Python keras.backend.reshape() Examples

def call(self, x):
        mean = K.mean(x, axis=-1)
        std = K.std(x, axis=-1)

        if len(x.shape) == 3:
            mean = K.permute_dimensions(
                K.repeat(mean, x.shape.as_list()[-1]),
                [0,2,1]
            )
            std = K.permute_dimensions(
                K.repeat(std, x.shape.as_list()[-1]),
                [0,2,1] 
            )
            
        elif len(x.shape) == 2:
            mean = K.reshape(
                K.repeat_elements(mean, x.shape.as_list()[-1], 0),
                (-1, x.shape.as_list()[-1])
            )
            std = K.reshape(
                K.repeat_elements(mean, x.shape.as_list()[-1], 0),
                (-1, x.shape.as_list()[-1])
            )
        
        return self._g * (x - mean) / (std + self._epsilon) + self._b 

def call(self, x, mask=None):
        # computes a probability distribution over the timesteps
        # uses 'max trick' for numerical stability
        # reshape is done to avoid issue with Tensorflow
        # and 1-dimensional weights
        logits = K.dot(x, self.W)
        x_shape = K.shape(x)
        logits = K.reshape(logits, (x_shape[0], x_shape[1]))
        ai = K.exp(logits - K.max(logits, axis=-1, keepdims=True))

        # masked timesteps have zero weight
        if mask is not None:
            mask = K.cast(mask, K.floatx())
            ai = ai * mask
        att_weights = ai / (K.sum(ai, axis=1, keepdims=True) + K.epsilon())
        weighted_input = x * K.expand_dims(att_weights)
        result = K.sum(weighted_input, axis=1)
        if self.return_attention:
            return [result, att_weights]
        return result 

def call(self,x,mask=None):
        conv_input,theta = x
        s = theta.shape
        theta = T.reshape(theta,[-1,s[2]])
        m = K.not_equal(conv_input,0.)

        #### For translation
        trans = _trans(theta)
        output = _transform_trans(trans, conv_input)
        output = output * K.cast(m,K.floatx())

        ### For rotation
        M = _fusion(theta)
        output = _transform_rot(M,output)

        return output 

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 get_output(self, train=False):
        def format_shape(shape):
            if K._BACKEND == 'tensorflow':
                def trf(x):
                    try:
                        return int(x)
                    except TypeError:
                        return x

                return map(trf, shape)
            return shape

        X = self.get_input(train)

        in_shape = format_shape(K.shape(X))
        batch_flatten_len = K.prod(in_shape[:2])
        cast_in_shape = (batch_flatten_len, ) + tuple(in_shape[i] for i in range(2, K.ndim(X)))
        
        pre_outs = self.layer(K.reshape(X, cast_in_shape))
        
        out_shape = format_shape(K.shape(pre_outs))
        cast_out_shape = (in_shape[0], in_shape[1]) + tuple(out_shape[i] for i in range(1, K.ndim(pre_outs)))
        
        outputs = K.reshape(pre_outs, cast_out_shape)
        return outputs 

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 get_constants(self, x):
		constants = []
		if 0 < self.dropout_U < 1:
			ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
			ones = K.tile(ones, (1, self.hidden_recurrent_dim))
			B_U = K.in_train_phase(K.dropout(ones, self.dropout_U), ones)
			constants.append(B_U)
		else:
			constants.append(K.cast_to_floatx(1.))
        
		if self.consume_less == 'cpu' and 0 < self.dropout_W < 1:
			input_shape = self.input_spec[0].shape
			input_dim = input_shape[-1]
			ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
			ones = K.tile(ones, (1, input_dim))
			B_W = K.in_train_phase(K.dropout(ones, self.dropout_W), ones)
			constants.append(B_W)
		else:
			constants.append(K.cast_to_floatx(1.))

		return constants 

def get_constants(self, x):
		constants = []
		if 0 < self.dropout_U < 1:
			ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
			ones = K.tile(ones, (1, self.input_dim))
			B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(4)]
			constants.append(B_U)
		else:
			constants.append([K.cast_to_floatx(1.) for _ in range(4)])

		if 0 < self.dropout_W < 1:
			input_shape = K.int_shape(x)
			input_dim = input_shape[-1]
			ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
			ones = K.tile(ones, (1, int(input_dim)))
			B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(4)]
			constants.append(B_W)
		else:
			constants.append([K.cast_to_floatx(1.) for _ in range(4)])
		return constants 

def contrastive_divergence_loss(self, y_true, y_pred):

		x = y_pred
		#x = K.reshape(x, (-1, self.input_dim))

		if(self.is_persistent):
			chain_start = self.persistent_chain
		else:
			chain_start = x

		def loss(chain_start, x):
			x_rec, _, _ = self.mcmc_chain(chain_start, self.nb_gibbs_steps)
			cd = K.mean(self.free_energy(x)) - K.mean(self.free_energy(x_rec))
			return cd, x_rec

		y, x_rec = loss(chain_start, x)

		if(self.is_persistent):
			self.updates = [(self.persistent_chain, x_rec)]

		return y 

def call(self, inputs):
        def wrapper(rois, mrcnn_class, mrcnn_bbox, image_meta):
            # currently supports one image per batch
            b = 0
            _, _, window, _ = parse_image_meta(image_meta)
            detections = refine_detections(
                rois[b], mrcnn_class[b], mrcnn_bbox[b], window[b], self.config)
            # Pad with zeros if detections < DETECTION_MAX_INSTANCES
            gap = self.config.DETECTION_MAX_INSTANCES - detections.shape[0]
            assert gap >= 0
            if gap > 0:
                detections = np.pad(detections, [(0, gap), (0, 0)],
                                    'constant', constant_values=0)

            # Cast to float32
            # TODO: track where float64 is introduced
            detections = detections.astype(np.float32)

            # Reshape output
            # [batch, num_detections, (y1, x1, y2, x2, class_score)] in pixels
            return np.reshape(detections,
                              [1, self.config.DETECTION_MAX_INSTANCES, 6])

        # Return wrapped function
        return tf.py_func(wrapper, inputs, tf.float32) 

def ifft2(x):
	ff = x
	ff = KB.permute_dimensions(ff, (0, 2, 1))
	ff = KB.reshape(ff, (x.shape[0] *x.shape[2], x.shape[1]))
	tf = ifft(ff)
	tf = KB.reshape(tf, (x.shape[0], x.shape[2], x.shape[1]))
	tf = KB.permute_dimensions(tf, (0, 2, 1))
	tf = KB.reshape(tf, (x.shape[0] *x.shape[1], x.shape[2]))
	tt = ifft(tf)
	tt = KB.reshape(tt, (x.shape[0], x.shape[1], x.shape[2]))
	return tt

#
# FFT Layers:
#
#  FFT:   Batched 1-D FFT  (Input: (Batch, FeatureMaps, TimeSamples))
#  IFFT:  Batched 1-D IFFT (Input: (Batch, FeatureMaps, FreqSamples))
#  FFT2:  Batched 2-D FFT  (Input: (Batch, FeatureMaps, TimeSamplesH, TimeSamplesW))
#  IFFT2: Batched 2-D IFFT (Input: (Batch, FeatureMaps, FreqSamplesH, FreqSamplesW))
# 

def call(self, x, mask=None):
		a = KB.permute_dimensions(x, (1,0,2,3))
		a = KB.reshape(a, (x.shape[1] *x.shape[0], x.shape[2], x.shape[3]))
		a = ifft2(a)
		a = KB.reshape(a, (x.shape[1], x.shape[0], x.shape[2], x.shape[3]))
		return KB.permute_dimensions(a, (1,0,2,3))



#
# Tests
#
# Note: The IFFT is the conjugate of the FFT of the conjugate.
#
#     np.fft.ifft(x) == np.conj(np.fft.fft(np.conj(x)))
# 

def call(self, x, mask=None):

        assert self.built, 'Layer must be built before being called'
        input_shape = K.int_shape(x)

        reduction_axes = list(range(len(input_shape)))
        del reduction_axes[self.axis]
        broadcast_shape = [1] * len(input_shape)
        broadcast_shape[self.axis] = input_shape[self.axis]

        if sorted(reduction_axes) == range(K.ndim(x))[:-1]:
            x_normed = K.batch_normalization(
                x, self.running_mean, self.running_std,
                self.beta, self.gamma,
                epsilon=self.epsilon)
        else:
            # need broadcasting
            broadcast_running_mean = K.reshape(self.running_mean, broadcast_shape)
            broadcast_running_std = K.reshape(self.running_std, broadcast_shape)
            broadcast_beta = K.reshape(self.beta, broadcast_shape)
            broadcast_gamma = K.reshape(self.gamma, broadcast_shape)
            x_normed = K.batch_normalization(
                x, broadcast_running_mean, broadcast_running_std,
                broadcast_beta, broadcast_gamma,
                epsilon=self.epsilon)

        return x_normed 

def _transform_trans(theta,input):
    batch1, step1, dim1 = input.shape
    input = K.reshape(input,(batch1,step1,dim1//3,3))
    input = K.reshape(input,(batch1*step1,dim1//3,3))
    input = K.permute_dimensions(input,[0,2,1])
    add = T.ones((batch1*step1,1,dim1//3))
    input= K.concatenate([input,add],axis=1)

    output = K.batch_dot(theta,input)
    output = K.permute_dimensions(output,[0,2,1])
    output = K.reshape(output,(output.shape[0],dim1))
    output = K.reshape(output,(batch1,step1,output.shape[1]))

    return output 

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 _rotation_y(theta):
    r1 = K.cos(theta[:,0:1])
    r2 = K.sin(theta[:,0:1])
    zero = K.zeros_like(r1)
    one = K.ones_like(r1)
    first = K.reshape(K.concatenate([r1,zero,r2,zero],axis=1),(-1,1,4))
    second = K.reshape(K.concatenate([zero,one,zero,zero],axis=1),(-1,1,4))
    third = K.reshape(K.concatenate([-r2,zero,r1,zero],axis=1),(-1,1,4))
    fourth = K.reshape(K.concatenate([zero,zero,zero,one],axis=1),(-1,1,4))
    rotation_y = K.concatenate([first,second,third,fourth],axis=1)
    rotation_y = T.reshape(rotation_y,[-1,4,4])
    return rotation_y 

def _rotation_x(theta):
    r1 = K.cos(theta[:,1:2])
    r2 = K.sin(theta[:,1:2])
    zero = K.zeros_like(r1)
    one = K.ones_like(r1)
    first = K.reshape(K.concatenate([one,zero,zero,zero],axis=1),(-1,1,4))
    second = K.reshape(K.concatenate([zero,r1,-r2,zero],axis=1),(-1,1,4))
    third = K.reshape(K.concatenate([zero,r2,r1,zero],axis=1),(-1,1,4))
    fourth = K.reshape(K.concatenate([zero,zero,zero,one],axis=1),(-1,1,4))
    rotation_x = K.concatenate([first,second,third,fourth],axis=1)
    rotation_x = T.reshape(rotation_x,[-1,4,4])
    return rotation_x 

def _trans_rot_new(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))
    fourth = K.reshape(K.concatenate([zero,zero,zero,one],axis=1),(-1,1,4))
    trans = K.concatenate([first,second,third,fourth],axis=1)

    trans = T.reshape(trans,[-1,4,4])
    return trans 

def _transform_rot(theta,input):

    batch1, step1, dim1 = input.shape
    input = T.reshape(input,[-1,dim1//3,3])
    input = K.permute_dimensions(input,[0,2,1])
    add = T.ones((batch1*step1,1,dim1//3))
    input= K.concatenate([input,add],axis=1)

    output = K.batch_dot(theta,input)
    output = K.permute_dimensions(output,[0,2,1])
    output = output[:,:,0:3]
    output = T.reshape(output,[-1,dim1])
    output = T.reshape(output,[-1,step1,dim1])

    return output 

def overlaps_graph(boxes1, boxes2):
    """Computes IoU overlaps between two sets of boxes.
    boxes1, boxes2: [N, (y1, x1, y2, x2)].
    """
    # 1. Tile boxes2 and repeat boxes1. This allows us to compare
    # every boxes1 against every boxes2 without loops.
    # TF doesn't have an equivalent to np.repeat() so simulate it
    # using tf.tile() and tf.reshape.
    b1 = tf.reshape(tf.tile(tf.expand_dims(boxes1, 1),
                            [1, 1, tf.shape(boxes2)[0]]), [-1, 4])
    b2 = tf.tile(boxes2, [tf.shape(boxes1)[0], 1])
    # 2. Compute intersections
    b1_y1, b1_x1, b1_y2, b1_x2 = tf.split(b1, 4, axis=1)
    b2_y1, b2_x1, b2_y2, b2_x2 = tf.split(b2, 4, axis=1)
    y1 = tf.maximum(b1_y1, b2_y1)
    x1 = tf.maximum(b1_x1, b2_x1)
    y2 = tf.minimum(b1_y2, b2_y2)
    x2 = tf.minimum(b1_x2, b2_x2)
    intersection = tf.maximum(x2 - x1, 0) * tf.maximum(y2 - y1, 0)
    # 3. Compute unions
    b1_area = (b1_y2 - b1_y1) * (b1_x2 - b1_x1)
    b2_area = (b2_y2 - b2_y1) * (b2_x2 - b2_x1)
    union = b1_area + b2_area - intersection
    # 4. Compute IoU and reshape to [boxes1, boxes2]
    iou = intersection / union
    overlaps = tf.reshape(iou, [tf.shape(boxes1)[0], tf.shape(boxes2)[0]])
    return overlaps 

def call(self, inputs):
        rois = inputs[0]
        mrcnn_class = inputs[1]
        mrcnn_bbox = inputs[2]
        image_meta = inputs[3]

        # Get windows of images in normalized coordinates. Windows are the area
        # in the image that excludes the padding.
        # Use the shape of the first image in the batch to normalize the window
        # because we know that all images get resized to the same size.
        m = parse_image_meta_graph(image_meta)
        image_shape = m['image_shape'][0]
        window = norm_boxes_graph(m['window'], image_shape[:2])

        # Run detection refinement graph on each item in the batch
        detections_batch = utils.batch_slice(
            [rois, mrcnn_class, mrcnn_bbox, window],
            lambda x, y, w, z: refine_detections_graph(x, y, w, z, self.config),
            self.config.IMAGES_PER_GPU)

        # Reshape output
        # [batch, num_detections, (y1, x1, y2, x2, class_id, class_score)] in
        # normalized coordinates
        return tf.reshape(
            detections_batch,
            [self.config.BATCH_SIZE, self.config.DETECTION_MAX_INSTANCES, 6]) 

def rpn_graph(feature_map, anchors_per_location, anchor_stride):
    """Builds the computation graph of Region Proposal Network.
    feature_map: backbone features [batch, height, width, depth]
    anchors_per_location: number of anchors per pixel in the feature map
    anchor_stride: Controls the density of anchors. Typically 1 (anchors for
                   every pixel in the feature map), or 2 (every other pixel).
    Returns:
        rpn_class_logits: [batch, H * W * anchors_per_location, 2] Anchor classifier logits (before softmax)
        rpn_probs: [batch, H * W * anchors_per_location, 2] Anchor classifier probabilities.
        rpn_bbox: [batch, H * W * anchors_per_location, (dy, dx, log(dh), log(dw))] Deltas to be
                  applied to anchors.
    """
    # TODO: check if stride of 2 causes alignment issues if the feature map
    # is not even.
    # Shared convolutional base of the RPN
    shared = KL.Conv2D(512, (3, 3), padding='same', activation='relu',
                       strides=anchor_stride,
                       name='rpn_conv_shared')(feature_map)

    # Anchor Score. [batch, height, width, anchors per location * 2].
    x = KL.Conv2D(2 * anchors_per_location, (1, 1), padding='valid',
                  activation='linear', name='rpn_class_raw')(shared)

    # Reshape to [batch, anchors, 2]
    rpn_class_logits = KL.Lambda(
        lambda t: tf.reshape(t, [tf.shape(t)[0], -1, 2]))(x)

    # Softmax on last dimension of BG/FG.
    rpn_probs = KL.Activation(
        "softmax", name="rpn_class_xxx")(rpn_class_logits)

    # Bounding box refinement. [batch, H, W, anchors per location * depth]
    # where depth is [x, y, log(w), log(h)]
    x = KL.Conv2D(anchors_per_location * 4, (1, 1), padding="valid",
                  activation='linear', name='rpn_bbox_pred')(shared)

    # Reshape to [batch, anchors, 4]
    rpn_bbox = KL.Lambda(lambda t: tf.reshape(t, [tf.shape(t)[0], -1, 4]))(x)

    return [rpn_class_logits, rpn_probs, rpn_bbox] 

def mrcnn_bbox_loss_graph(target_bbox, target_class_ids, pred_bbox):
    """Loss for Mask R-CNN bounding box refinement.
    target_bbox: [batch, num_rois, (dy, dx, log(dh), log(dw))]
    target_class_ids: [batch, num_rois]. Integer class IDs.
    pred_bbox: [batch, num_rois, num_classes, (dy, dx, log(dh), log(dw))]
    """
    # Reshape to merge batch and roi dimensions for simplicity.
    target_class_ids = K.reshape(target_class_ids, (-1,))
    target_bbox = K.reshape(target_bbox, (-1, 4))
    pred_bbox = K.reshape(pred_bbox, (-1, K.int_shape(pred_bbox)[2], 4))

    # Only positive ROIs contribute to the loss. And only
    # the right class_id of each ROI. Get their indices.
    positive_roi_ix = tf.where(target_class_ids > 0)[:, 0]
    positive_roi_class_ids = tf.cast(
        tf.gather(target_class_ids, positive_roi_ix), tf.int64)
    indices = tf.stack([positive_roi_ix, positive_roi_class_ids], axis=1)

    # Gather the deltas (predicted and true) that contribute to loss
    target_bbox = tf.gather(target_bbox, positive_roi_ix)
    pred_bbox = tf.gather_nd(pred_bbox, indices)

    # Smooth-L1 Loss
    loss = K.switch(tf.size(target_bbox) > 0,
                    smooth_l1_loss(y_true=target_bbox, y_pred=pred_bbox),
                    tf.constant(0.0))
    loss = K.mean(loss)
    return loss 

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

    # Adjust preditions to each spatial grid point and anchor size.
    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 yolo_boxes_and_scores(feats, anchors, num_classes, input_shape, image_shape):
    '''Process Conv layer output'''
    box_xy, box_wh, box_confidence, box_class_probs = yolo_head(feats,
        anchors, num_classes, input_shape)
    boxes = yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape)
    boxes = K.reshape(boxes, [-1, 4])
    box_scores = box_confidence * box_class_probs
    box_scores = K.reshape(box_scores, [-1, num_classes])
    return boxes, box_scores 

def yolo_eval(yolo_outputs,
              image_shape,
              max_boxes=10,
              score_threshold=.6,
              iou_threshold=.5):
    """Evaluate YOLO model on given input batch and return filtered boxes."""
    box_xy, box_wh, box_confidence, box_class_probs = yolo_outputs
    boxes = yolo_boxes_to_corners(box_xy, box_wh)
    boxes, scores, classes = yolo_filter_boxes(
        boxes, box_confidence, box_class_probs, threshold=score_threshold)

    # Scale boxes back to original image shape.
    height = image_shape[0]
    width = image_shape[1]
    image_dims = K.stack([height, width, height, width])
    image_dims = K.reshape(image_dims, [1, 4])
    boxes = boxes * image_dims

    # TODO: Something must be done about this ugly hack!
    max_boxes_tensor = K.variable(max_boxes, dtype='int32')
    K.get_session().run(tf.variables_initializer([max_boxes_tensor]))
    nms_index = tf.image.non_max_suppression(
        boxes, scores, max_boxes_tensor, iou_threshold=iou_threshold)
    boxes = K.gather(boxes, nms_index)
    scores = K.gather(scores, nms_index)
    classes = K.gather(classes, nms_index)
    return boxes, scores, classes 

def call(self, inputs):

        input_shape = K.int_shape(inputs)
        if len(input_shape) != 4:
            raise ValueError('Inputs should have rank ' +
                             str(4) +
                             '; Received input shape:', str(input_shape))

        if self.data_format == 'channels_first':
            batch_size, c, h, w = input_shape
            if batch_size is None:
                batch_size = -1
            rh, rw = self.size
            oh, ow = h * rh, w * rw
            oc = c // (rh * rw)

            out = K.reshape(inputs, (batch_size, rh, rw, oc, h, w))
            out = K.permute_dimensions(out, (0, 3, 4, 1, 5, 2))
            out = K.reshape(out, (batch_size, oc, oh, ow))
            return out

        elif self.data_format == 'channels_last':
            batch_size, h, w, c = input_shape
            if batch_size is None:
                batch_size = -1
            rh, rw = self.size
            oh, ow = h * rh, w * rw
            oc = c // (rh * rw)

            out = K.reshape(inputs, (batch_size, h, w, rh, rw, oc))
            out = K.permute_dimensions(out, (0, 1, 3, 2, 4, 5))
            out = K.reshape(out, (batch_size, oh, ow, oc))
            return out 

def call(self, inputs):

        input_shape = K.int_shape(inputs)
        if len(input_shape) != 4:
            raise ValueError('Inputs should have rank ' +
                             str(4) +
                             '; Received input shape:', str(input_shape))

        if self.data_format == 'channels_first':
            batch_size, c, h, w = input_shape
            if batch_size is None:
                batch_size = -1
            rh, rw = self.size
            oh, ow = h * rh, w * rw
            oc = c // (rh * rw)

            out = K.reshape(inputs, (batch_size, rh, rw, oc, h, w))
            out = K.permute_dimensions(out, (0, 3, 4, 1, 5, 2))
            out = K.reshape(out, (batch_size, oc, oh, ow))
            return out

        elif self.data_format == 'channels_last':
            batch_size, h, w, c = input_shape
            if batch_size is None:
                batch_size = -1
            rh, rw = self.size
            oh, ow = h * rh, w * rw
            oc = c // (rh * rw)

            out = K.reshape(inputs, (batch_size, h, w, rh, rw, oc))
            out = K.permute_dimensions(out, (0, 1, 3, 2, 4, 5))
            out = K.reshape(out, (batch_size, oh, ow, oc))
            return out 

def call(self, x, mask=None):
        input_shape = self.input_spec[0].shape
        broadcast_shape = [1] * len(input_shape)
        broadcast_shape[self.axis] = input_shape[self.axis]

        out = K.reshape(self.gamma, broadcast_shape) * x + K.reshape(self.beta, broadcast_shape)
        return out 

def call(self, x, mask=None):
        input_shape = self.input_spec[0].shape
        broadcast_shape = [1] * len(input_shape)
        broadcast_shape[self.axis] = input_shape[self.axis]

        out = K.reshape(self.gamma, broadcast_shape) * x + K.reshape(self.beta, broadcast_shape)
        return out