize: int
    :return:
    """

    test_fr_seq = sents2sequences(fr_tokenizer, ['sos'], fr_vsize)
    test_en_onehot_seq = to_categorical(test_en_seq, num_classes=en_vsize)
    test_fr_onehot_seq = np.expand_dims(to_categorical(test_fr_seq, num_classes=fr_vsize), 1)

    enc_outs, enc_last_state = encoder_model.predict(test_en_onehot_seq)
    dec_state = enc_last_state
    attention_weights = []
    fr_text = ''
    for i in range(20):

        dec_out, attention, dec_state = decoder_model.predict([enc_outs, dec_state, test_fr_onehot_seq])
        dec_ind = np.argmax(dec_out, axis=-1)[0, 0]

        if dec_ind == 0:
            break
        test_fr_seq = sents2sequences(fr_tokenizer, [fr_index2word[dec_ind]], fr_vsize)
        test_fr_onehot_seq = np.expand_dims(to_categorical(test_fr_seq, num_classes=fr_vsize), 1)

        attention_weights.append((dec_ind, attention))
        fr_text += fr_index2word[dec_ind] + ' '

    return fr_text, attention_weights