How to match values of logits and labels while creating a GAN?

Question

I am trying to train a GAN(Generative Adversarial Network) and I am getting the following error :

ValueError: logits and labels must have the same shape, received ((1, 48, 64, 1) vs (1, 48, 48, 1)).

This is an image of the error I get. Can someone help me?

Is it a error regarding different outputs sizes? I will try to provide as much code as possible . The RGB images are 768x1024

def train(d_model, g_model, gan_model, dataset, n_epochs=100, n_batch=1):
    # determine the output square shape of the discriminator
    n_patch = d_model.output_shape[1]
    # unpack dataset
    trainA, trainB = dataset
    # calculate the number of batches per training epoch
    bat_per_epo = int(len(trainA) / n_batch)
    print("LEN : {}\nN_BATCH : {}".format(len(trainA),n_batch))
    # calculate the number of training iterations
    n_steps = bat_per_epo * n_epochs
    # manually enumerate epochs
    for i in range(n_steps):
        # select a batch of real samples
        [X_realA, X_realB], y_real = generate_real_samples(dataset, n_batch, n_patch)
        # generate a batch of fake samples
        X_fakeB, y_fake = generate_fake_samples(g_model, X_realA, n_patch)
        # update discriminator for real samples
        d_loss1 = d_model.train_on_batch([X_realA, X_realB], y_real)
        # update discriminator for generated samples
        d_loss2 = d_model.train_on_batch([X_realA, X_fakeB], y_fake)
        # update the generator
        g_loss, _, _ = gan_model.train_on_batch(X_realA, [y_real, X_realB])
        # summarize performance
        print('>%d, d1[%.3f] d2[%.3f] g[%.3f]' % (i+1, d_loss1, d_loss2, g_loss))
        # summarize model performance
        if (i+1) % (bat_per_epo * 100) == 0:
            plota_salva_modelo(i, g_model, dataset)

def define_generator(image_shape=(768,1024,3)):
    # weight initialization
    init = RandomNormal(stddev=0.02,seed=seed)
    # image input
    in_image = Input(shape=image_shape)
    # encoder model
    e1 = define_encoder_block(in_image, 64, batchnorm=False)
    e2 = define_encoder_block(e1, 128)
    e3 = define_encoder_block(e2, 256)
    e4 = define_encoder_block(e3, 512)
    e5 = define_encoder_block(e4, 512)
    e6 = define_encoder_block(e5, 512)
    e7 = define_encoder_block(e6, 512)
    # bottleneck, no batch norm and relu
    b = Conv2D(512, (4,4), strides=(2,2), padding='same', kernel_initializer=init)(e7)
    b = Activation('relu')(b)
    # decoder model
    d1 = decoder_block(b, e7, 512)
    d2 = decoder_block(d1, e6, 512)
    d3 = decoder_block(d2, e5, 512)
    d4 = decoder_block(d3, e4, 512, dropout=False)
    d5 = decoder_block(d4, e3, 256, dropout=False)
    d6 = decoder_block(d5, e2, 128, dropout=False)
    d7 = decoder_block(d6, e1, 64, dropout=False)
    # output
    g = Conv2DTranspose(3, (4,4), strides=(2,2), padding='same', kernel_initializer=init)(d7)
    out_image = Activation('tanh')(g)
    
    # define model
    model = Model(in_image, out_image)
    return model

def define_discriminator(image_shape):
    # weight initialization
    init = RandomNormal(stddev=0.02,seed=seed)
    # source image input
    in_src_image = Input(shape=image_shape)
    # target image input
    in_target_image = Input(shape=image_shape)
    # concatenate images channel-wise
    merged = Concatenate()([in_src_image, in_target_image])
    # C64
    d = Conv2D(64, (4,4), strides=(2,2), padding='same', kernel_initializer=init)(merged)
    d = LeakyReLU(alpha=0.2)(d)
    # C128
    d = Conv2D(128, (4,4), strides=(2,2), padding='same', kernel_initializer=init)(d)
    d = BatchNormalization()(d)
    d = LeakyReLU(alpha=0.2)(d)
    # C256
    d = Conv2D(256, (4,4), strides=(2,2), padding='same', kernel_initializer=init)(d)
    d = BatchNormalization()(d)
    d = LeakyReLU(alpha=0.2)(d)
    # C512
    d = Conv2D(512, (4,4), strides=(2,2), padding='same', kernel_initializer=init)(d)
    d = BatchNormalization()(d)
    d = LeakyReLU(alpha=0.2)(d)
    # second last output layer
    d = Conv2D(512, (4,4), padding='same', kernel_initializer=init)(d)
    d = BatchNormalization()(d)
    d = LeakyReLU(alpha=0.2)(d)
    # patch output
    d = Conv2D(1, (4,4), padding='same', kernel_initializer=init)(d)
    patch_out = Activation('sigmoid')(d)
    # define model
    model = Model([in_src_image, in_target_image], patch_out)
    # compile model
    opt = Adam(learning_rate=0.0002, beta_1=0.5)
    model.compile(loss='binary_crossentropy', optimizer=opt, loss_weights=[0.5])
    return model

# define an encoder block
def define_encoder_block(layer_in, n_filters, batchnorm=True):
    # weight initialization
    init = RandomNormal(stddev=0.02,seed=seed)
    # add downsampling layer
    g = Conv2D(n_filters, (4,4), strides=(2,2), padding='same', kernel_initializer=init)(layer_in)
    # conditionally add batch normalization
    if batchnorm:
        g = BatchNormalization()(g, training=True)
    # leaky relu activation
    g = LeakyReLU(alpha=0.2)(g)
    return g

# define a decoder block
def decoder_block(layer_in, skip_in, n_filters, dropout=True):
    # weight initialization
    init = RandomNormal(stddev=0.02,seed=seed)
    # add upsampling layer
    g = Conv2DTranspose(n_filters, (4,4), strides=(2,2), padding='same', kernel_initializer=init)(layer_in)
    # add batch normalization
    g = BatchNormalization()(g, training=True)
    # conditionally add dropout
    if dropout:
        g = Dropout(0.5)(g, training=True)
    # merge with skip connection
    g = Concatenate()([g, skip_in])
    # relu activation
    g = Activation('relu')(g)
    return g

# load image
dataset = load_real_samples(filename)
print('Loaded', dataset[0].shape)

# A entrada da rede depende do tamanho da imagen
image_shape = dataset[0].shape[1:]
print(image_shape)

# modelos G e D
d_model = define_discriminator(image_shape)
g_model = define_generator(image_shape)

# forma a GAN com o gerador e o discriminador
gan_model = define_gan(g_model, d_model, image_shape)


train(d_model, g_model, gan_model, dataset,n_epochs=1000)

I am still struggling with the code, and cannot seem to find what is wrong with it. I would love if someone could shed a light on this matter. Thank you in advance!