![](/img/trans.png)
[英]Tensorflow Conv2D layers input_shape configuration error: ValueError: Input 0 of layer "sequential" is incompatible with the layer:
[英]Input incompatible with layers - Tensorflow
我目前面臨 Tensorflow 庫的問題,我無法解決。 我已經在 stackoverflow 上找到的所有解決方案都沒有幫助我理解真正的問題。
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
然后我構建我的神經網絡:
model = build_model(dim_data=3, n_neurons=10)
然后我定義一個訓練步驟:
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
當我嘗試這個 function 時,我得到了這個錯誤
input 0 of layer "dense_37" is incompatible with the layer: expected min_ndim=2, found ndim=1. Full shape received: (3,)
請你幫助我好嗎?
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.