Keras実装中のエラー対処

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D
from tensorflow.keras.layers import MaxPool2D
from tensorflow.keras.optimizers import Adam

import tensorflow as tf
from tensorflow.keras.models import Sequential, Model
!pip install git+https://www.github.com/keras-team/keras-contrib.git
from tensorflow.keras.layers import Input,Dense, Activation, Dropout, Flatten,LeakyReLU,UpSampling2D,Concatenate
from keras_contrib.layers.normalization.instancenormalization import InstanceNormalization
from tensorflow.keras.utils import plot_model, to_categorical
from keras.callbacks import TensorBoard

class Generator():
  def __init__(self):
    self.img_rows = 256
    self.img_cols = 256
    self.channels = 3
    self.img_shape = (self.img_rows, self.img_rows, self.channels)
    self.gf = 32

  def encode(self,layer_input,filter_size,f_size = 4, normalization = True):
    d = Conv2D(filter_size,kernel_size = f_size,strides = 2,padding = "same")(layer_input)
    d = LeakyReLU(alpha = 0.2)(d)
    if normalization:
      d = InstanceNormalization()(d)
    return d

  def decode(self,layer_input,marge_layer,filter_size,f_size = 4, normalization = True,dropout_rate=0):
    u = UpSampling2D(size = 2)(layer_input)
    u = Conv2D(filter_size,kernel_size = f_size,strides = 1,padding = "same",activation="relu")(u)
    if dropout_rate:
      u = Dropout(dropout_rate)(u)
    u = InstanceNormalization()(u)
    u = Concatenate()([u,marge_layer])
    return u
  
  def forward(self):
    #make layer
    self.d0 = Input(shape = self.img_shape)
    # down sampling
    self.d1 = self.encode(self.d0,self.gf)
    self.d2 = self.encode(self.d1,self.gf*2)
    self.d3 = self.encode(self.d2,self.gf*4)
    self.d4 = self.encode(self.d3,self.gf*8)
    # up sampling
    self.u1 = self.decode(self.d4,self.d3,self.gf *4)
    self.u2 = self.decode(self.u1,self.d2,self.gf *2)
    self.u3 = self.decode(self.u2,self.d1,self.gf)
    #output layer
    self.u4 = UpSampling2D(size = 2)(self.u3)
    self.u5 = Conv2D(self.channels,kernel_size=4,strides = 1,padding="same",activation="tanh")(self.u4)
    return self.u5

model = Generator()
a = model.forward()
a.summary()