Python keras.backend.zeros_like() Examples

def __init__(self,
                 resource_path='./resources/',
                 learning_rate=0.0002,
                 decay_rate=2e-6,
                 gpus = 1):
        
        self.gpus = gpus
        self.learning_rate = learning_rate
        self.decay_rate = decay_rate
        

        def zero_loss(y_true, y_pred):
        	return K.zeros_like(y_true)
               
        discriminator_full = load_model(resource_path + 'discriminator_full.h5', custom_objects={'Conv2D_r': Conv2D_r, 'InstanceNormalization': InstanceNormalization, 'tf': tf, 'zero_loss': zero_loss, 'ConvSN2D': ConvSN2D, 'DenseSN': DenseSN})
        
        discriminator_full.trainable = True
        discriminator_full.name = "discriminator_full"
        
        self.model = discriminator_full
        self.save_model = discriminator_full 

def precision_keras(y_true, y_pred):
    #convert probas to 0,1
    y_pred_ones = K.zeros_like(y_true)
    y_pred_ones[:, K.argmax(y_pred, axis=-1)] = 1

    #where y_ture=1 and y_pred=1 -> true positive
    y_true_pred = K.sum(y_true*y_pred_ones, axis=0)

    #for each class: how many where classified as said class
    pred_cnt = K.sum(y_pred_ones, axis=0)

    #precision for each class
    precision = K.switch(K.equal(pred_cnt, 0), 0, y_true_pred/pred_cnt)
    
    #return average f1 score over all classes
    return K.mean(precision) 

def call(self, X, mask=None):
        if mask is not None:
            assert K.ndim(mask) == 2, 'Input mask to CRF must have dim 2 if not None'

        if self.test_mode == 'viterbi':
            test_output = self.viterbi_decoding(X, mask)
        else:
            test_output = self.get_marginal_prob(X, mask)

        self.uses_learning_phase = True
        if self.learn_mode == 'join':
            train_output = K.zeros_like(K.dot(X, self.kernel))
            out = K.in_train_phase(train_output, test_output)
        else:
            if self.test_mode == 'viterbi':
                train_output = self.get_marginal_prob(X, mask)
                out = K.in_train_phase(train_output, test_output)
            else:
                out = test_output
        return out 

def audio_discriminate_loss2(gamma=0.1,beta = 2*0.1,num_speaker=2):
    def loss_func(S_true,S_pred,gamma=gamma,beta=beta,num_speaker=num_speaker):
        sum_mtr = K.zeros_like(S_true[:,:,:,:,0])
        for i in range(num_speaker):
            sum_mtr += K.square(S_true[:,:,:,:,i]-S_pred[:,:,:,:,i])
            for j in range(num_speaker):
                if i != j:
                    sum_mtr -= gamma*(K.square(S_true[:,:,:,:,i]-S_pred[:,:,:,:,j]))

        for i in range(num_speaker):
            for j in range(i+1,num_speaker):
                #sum_mtr -= beta*K.square(S_pred[:,:,:,i]-S_pred[:,:,:,j])
                #sum_mtr += beta*K.square(S_true[:,:,:,:,i]-S_true[:,:,:,:,j])
                pass
        #sum = K.sum(K.maximum(K.flatten(sum_mtr),0))

        loss = K.mean(K.flatten(sum_mtr))

        return loss
    return loss_func 

def collect_final_step_of_lstm(lstm_representation, lengths):
    """
    Collect final step of lstm.

    :param lstm_representation: [batch_size, len_rt, dim]
    :param lengths: [batch_size]
    :return: [batch_size, dim]
    """
    lengths = tf.maximum(lengths, K.zeros_like(lengths))

    batch_size = tf.shape(lengths)[0]
    # shape (batch_size)
    batch_nums = tf.range(0, limit=batch_size)
    # shape (batch_size, 2)
    indices = tf.stack((batch_nums, lengths), axis=1)
    result = tf.gather_nd(lstm_representation, indices,
                            name='last-forwar-lstm')
    # [batch_size, dim]
    return result 

def precision_keras(y_true, y_pred):
    # convert probas to 0,1
    y_pred_ones = K.zeros_like(y_true)
    y_pred_ones[:, K.argmax(y_pred, axis=-1)] = 1

    # where y_ture=1 and y_pred=1 -> true positive
    y_true_pred = K.sum(y_true * y_pred_ones, axis=0)

    # for each class: how many where classified as said class
    pred_cnt = K.sum(y_pred_ones, axis=0)

    # precision for each class
    precision = K.switch(K.equal(pred_cnt, 0), 0, y_true_pred / pred_cnt)

    # return average f1 score over all classes
    return K.mean(precision) 

def f1_score_taskB(y_true, y_pred):
    # convert probas to 0,1
    y_pred_ones = K.zeros_like(y_true)
    y_pred_ones[:, K.argmax(y_pred, axis=-1)] = 1

    # where y_ture=1 and y_pred=1 -> true positive
    y_true_pred = K.sum(y_true * y_pred_ones, axis=0)

    # for each class: how many where classified as said class
    pred_cnt = K.sum(y_pred_ones, axis=0)

    # for each class: how many are true members of said class
    gold_cnt = K.sum(y_true, axis=0)

    # precision for each class
    precision = K.switch(K.equal(pred_cnt, 0), 0, y_true_pred / pred_cnt)

    # recall for each class
    recall = K.switch(K.equal(gold_cnt, 0), 0, y_true_pred / gold_cnt)

    # f1 for each class
    f1_class = K.switch(K.equal(precision + recall, 0), 0, 2 * (precision * recall) / (precision + recall))

    # return average f1 score over all classes
    return f1_class 

def precision_keras(y_true, y_pred):
    #convert probas to 0,1
    y_pred_ones = K.zeros_like(y_true)
    y_pred_ones[:, K.argmax(y_pred, axis=-1)] = 1

    #where y_ture=1 and y_pred=1 -> true positive
    y_true_pred = K.sum(y_true*y_pred_ones, axis=0)

    #for each class: how many where classified as said class
    pred_cnt = K.sum(y_pred_ones, axis=0)

    #precision for each class
    precision = K.switch(K.equal(pred_cnt, 0), 0, y_true_pred/pred_cnt)
    
    #return average f1 score over all classes
    return K.mean(precision) 

def f1_score_semeval(y_true, y_pred):
    # convert probas to 0,1
    y_ppred = K.zeros_like(y_true)
    y_pred_ones = K.T.set_subtensor(y_ppred[K.T.arange(y_true.shape[0]), K.argmax(y_pred, axis=-1)], 1)

    # where y_ture=1 and y_pred=1 -> true positive
    y_true_pred = K.sum(y_true * y_pred_ones, axis=0)

    # for each class: how many where classified as said class
    pred_cnt = K.sum(y_pred_ones, axis=0)

    # for each class: how many are true members of said class
    gold_cnt = K.sum(y_true, axis=0)

    # precision for each class
    precision = K.T.switch(K.T.eq(pred_cnt, 0), 0, y_true_pred / pred_cnt)

    # recall for each class
    recall = K.T.switch(K.T.eq(gold_cnt, 0), 0, y_true_pred / gold_cnt)

    # f1 for each class
    f1_class = K.T.switch(K.T.eq(precision + recall, 0), 0, 2 * (precision * recall) / (precision + recall))

    #return average f1 score over all classes
    return (f1_class[0] + f1_class[2])/2.0 

def f1_score_taskB(y_true, y_pred):
    #convert probas to 0,1
    y_pred_ones = K.zeros_like(y_true)
    y_pred_ones[:, K.argmax(y_pred, axis=-1)] = 1

    #where y_ture=1 and y_pred=1 -> true positive
    y_true_pred = K.sum(y_true*y_pred_ones, axis=0)

    #for each class: how many where classified as said class
    pred_cnt = K.sum(y_pred_ones, axis=0)

    #for each class: how many are true members of said class
    gold_cnt = K.sum(y_true, axis=0)

    #precision for each class
    precision = K.switch(K.equal(pred_cnt, 0), 0, y_true_pred/pred_cnt)

    #recall for each class
    recall = K.switch(K.equal(gold_cnt, 0), 0, y_true_pred/gold_cnt)

    #f1 for each class
    f1_class = K.switch(K.equal(precision + recall, 0), 0, 2*(precision*recall)/(precision+recall))

    #return average f1 score over all classes
    return f1_class 

def f1_score_keras(y_true, y_pred):
    #convert probas to 0,1
    y_ppred = K.zeros_like(y_true)
    y_pred_ones = K.T.set_subtensor(y_ppred[K.T.arange(y_true.shape[0]), K.argmax(y_pred, axis=-1)], 1)

    #where y_ture=1 and y_pred=1 -> true positive
    y_true_pred = K.sum(y_true*y_pred_ones, axis=0)

    #for each class: how many where classified as said class
    pred_cnt = K.sum(y_pred_ones, axis=0)

    #for each class: how many are true members of said class
    gold_cnt = K.sum(y_true, axis=0)

    #precision for each class
    precision = K.T.switch(K.T.eq(pred_cnt, 0), 0, y_true_pred/pred_cnt)

    #recall for each class
    recall = K.T.switch(K.T.eq(gold_cnt, 0), 0, y_true_pred/gold_cnt)

    #f1 for each class
    f1_class = K.T.switch(K.T.eq(precision + recall, 0), 0, 2*(precision*recall)/(precision+recall))

    #return average f1 score over all classes
    return K.mean(f1_class) 

def _forward(x, reduce_step, initial_states, U, mask=None):
    '''Forward recurrence of the linear chain crf.'''

    def _forward_step(energy_matrix_t, states):
        alpha_tm1 = states[-1]
        new_states = reduce_step(K.expand_dims(alpha_tm1, 2) + energy_matrix_t)
        return new_states[0], new_states

    U_shared = K.expand_dims(K.expand_dims(U, 0), 0)

    if mask is not None:
        mask = K.cast(mask, K.floatx())
        mask_U = K.expand_dims(K.expand_dims(mask[:, :-1] * mask[:, 1:], 2), 3)
        U_shared = U_shared * mask_U

    inputs = K.expand_dims(x[:, 1:, :], 2) + U_shared
    inputs = K.concatenate([inputs, K.zeros_like(inputs[:, -1:, :, :])], axis=1)

    last, values, _ = K.rnn(_forward_step, inputs, initial_states)
    return last, values 

def add_boundary_energy(x, b_start=None, b_end=None, mask=None):
    '''Given the observations x, it adds the start boundary energy b_start (resp.
    end boundary energy b_end on the start (resp. end) elements and multiplies
    the mask.'''
    if mask is None:
        if b_start is not None:
            x = K.concatenate([x[:, :1, :] + b_start, x[:, 1:, :]], axis=1)
        if b_end is not None:
            x = K.concatenate([x[:, :-1, :], x[:, -1:, :] + b_end], axis=1)
    else:
        mask = K.cast(mask, K.floatx())
        mask = K.expand_dims(mask, 2)
        x *= mask
        if b_start is not None:
            mask_r = K.concatenate([K.zeros_like(mask[:, :1]), mask[:, :-1]], axis=1)
            start_mask = K.cast(K.greater(mask, mask_r), K.floatx())
            x = x + start_mask * b_start
        if b_end is not None:
            mask_l = K.concatenate([mask[:, 1:], K.zeros_like(mask[:, -1:])], axis=1)
            end_mask = K.cast(K.greater(mask, mask_l), K.floatx())
            x = x + end_mask * b_end
    return x 

def add_boundary_energy(x, b_start=None, b_end=None, mask=None):
    '''Given the observations x, it adds the start boundary energy b_start (resp.
    end boundary energy b_end on the start (resp. end) elements and multiplies
    the mask.'''
    if mask is None:
        if b_start is not None:
            x = K.concatenate([x[:, :1, :] + b_start, x[:, 1:, :]], axis=1)
        if b_end is not None:
            x = K.concatenate([x[:, :-1, :], x[:, -1:, :] + b_end], axis=1)
    else:
        mask = K.cast(mask, K.floatx())
        mask = K.expand_dims(mask, 2)
        x *= mask
        if b_start is not None:
            mask_r = K.concatenate([K.zeros_like(mask[:, :1]), mask[:, :-1]], axis=1)
            start_mask = K.cast(K.greater(mask, mask_r), K.floatx())
            x = x + start_mask * b_start
        if b_end is not None:
            mask_l = K.concatenate([mask[:, 1:], K.zeros_like(mask[:, -1:])], axis=1)
            end_mask = K.cast(K.greater(mask, mask_l), K.floatx())
            x = x + end_mask * b_end
    return x 

def _forward(x, reduce_step, initial_states, U, mask=None):
    '''Forward recurrence of the linear chain crf.'''

    def _forward_step(energy_matrix_t, states):
        alpha_tm1 = states[-1]
        new_states = reduce_step(K.expand_dims(alpha_tm1, 2) + energy_matrix_t)
        return new_states[0], new_states

    U_shared = K.expand_dims(K.expand_dims(U, 0), 0)

    if mask is not None:
        mask = K.cast(mask, K.floatx())
        mask_U = K.expand_dims(K.expand_dims(mask[:, :-1] * mask[:, 1:], 2), 3)
        U_shared = U_shared * mask_U

    inputs = K.expand_dims(x[:, 1:, :], 2) + U_shared
    inputs = K.concatenate([inputs, K.zeros_like(inputs[:, -1:, :, :])], axis=1)

    last, values, _ = K.rnn(_forward_step, inputs, initial_states)
    return last, values 

def _backward(gamma, mask):
    '''Backward recurrence of the linear chain crf.'''
    gamma = K.cast(gamma, 'int32')

    def _backward_step(gamma_t, states):
        y_tm1 = K.squeeze(states[0], 0)
        y_t = batch_gather(gamma_t, y_tm1)
        return y_t, [K.expand_dims(y_t, 0)]

    initial_states = [K.expand_dims(K.zeros_like(gamma[:, 0, 0]), 0)]
    _, y_rev, _ = K.rnn(_backward_step,
                        gamma,
                        initial_states,
                        go_backwards=True)
    y = K.reverse(y_rev, 1)

    if mask is not None:
        mask = K.cast(mask, dtype='int32')
        # mask output
        y *= mask
        # set masked values to -1
        y += -(1 - mask)
    return y 

def _backward(gamma, mask):
    '''Backward recurrence of the linear chain crf.'''
    gamma = K.cast(gamma, 'int32')

    def _backward_step(gamma_t, states):
        y_tm1 = K.squeeze(states[0], 0)
        y_t = batch_gather(gamma_t, y_tm1)
        return y_t, [K.expand_dims(y_t, 0)]

    initial_states = [K.expand_dims(K.zeros_like(gamma[:, 0, 0]), 0)]
    _, y_rev, _ = K.rnn(_backward_step,
                        gamma,
                        initial_states,
                        go_backwards=True)
    y = K.reverse(y_rev, 1)

    if mask is not None:
        mask = K.cast(mask, dtype='int32')
        # mask output
        y *= mask
        # set masked values to -1
        y += -(1 - mask)
    return y 

def call(self, u_vecs):
        if self.share_weights:
            u_hat_vecs = K.conv1d(u_vecs, self.W)
        else:
            u_hat_vecs = K.local_conv1d(u_vecs, self.W, [1], [1])

        batch_size = K.shape(u_vecs)[0]
        input_num_capsule = K.shape(u_vecs)[1]
        u_hat_vecs = K.reshape(u_hat_vecs, (batch_size, input_num_capsule,
                                            self.num_capsule, self.dim_capsule))
        u_hat_vecs = K.permute_dimensions(u_hat_vecs, (0, 2, 1, 3))
        # final u_hat_vecs.shape = [None, num_capsule, input_num_capsule, dim_capsule]

        b = K.zeros_like(u_hat_vecs[:, :, :, 0])  # shape = [None, num_capsule, input_num_capsule]
        outputs = None
        for i in range(self.routings):
            b = K.permute_dimensions(b, (0, 2, 1))  # shape = [None, input_num_capsule, num_capsule]
            c = K.softmax(b)
            c = K.permute_dimensions(c, (0, 2, 1))
            b = K.permute_dimensions(b, (0, 2, 1))
            outputs = self.activation(K.batch_dot(c, u_hat_vecs, [2, 2]))
            if i < self.routings - 1:
                b = K.batch_dot(outputs, u_hat_vecs, [2, 3])

        return outputs 

def call(self, u_vecs):
        if self.share_weights:
            u_hat_vecs = K.conv1d(u_vecs, self.W)
        else:
            u_hat_vecs = K.local_conv1d(u_vecs, self.W, [1], [1])

        batch_size = K.shape(u_vecs)[0]
        input_num_capsule = K.shape(u_vecs)[1]
        u_hat_vecs = K.reshape(u_hat_vecs, (batch_size, input_num_capsule,
                                            self.num_capsule, self.dim_capsule))
        u_hat_vecs = K.permute_dimensions(u_hat_vecs, (0, 2, 1, 3))

        b = K.zeros_like(u_hat_vecs[:, :, :, 0])  # shape = [None, num_capsule, input_num_capsule]
        for i in range(self.routings):
            b = K.permute_dimensions(b, (0, 2, 1))  # shape = [None, input_num_capsule, num_capsule]
            c = K.softmax(b)
            c = K.permute_dimensions(c, (0, 2, 1))
            b = K.permute_dimensions(b, (0, 2, 1))
            outputs = self.activation(K.batch_dot(c, u_hat_vecs, [2, 2]))
            if i < self.routings - 1:
                b = K.batch_dot(outputs, u_hat_vecs, [2, 3])

        return outputs 

def __init__(self,
                 resource_path='./resources/',
                 learning_rate=0.0002,
                 decay_rate=2e-6,
                 gpus = 0):
        
        self.gpus = gpus
        self.learning_rate = learning_rate
        self.decay_rate = decay_rate
        
        def zero_loss(y_true, y_pred):
        	return K.zeros_like(y_true)
       
        discriminator_low = load_model(resource_path + 'discriminator_low.h5', custom_objects={'Conv2D_r': Conv2D_r, 'InstanceNormalization': InstanceNormalization, 'tf': tf,'zero_loss': zero_loss, 'ConvSN2D': ConvSN2D, 'DenseSN': DenseSN})
        
        discriminator_low.trainable = True
        discriminator_low.name = "discriminator_low"

        self.model = discriminator_low
        self.save_model = discriminator_low 

def f1_score_task3(y_true, y_pred):
    #convert probas to 0,1
    y_ppred = K.zeros_like(y_true)
    y_pred_ones = K.T.set_subtensor(y_ppred[K.T.arange(y_true.shape[0]), K.argmax(y_pred, axis=-1)], 1)

    #where y_ture=1 and y_pred=1 -> true positive
    y_true_pred = K.sum(y_true*y_pred_ones, axis=0)

    #for each class: how many where classified as said class
    pred_cnt = K.sum(y_pred_ones, axis=0)

    #for each class: how many are true members of said class
    gold_cnt = K.sum(y_true, axis=0)

    #precision for each class
    precision = K.T.switch(K.T.eq(pred_cnt, 0), 0, y_true_pred/pred_cnt)

    #recall for each class
    recall = K.T.switch(K.T.eq(gold_cnt, 0), 0, y_true_pred/gold_cnt)

    #f1 for each class
    f1_class = K.T.switch(K.T.eq(precision + recall, 0), 0, 2*(precision*recall)/(precision+recall))

    #return average f1 score over all classes
    return f1_class[1] 

def shift_right(x, offset=1):
        assert offset > 0
        return K.concatenate([K.zeros_like(x[:, :offset]), x[:, :-offset]], axis=1) 

def resnet_block(
        layer,
        num_filters,
        subsample_length,
        block_index,
        **params):
    from keras.layers import Add 
    from keras.layers import MaxPooling1D
    from keras.layers.core import Lambda

    def zeropad(x):
        y = K.zeros_like(x)
        return K.concatenate([x, y], axis=2)

    def zeropad_output_shape(input_shape):
        shape = list(input_shape)
        assert len(shape) == 3
        shape[2] *= 2
        return tuple(shape)

    shortcut = MaxPooling1D(pool_size=subsample_length)(layer)
    zero_pad = (block_index % params["conv_increase_channels_at"]) == 0 \
        and block_index > 0
    if zero_pad is True:
        shortcut = Lambda(zeropad, output_shape=zeropad_output_shape)(shortcut)

    for i in range(params["conv_num_skip"]):
        if not (block_index == 0 and i == 0):
            layer = _bn_relu(
                layer,
                dropout=params["conv_dropout"] if i > 0 else 0,
                **params)
        layer = add_conv_weight(
            layer,
            params["conv_filter_length"],
            num_filters,
            subsample_length if i == 0 else 1,
            **params)
    layer = Add()([shortcut, layer])
    return layer 

def _mask_loss(y_true, y_pred, y_mask, element_wise_loss):
    l = K.switch(y_mask, element_wise_loss(y_true, y_pred), K.zeros_like(y_mask, dtype=K.floatx()))
    return K.sum(l) / (K.cast(K.sum(y_mask), dtype='float32') + K.epsilon()) 

def zeropad(x):
    y = K.zeros_like(x)
    return K.concatenate([x, y], axis=1) 

def _trans(theta):
    tx = theta[:,3:4]
    ty = theta[:,4:5]
    tz = theta[:,5:6]
    zero = K.zeros_like(tx)
    one = K.ones_like(tx)
    first = K.reshape(K.concatenate([one,zero,zero,tx],axis=1),(-1,1,4))
    second = K.reshape(K.concatenate([zero,one,zero,ty],axis=1),(-1,1,4))
    third = K.reshape(K.concatenate([zero,zero,one,tz],axis=1),(-1,1,4))
    trans = K.concatenate([first,second,third],axis=1)
    trans = trans.reshape((trans.shape[0],3,4))

    return trans 

def batch_reading(head_num, memory_size, memory_dim, memory_t, weight_t):
    """
    Reading memory.
    :param head_num:
    :param memory_size:
    :param memory_dim:
    :param memory_t: the $N \times M$ memory matrix at time $t$, where $N$
    is the number of memory locations, and $M$ is the vector size at each
    location.
    :param weight_t: $w_t$ is a vector of weightings over the $N$ locations
    emitted by a reading head at time $t$.

    Since all weightings are normalized, the $N$ elements $w_t(i)$ of
    $\textbf{w}_t$ obey the following constraints:
    $$\sum_{i=1}^{N} w_t(i) = 1, 0 \le w_t(i) \le 1,\forall i$$

    The length $M$ read vector $r_t$ returned by the head is defined as a
    convex combination of the row-vectors $M_t(i)$ in memory:
    $$\textbf{r}_t \leftarrow \sum_{i=1}^{N}w_t(i)\textbf{M}_t(i)$$
    :return: the content reading from memory.
    """
    r_t_list = K.zeros_like((head_num * memory_dim, 1))

    for i in xrange(head_num):
        begin = i * memory_size
        end = begin + memory_size
        r_t = reading(memory_t, weight_t[begin:end])
        r_t_list[begin:end] = r_t

    return r_t_list 

def _format_encoder_states(self, encoder_states, use_first=True):
        """
        Format the encoder states in such a way that only the last state from the first layer of the encoder
        is used to init the first layer of the decoder.
        If the cell type used is LSTM then both c and h are kept.
        :param encoder_states: Keras.tensor
            (last) hidden state of the decoder
        :param use_first: bool
            if True use only the last hidden state from first layer of the encoder, while the other are init to zero.
            if False use last hidden state for all layers
        :return:
            masked encoder states
        """
        if use_first:
            # Keras version 2.1.4 has encoder states reversed w.r.t later versions
            if keras.__version__ < '2.2':
                if self.cell == 'lstm':
                    encoder_states = [Lambda(lambda x: K.zeros_like(x))(s) for s in encoder_states[:-2]] + [
                        encoder_states[-2]]
                else:
                    encoder_states = [Lambda(lambda x: K.zeros_like(x))(s) for s in encoder_states[:-1]] + [
                        encoder_states[-1]]
            else:
                if self.cell == 'lstm':
                    encoder_states = encoder_states[:2] + [Lambda(lambda x: K.zeros_like(x))(s) for s in
                                                                encoder_states[2:]]
                else:
                    encoder_states = encoder_states[:1] + [Lambda(lambda x: K.zeros_like(x))(s) for s in
                                                                encoder_states[1:]]
        return encoder_states 

def weighted_mean_squared_error(y_true, y_pred, weights):
    mask = K.zeros_like(y_true)
    for lbl in weights:     mask += K.cast(K.equal(y_true, lbl), dtype='float32') * (K.zeros_like(y_true) + weights[lbl])      # An adhoc way to solve the problem of: tensor object does not support item assignment
    return K.mean(K.square(y_pred - y_true)*mask, axis=-1) 

def zeropad(x):
    y = K.zeros_like(x)
    return K.concatenate([x, y], axis=1)