Python 3.x '；非类型'；对象不可调用-带有keras和反向传播的MDN

我已经用很多方法编辑了这段代码，我正在尝试实现一个混合密度网络，它可以获得一维输入并返回二维输出。
我是tensorflow的新手，非常感谢您的帮助。每次我尝试这个，都会出问题。现在它给了我这个错误： TypeError:在转换的代码中：

<ipython-input-127-593edcacdfbd>:6 train_step  *
    mdn_loss = mdn_loss_func(output_dim, num_mixes, x_true, y_true)
<ipython-input-124-785c7bda58fa>:3 mdn_loss_func  *
    y_pred = mdn_model(x_true)
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow_core\python\autograph\impl\api.py:396 converted_call
    return py_builtins.overload_of(f)(*args)

TypeError: 'NoneType' object is not callable

损失函数的定义如下：

def mdn_loss_func(output_dim, num_mixes, x_true, y_true):

        y_pred = mdn_model(x_true)
        print('y_pred shape is {}'.format(y_pred.shape))
        y_pred = tf.reshape(y_pred, [-1, (2 * num_mixes * output_dim) + num_mixes], name='reshape_ypreds')
        y_true = tf.reshape(y_true, [-1, output_dim], name='reshape_ytrue')

        out_mu, out_sigma, out_pi = tf.split(y_pred, num_or_size_splits=[num_mixes * output_dim,
                                                                         num_mixes * output_dim,
                                                                         num_mixes],
                                             axis=-1, name='mdn_coef_split')
        # Construct the mixture models
        cat = tfd.Categorical(logits=out_pi)
        component_splits = [output_dim] * num_mixes
        mus = tf.split(out_mu, num_or_size_splits=component_splits, axis=1)
        sigs = tf.split(out_sigma, num_or_size_splits=component_splits, axis=1)
        coll = [tfd.MultivariateNormalDiag(loc=loc, scale_diag=scale) for loc, scale
                in zip(mus, sigs)]
        mixture = tfd.Mixture(cat=cat, components=coll)
        loss = mixture.log_prob(y_true)
        loss = tf.negative(loss)
        loss = tf.reduce_mean(loss)
        return loss

我使用了keras的Adam优化器：

mdn_optimizer = tf.keras.optimizers.Adam(1e-4)

然后我像这样训练它：

def train(dataset, output_dim, num_mixes, epochs):
  for epoch in range(epochs):
    start = time.time()

    for x_true, y_true in dataset:
      train_step(x_true, y_true, output_dim, num_mixes)

    print ('Time for epoch {} is {} sec'.format(epoch + 1, time.time()-start))


  display.clear_output(wait=True)

---

下面是代码：由于格式错误，请重新格式化上面的代码很难说，但看起来您的

mdn\u模型

函数没有返回任何内容。@IanQuah，是的。感谢您的帮助以下是代码：由于格式错误，请重新格式化上面的代码很难说，但您的

mdn_模型

函数似乎没有返回任何内容。@IanQuah，是的。谢谢你的帮助

@tf.function
def train_step(x_true, y_true, output_dim, num_mixes):

    with tf.GradientTape() as gen_tape, tf.GradientTape() as disc_tape:

      mdn_loss = mdn_loss_func(output_dim, num_mixes, x_true, y_true)

    gradients_of_mdn = gen_tape.gradient(mdn_loss, mdn_model.trainable_variables)

    mdn_optimizer.apply_gradients(zip(gradients_of_mdn, mdn_model.trainable_variables))

def train(dataset, output_dim, num_mixes, epochs):
  for epoch in range(epochs):
    start = time.time()

    for x_true, y_true in dataset:
      train_step(x_true, y_true, output_dim, num_mixes)

    print ('Time for epoch {} is {} sec'.format(epoch + 1, time.time()-start))


  display.clear_output(wait=True)

%%time
train(train_dataset, OUTPUT_DIMS, N_MIXES, EPOCHS)
``````