AttributeError: 'KerasTensor' object has no attribute 'train_on_batch'

Question

実現したいこと

https://github.com/crmaximo/VAEGAN/blob/master/VAEGAN.py
のコードを動かそうとしています。

githubのVAEGANコードをtensorflow.kerasに変えて動かしてみようとしています。

AttributeError: 'KerasTensor' object has no attribute 'train_on_batch'

該当のソースコード

def discriminator(kernel, filter, rows, columns, channel):
    X = Input(shape=(rows, columns, channel))

    model = Conv2D(filters=filter*2, kernel_size=kernel, strides=2, padding='same')(X)
    model = LeakyReLU(alpha=0.2)(model)
    model = Conv2D(filters=filter*4, kernel_size=kernel, strides=2, padding='same')(model)
    model = BatchNormalization(epsilon=1e-5)(model)
    model = LeakyReLU(alpha=0.2)(model)
    model = Conv2D(filters=filter*8, kernel_size=kernel, strides=2, padding='same')(model)
    model = BatchNormalization(epsilon=1e-5)(model)
    model = LeakyReLU(alpha=0.2)(model)
    model = Conv2D(filters=filter*8, kernel_size=kernel, strides=2, padding='same')(model)

    dec = BatchNormalization(epsilon=1e-5)(model)
    dec = LeakyReLU(alpha=0.2)(dec)    
    dec = Flatten()(dec)
    dec = Dense(1, activation='sigmoid')(dec)

    output = keras.Model([X], [dec, model])
    return output

dataset.shape=(2000,64,64,3)
rows = 64
columns = 64
channel = 3
X = Input(shape=(rows, columns, channel))

D = discriminator(5, 32, rows, columns, channel)
D.compile(optimizer=SGDop, loss='mse')
D_true, F_true = D(X)

DlossTrue = D_true.train_on_batch(dataset, np.ones((batch_size, 1)))

D_trueがModelになっていないのでtrain_on_batchできないのでしょうか？

Answer 1

D_trueがModelになっていないのでtrain_on_batchできないのでしょうか？

はいそうです．