errore 形状必须为 1 级但为 2 级

Question

感谢您对此 TensorFlow 代码的帮助。当我尝试运行此代码时

def fine_tune(num_classes,
              num_hidden=64,
              activation='softmax',
              regularization=0.03,
              ):


model = yamnet_frames_model(Params())
x = model.layers[-6].output
output= Dense(num_classes, activation=activation)(x)
model = Model(inputs=model.input, outputs=output)
print(model.summary())
return model

我收到以下错误

ValueError: Shape must be rank 1 but is rank 2 for '{{node model/tf.compat.v1.pad_2/Pad}} = Pad[T=DT_FLOAT, Tpaddings=DT_INT32](IteratorGetNext, model/tf.compat.v1.pad_2/Pad/paddings)' with input shapes: [?,1024], [1,2].