我们可以在不使用keras的情况下在tensorflow2.0中训练模型吗？

import tensorflow as tf

# 定义模型
class MyModel(tf.keras.Model):
    def __init__(self):
        super(MyModel, self).__init__()
        self.dense = tf.keras.layers.Dense(units=10)

    def call(self, inputs):
        return self.dense(inputs)

# 准备数据
x_train = ...
y_train = ...

# 创建模型实例
model = MyModel()

# 定义损失函数和优化器
loss_object = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
optimizer = tf.keras.optimizers.Adam()

# 定义训练步骤
@tf.function
def train_step(inputs, labels):
    with tf.GradientTape() as tape:
        predictions = model(inputs)
        loss = loss_object(labels, predictions)
    gradients = tape.gradient(loss, model.trainable_variables)
    optimizer.apply_gradients(zip(gradients, model.trainable_variables))
    return loss

# 执行训练循环
for epoch in range(num_epochs):
    for batch_inputs, batch_labels in train_dataset:
        loss = train_step(batch_inputs, batch_labels)
        # 打印训练损失等信息

# 使用训练好的模型进行预测
x_test = ...
predictions = model(x_test)