Exception encountered when calling TimeDistributed.call()

[Yogesh_Sharma]

I’m getting this weird exception while running the exact notebook that’s given source

net = tf.keras.applications.EfficientNetB0(include_top = False)
net.trainable = False

model = tf.keras.Sequential([
    tf.keras.layers.Rescaling(scale=255),
    tf.keras.layers.TimeDistributed(net),
    tf.keras.layers.Dense(10),
    tf.keras.layers.GlobalAveragePooling3D()
])

model.compile(optimizer = 'adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits = True),
              metrics=['accuracy'])

model.fit(x=train_ds, 
          epochs = 10,
          validation_data = val_ds,
          callbacks = tf.keras.callbacks.EarlyStopping(patience = 2, monitor = 'val_loss'))

[Kiran_Sai_Ramineni]

Hi @Yogesh_Sharma, I have executed the above tutorial in the latest tensorflow version(TF2.17) and did not face any error. please refer to this gist. Thank You.