输入与图层不兼容 - Tensorflow

Question

我目前面临 Tensorflow 库的问题，我无法解决。 我已经在 stackoverflow 上找到的所有解决方案都没有帮助我理解真正的问题。

def build_model(dim_data, n_neurons):

model = tf.keras.Sequential(name="Reseau_de_neurones")

model.add(layers.Dense(units = n_neurons, input_shape=(3, 1), bias_initializer="glorot_uniform")) 
model.add(layers.ReLU())
model.add(layers.Dense(units = n_neurons, input_shape=(dim_data,), bias_initializer="glorot_uniform")) 
model.add(layers.ReLU())
model.add(layers.Dense(units = n_neurons, input_shape=(dim_data,),  bias_initializer="glorot_uniform")) 
model.add(layers.ReLU())
model.add(layers.Dense(units = n_neurons, input_shape=(dim_data,), bias_initializer="glorot_uniform")) 
model.add(layers.ReLU())
model.add(layers.Dense(units = dim_data - 1, bias_initializer="glorot_uniform")) 

return model

然后我构建我的神经网络：

model = build_model(dim_data=3, n_neurons=10)

然后我定义一个训练步骤：

def train_step(model):

   with tf.GradientTape() as tape:
    pos = [0,0]
    controle_actuel = model(np.array([0,pos[0],pos[1]]))
    loss_value = loss
   gradients = tape.gradient(loss_value, model.trainable_variables)
   return loss_value, gradients

当我尝试这个 function 时，我得到了这个错误

input 0 of layer "dense_37" is incompatible with the layer: expected min_ndim=2, found ndim=1. Full shape received: (3,)

请你帮助我好吗？