Python keras.backend.concatenate() Examples

def yolo_body(inputs, num_anchors, num_classes):
    """Create YOLO_V2 model CNN body in Keras."""
    darknet = Model(inputs, darknet_body()(inputs))
    conv20 = compose(
        DarknetConv2D_BN_Leaky(1024, (3, 3)),
        DarknetConv2D_BN_Leaky(1024, (3, 3)))(darknet.output)

    conv13 = darknet.layers[43].output
    conv21 = DarknetConv2D_BN_Leaky(64, (1, 1))(conv13)
    # TODO: Allow Keras Lambda to use func arguments for output_shape?
    conv21_reshaped = Lambda(
        space_to_depth_x2,
        output_shape=space_to_depth_x2_output_shape,
        name='space_to_depth')(conv21)

    x = concatenate([conv21_reshaped, conv20])
    x = DarknetConv2D_BN_Leaky(1024, (3, 3))(x)
    x = DarknetConv2D(num_anchors * (num_classes + 5), (1, 1))(x)
    return Model(inputs, x) 

def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

def _pad(self, input):
        """
        pads the network output so y_pred and y_true have the same dimensions
        :param input: previous layer
        :return: layer, last dimensions padded for 4
        """

        #pad = K.placeholder( (None,self.config.ANCHORS, 4))


        #pad = np.zeros ((self.config.BATCH_SIZE,self.config.ANCHORS, 4))
        #return K.concatenate( [input, pad], axis=-1)


        padding = np.zeros((3,2))
        padding[2,1] = 4
        return tf.pad(input, padding ,"CONSTANT")



    #loss function to optimize 

def call(self , x, mask=None):
        
        e1=x[0].T
        e2=x[1].T
        
        batch_size = K.shape(x[0])[0]
        sim = []
        V_out = K.dot(self.V, K.concatenate([e1,e2],axis=0))     

        for i in range(self.k): 
            temp = K.batch_dot(K.dot(e1.T,self.W[i,:,:]),e2.T,axes=1)
            sim.append(temp)
        sim=K.reshape(sim,(self.k,batch_size))

        tensor_bi_product = self.activation(V_out+sim)
        tensor_bi_product = K.dot(self.U.T, tensor_bi_product).T

        return tensor_bi_product 

def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

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 yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

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 yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

def call(self,x,training=None):
        deta1 = 0.3
        deta2 = 0.3
        deta3 = 0.3
        seed = np.random.randint(1, 10e6)
        rng = RandomStreams(seed=seed)
        theta1 = rng.uniform(size=(x.shape[0],1),low=-deta1,high=deta1,dtype='float32')
        theta2 = rng.uniform(size=(x.shape[0],1),low=-deta2,high=deta2,dtype='float32')
        theta3 = rng.uniform(size=(x.shape[0],1),low=-deta3,high=deta3,dtype='float32')
        theta = K.concatenate([theta1,theta2,theta3],axis=-1)
        theta = K.tile(theta,x.shape[1])
        theta = theta.reshape((x.shape[0], x.shape[1], 3))

        theta = theta.reshape((theta.shape[0]*theta.shape[1], theta.shape[2]))
        M = _fusion(theta)
        output = _transform_rot(M, x)

        return K.in_train_phase(output,x,training = training) 

def _correct_boxes(
            self, box_xy, box_wh, input_shape, image_shape):
        """Get corrected boxes, which are scaled to original shape."""
        box_yx = box_xy[..., ::-1]
        box_hw = box_wh[..., ::-1]
        input_shape = K.cast(input_shape, K.dtype(box_yx))
        image_shape = K.cast(image_shape, K.dtype(box_yx))
        new_shape = K.round(image_shape * K.min(input_shape / image_shape))
        offset = (input_shape - new_shape) / 2. / input_shape
        scale = input_shape / new_shape
        box_yx = (box_yx - offset) * scale
        box_hw *= scale

        box_mins = box_yx - (box_hw / 2.)
        box_maxes = box_yx + (box_hw / 2.)
        boxes = K.concatenate([
            box_mins[..., 0:1],  # y_min
            box_mins[..., 1:2],  # x_min
            box_maxes[..., 0:1],  # y_max
            box_maxes[..., 1:2]  # x_max
        ])

        # Scale boxes back to original image shape.
        boxes *= K.concatenate([image_shape, image_shape])
        return boxes 

def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):

    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],
        box_mins[..., 1:2],
        box_maxes[..., 0:1],
        box_maxes[..., 1:2]
    ])


    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

def preprocess_input(self, x):
        if self.consume_less == 'cpu':
            if 0 < self.dropout_W < 1:
                dropout = self.dropout_W
            else:
                dropout = 0
            input_shape = self.input_spec[0].shape
            input_dim = input_shape[2]
            timesteps = input_shape[1]

            x_i = time_distributed_dense(x, self.W_i, self.b_i, dropout,
                                         input_dim, self.output_dim, timesteps)
            x_f = time_distributed_dense(x, self.W_f, self.b_f, dropout,
                                         input_dim, self.output_dim, timesteps)
            x_c = time_distributed_dense(x, self.W_c, self.b_c, dropout,
                                         input_dim, self.output_dim, timesteps)
            x_o = time_distributed_dense(x, self.W_o, self.b_o, dropout,
                                         input_dim, self.output_dim, timesteps)
            return K.concatenate([x_i, x_f, x_c, x_o], axis=2)
        else:
            return x 

def _multi_kmax_context_concat(inputs, top_k, poses):
	x, context_input = inputs
	idxes, topk_vs = list(), list()
	for p in poses:
		val, idx = tf.nn.top_k(tf.slice(x, [0,0,0], [-1,-1, p]), k=top_k, sorted=True, name=None)
		topk_vs.append(val)
		idxes.append(idx)
	concat_topk_max = tf.concat(topk_vs, -1, name='concat_val')
	concat_topk_idx = tf.concat(idxes, -1, name='concat_idx')
	# hack that requires the context to have the same shape as similarity matrices
	# https://stackoverflow.com/questions/41897212/how-to-sort-a-multi-dimensional-tensor-using-the-returned-indices-of-tf-nn-top-k
	shape = tf.shape(x)
	mg = tf.meshgrid(*[tf.range(d) for d in (tf.unstack(shape[:(x.get_shape().ndims - 1)]) + [top_k*len(poses)])], indexing='ij')
	val_contexts = tf.gather_nd(context_input, tf.stack(mg[:-1] + [concat_topk_idx], axis=-1))
	return tf.concat([concat_topk_max, val_contexts], axis=-1)
	# return backend.concatenate([concat_topk_max, val_contexts]) 

def preprocess(x):
    return K.concatenate([
        x[:,:,0:1] / 360.0,
        x[:,:,1:3],
        x[:,:,3:4] / 360.0, 
        x[:,:,4:6],
        x[:,:,6:18] / 360.0,
        x[:,:,18:19] - x[:,:,1:2],
        x[:,:,19:22],
        x[:,:,28:29] - x[:,:,1:2],
        x[:,:,29:30],
        x[:, :, 30:31] - x[:, :, 1:2],
        x[:, :, 31:32],
        x[:, :, 32:33] - x[:, :, 1:2],
        x[:, :, 33:34],
        x[:, :, 34:35] - x[:, :, 1:2],
        x[:, :, 35:41],
    ], axis=2) 

def step(self, x, states):  
        h = states[0]
        # states[1] necessary?
        
        # comes from the constants
        X_static = states[-2]
        # equals K.dot(static_x, self._W1) + self._b2 with X.shape=[bs, L, static_input_dim]
        total_x_static_prod = states[-1]

        # expand dims to add the vector which is only valid for this time step
        # to total_x_prod which is valid for all time steps
        hw = K.expand_dims(K.dot(h, self._W2), 1)
        additive_atn = total_x_static_prod + hw
        attention = K.softmax(K.dot(additive_atn, self._V), axis=1)
        static_x_weighted = K.sum(attention * X_static, [1])
        
        x = K.dot(K.concatenate([x, static_x_weighted], 1), self._W3) + self._b3

        h, new_states = self.layer.cell.call(x, states[:-2])
        
        # append attention to the states to "smuggle" it out of the RNN wrapper
        attention = K.squeeze(attention, -1)
        h = K.concatenate([h, attention])

        return h, new_states 

def step(self, x, states):   
        h = states[0]
        # states[1] necessary?

        # equals K.dot(X, self._W1) + self._b2 with X.shape=[bs, T, input_dim]
        total_x_prod = states[-1]
        # comes from the constants (equals the input sequence)
        X = states[-2]
        
        # expand dims to add the vector which is only valid for this time step
        # to total_x_prod which is valid for all time steps
        hw = K.expand_dims(K.dot(h, self._W2), 1)
        additive_atn = total_x_prod + hw
        attention = K.softmax(K.dot(additive_atn, self._V), axis=1)
        x_weighted = K.sum(attention * X, [1])

        x = K.dot(K.concatenate([x, x_weighted], 1), self._W3) + self._b3
        
        h, new_states = self.layer.cell.call(x, states[:-2])
        
        return h, new_states 

def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

def yolo_head(feats, anchors, num_classes, input_shape, calc_loss=False):
    num_anchors = len(anchors)
    # [1, 1, 1, num_anchors, 2]
    anchors_tensor = K.reshape(K.constant(anchors), [1, 1, 1, num_anchors, 2])

    # 获得x，y的网格
    # (13, 13, 1, 2)
    grid_shape = K.shape(feats)[1:3] # height, width
    grid_y = K.tile(K.reshape(K.arange(0, stop=grid_shape[0]), [-1, 1, 1, 1]),
        [1, grid_shape[1], 1, 1])
    grid_x = K.tile(K.reshape(K.arange(0, stop=grid_shape[1]), [1, -1, 1, 1]),
        [grid_shape[0], 1, 1, 1])
    grid = K.concatenate([grid_x, grid_y])
    grid = K.cast(grid, K.dtype(feats))

    # (batch_size,13,13,3,85)
    feats = K.reshape(feats, [-1, grid_shape[0], grid_shape[1], num_anchors, num_classes + 5])

    # 将预测值调成真实值
    # box_xy对应框的中心点
    # box_wh对应框的宽和高
    box_xy = (K.sigmoid(feats[..., :2]) + grid) / K.cast(grid_shape[::-1], K.dtype(feats))
    box_wh = K.exp(feats[..., 2:4]) * anchors_tensor / K.cast(input_shape[::-1], K.dtype(feats))
    box_confidence = K.sigmoid(feats[..., 4:5])
    box_class_probs = K.sigmoid(feats[..., 5:])

    # 在计算loss的时候返回如下参数
    if calc_loss == True:
        return grid, feats, box_xy, box_wh
    return box_xy, box_wh, box_confidence, box_class_probs

#---------------------------------------------------#
#   用于计算每个预测框与真实框的iou
#---------------------------------------------------# 

def _make_regular_grids(self, batch_size, height, width):
        # making a single regular grid
        x_linspace = K_linspace(-1., 1., width)
        y_linspace = K_linspace(-1., 1., height)
        x_coordinates, y_coordinates = K_meshgrid(x_linspace, y_linspace)
        x_coordinates = K.flatten(x_coordinates)
        y_coordinates = K.flatten(y_coordinates)
        ones = K.ones_like(x_coordinates)
        grid = K.concatenate([x_coordinates, y_coordinates, ones], 0)

        # repeating grids for each batch
        grid = K.flatten(grid)
        grids = K.tile(grid, K.stack([batch_size]))
        return K.reshape(grids, (batch_size, 3, height * width)) 

def yolo_head(feats, anchors, num_classes, input_shape, calc_loss=False):

    num_anchors = len(anchors)

    anchors_tensor = K.reshape(K.constant(anchors), [1, 1, 1, num_anchors, 2])

    grid_shape = K.shape(feats)[1:3]
    grid_y = K.tile(K.reshape(K.arange(0, stop=grid_shape[0]), [-1, 1, 1, 1]),
        [1, grid_shape[1], 1, 1])
    grid_x = K.tile(K.reshape(K.arange(0, stop=grid_shape[1]), [1, -1, 1, 1]),
        [grid_shape[0], 1, 1, 1])
    grid = K.concatenate([grid_x, grid_y])
    grid = K.cast(grid, K.dtype(feats))

    feats = K.reshape(
        feats, [-1, grid_shape[0], grid_shape[1], num_anchors, num_classes + 5])


    box_xy = (K.sigmoid(feats[..., :2]) + grid) / K.cast(grid_shape[::-1], K.dtype(feats))
    box_wh = K.exp(feats[..., 2:4]) * anchors_tensor / K.cast(input_shape[::-1], K.dtype(feats))
    box_confidence = K.sigmoid(feats[..., 4:5])
    box_class_probs = K.sigmoid(feats[..., 5:])

    if calc_loss == True:
        return grid, feats, box_xy, box_wh
    return box_xy, box_wh, box_confidence, box_class_probs 

def preprocess_input(self, x):
        print("begin preprocess_input(self, x)")
        if self.consume_less == 'cpu':
            if 0 < self.dropout_W < 1:
                dropout = self.dropout_W
            else:
                dropout = 0
            input_shape = self.input_spec[0].shape
            input_dim = input_shape[2]
            timesteps = input_shape[1]

            # x_i = time_distributed_dense(x, self.W_i, self.b_i, dropout,
            #                              input_dim, self.output_dim, timesteps)
            # x_f = time_distributed_dense(x, self.W_f, self.b_f, dropout,
            #                              input_dim, self.output_dim, timesteps)
            # x_c = time_distributed_dense(x, self.W_c, self.b_c, dropout,
            #                              input_dim, self.output_dim, timesteps)
            # x_o = time_distributed_dense(x, self.W_o, self.b_o, dropout,
            #                              input_dim, self.output_dim, timesteps)
            # add by Robot Steven ****************************************#
            x_i = time_distributed_dense(x, self.W_i, self.b_i, dropout,
                                         input_dim, self.controller_output_dim, timesteps)
            x_f = time_distributed_dense(x, self.W_f, self.b_f, dropout,
                                         input_dim, self.controller_output_dim, timesteps)
            x_c = time_distributed_dense(x, self.W_c, self.b_c, dropout,
                                         input_dim, self.controller_output_dim, timesteps)
            x_o = time_distributed_dense(x, self.W_o, self.b_o, dropout,
                                         input_dim, self.controller_output_dim, timesteps)
            # add by Robot Steven ****************************************#
            print("end preprocess_input(self,x )")
            return K.concatenate([x_i, x_f, x_c, x_o], axis=2)
        else:
            print("end preprocess_input(self,x )\n")
            return x 

def call(self, x,mask=None):
        newx = K.sort(x)
        #response = K.reverse(newx, axes=1)
        #response = K.sum(x> 0.5, axis=1) / self.k
        return K.concatenate([newx[:,:self.softmink], newx[:,newx.shape[1]-self.softmaxk:]], axis=-1)
        #response = K.reshape(newx,[-1,1])
        #return K.concatenate([1-response, response], axis=self.label)
        #response = K.reshape(x[:,self.axis], (-1,1))
        #return K.concatenate([1-response, response], axis=self.axis)
        #e = K.exp(x - K.max(x, axis=self.axis, keepdims=True))
        #s = K.sum(e, axis=self.axis, keepdims=True)
        #return e / s 

def yolo_head(feats, anchors, num_classes, input_shape):
    """Convert final layer features to bounding box parameters."""
    num_anchors = len(anchors)
    # Reshape to batch, height, width, num_anchors, box_params.
    anchors_tensor = K.reshape(K.constant(anchors), [1, 1, 1, num_anchors, 2])

    grid_shape = K.shape(feats)[1:3] # height, width
    grid_y = K.tile(K.reshape(K.arange(0, stop=grid_shape[0]), [-1, 1, 1, 1]),
        [1, grid_shape[1], 1, 1])
    grid_x = K.tile(K.reshape(K.arange(0, stop=grid_shape[1]), [1, -1, 1, 1]),
        [grid_shape[0], 1, 1, 1])
    grid = K.concatenate([grid_x, grid_y])
    grid = K.cast(grid, K.dtype(feats))

    feats = K.reshape(
        feats, [-1, grid_shape[0], grid_shape[1], num_anchors, num_classes + 5])

    box_xy = K.sigmoid(feats[..., :2])
    box_wh = K.exp(feats[..., 2:4])
    box_confidence = K.sigmoid(feats[..., 4:5])
    box_class_probs = K.sigmoid(feats[..., 5:])

    # Adjust preditions to each spatial grid point and anchor size.
    box_xy = (box_xy + grid) / K.cast(grid_shape[::-1], K.dtype(feats))
    box_wh = box_wh * anchors_tensor / K.cast(input_shape[::-1], K.dtype(feats))

    return box_xy, box_wh, box_confidence, box_class_probs 

def call(self, x,mask=None):
        newx = K.sort(x)
        #response = K.reverse(newx, axes=1)
        #response = K.sum(x> 0.5, axis=1) / self.k
        return K.concatenate([newx[:,:self.softmink], newx[:,newx.shape[1]-self.softmaxk:]], axis=-1)
        #response = K.reshape(newx,[-1,1])
        #return K.concatenate([1-response, response], axis=self.label)
        #response = K.reshape(x[:,self.axis], (-1,1))
        #return K.concatenate([1-response, response], axis=self.axis)
        #e = K.exp(x - K.max(x, axis=self.axis, keepdims=True))
        #s = K.sum(e, axis=self.axis, keepdims=True)
        #return e / s 

def call(self, x,mask=None):
        import theano.tensor as T
        newx = T.sort(x)
        #response = K.reverse(newx, axes=1)
        #response = K.sum(x> 0.5, axis=1) / self.k
        return newx
        #response = K.reshape(newx,[-1,1])
        #return K.concatenate([1-response, response], axis=self.label)
        #response = K.reshape(x[:,self.axis], (-1,1))
        #return K.concatenate([1-response, response], axis=self.axis)
        #e = K.exp(x - K.max(x, axis=self.axis, keepdims=True))
        #s = K.sum(e, axis=self.axis, keepdims=True)
        #return e / s 

def call(self, x,mask=None):
        response = K.reshape(x[:,self.axis], (-1,1))
        return K.concatenate([1-response, response], axis=self.axis)
        #e = K.exp(x - K.max(x, axis=self.axis, keepdims=True))
        #s = K.sum(e, axis=self.axis, keepdims=True)
        #return e / s 

def preprocess_input(self, x):
    if self.consume_less == 'cpu':
      input_shape = self.input_spec[0].shape
      input_dim = input_shape[2]
      timesteps = input_shape[1]

      x_t = time_distributed_dense(x, self.W_t, self.b_t, self.dropout_W,
                                   input_dim, self.output_dim, timesteps)
      x_h = time_distributed_dense(x, self.W_h, self.b_h, self.dropout_W,
                                   input_dim, self.output_dim, timesteps)
      return K.concatenate([x_t, x_h], axis=2)
    else:
      return x