tf.keras.layers.Dense(
    unITs, activation=None, use_bias=True,
    kernel_initializer='glorot_uniform',
    bias_initializer='zeros', kernel_regularizer=None,
    bias_regularizer=None, activity_regularizer=None, kernel_constraint=None,
    bias_constraint=None, **kwargs
)

# 创建正态分布
x = tf.random.normal([256, 784])

# 创建全连接层, 输出为512
net = tf.keras.layers.Dense(512)
out = net(x)

# 调试输出
PRint("w:", net.kernel.Shape)
print("b:", net.bias.shaPE)

tf.keras.Sequential(
    layers=None, name=None
)

# 创建正态分布
x = tf.random.normal([256, 784])

# 建立网络模型
model = tf.keras.Sequential([
    tf.keras.layers.Dense(256, activation="relu"),
    tf.keras.layers.Dense(128, activation="relu"),
    tf.keras.layers.Dense(10, activation="relu"),
])

# 传入x
model(x)

# 调试输出权重和偏置顶名字和形状
for p in model.trainable_VARiables:
    print(p.name, p.shape)