如何在tensorflow 2 Tensorflow 2 / Keras中制作自定义validation_step？

Question

我对验证数据有疑问。我有这个神经网络，我将数据分为 train_generator、val_generator、test_generator。

我制作了一个具有定制配合的定制模型。

class MyModel(tf.keras.Model):
     def __init__(self):
     def __call__(.....)
     def train_step(....)

那么我有：

 train_generator = DataGenerator(....)
 val_generator = DataGenerator(....)
 test_generator = DataGenerator(....)

然后 ：

 model = MyModel()
 model.compile(optimizer=keras.optimizers.Adam(clipnorm=5.),
               metrics=["accuracy"])
 model.fit(train_generator, validation_data = val_generator, epochs=40)

好的，程序没有给我任何错误，但我的问题是：我如何知道我的validation_data发生了什么？它的处理方式是否与 train_step 函数中的 train_data (train_generator) 相同？或者我是否需要指定如何处理验证数据？

如果有帮助的话我也会参加 MyModel 课程

class MyModel(tf.keras.Model):
def __init__(self):
    super(MyModel2, self).__init__()
    self.dec2 = Decoder2()

def __call__(self, y_hat, **kwargs): 

    print(y_hat.shape)

    z_hat = self.dec2(y_hat)
    return z_hat

def train_step(self, dataset): 
    with tf.GradientTape() as tape:

        y_hat = dataset[0]
        z_true = dataset[1]

        z_pred = self(y_hat, training=True)

        #print("This is z_true : ", z_true.shape)
        #print("This is z_pred : ", z_pred.shape)
        loss = tf.reduce_mean(tf.abs(tf.cast(z_pred, tf.float64) - tf.cast(z_true, tf.float64)))
        print("loss: ", loss)
        global_loss.append(loss)

    # Compute gradients. TRE SA FAC GRADIENT CLIPPING
    trainable_vars = self.trainable_variables
    gradients = tape.gradient(loss, trainable_vars)
    # Update weights
    self.optimizer.apply_gradients(zip(gradients, trainable_vars))
    # Update metrics (includes the metric that tracks the loss)
    self.compiled_metrics.update_state(z_true, z_pred)
    # Return a dict mapping metric names to current value
    return {m.name: m.result() for m in self.metrics}

Answer 1

您必须将 test_step(self, data) 函数添加到 MyModel 类，如您在此处看到的：提供您自己的评估步骤