在Keras的循环中创建带有Lamda层的load_model

Question

我有一个功能模型，该模型在具有<div class="container"> <p class="section-description" id="txt">Today I went to the zoo. I saw a(n) <input placeholder="noun" id="noun1"> <input placeholder="adjective" id="adjective1"> jumping up and down in its tree. He <input placeholder="verb, past tense" id="verb1"> <input placeholder="adverb" id="adverb1"> through the large tunnel that led to its <input placeholder="adjective" id="adjective2"> <input placeholder="noun" id="noun2">. I got some peanuts and passed them through the cage to a gigantic gray <input placeholder="noun" id="noun3"> towering above my head. Feeding that animal made me. </p> </div>层的keras循环中创建多个门：

int 16h

当我尝试加载模型时，它抱怨：

Lambda

在添加predictions = [] for ii, kk in enumerate(label_cols): slicer = Lambda(lambda x: x[:,:,:,ii:ii+1], output_shape=gates_shape[:-2]+(1,), name='slice_'+kk) gate_ = slicer(gates) ... prediction = Dense(n_classes[kk], activation=final_activation, name=kk)(x) predictions.append(prediction) 之前，一切正常。 正确的方法是什么？

Answer 1

ii变量不在lambda范围内，因此您必须将其通过arguments传递。

尝试：

x = Lambda(lambda x,ii: x[:,:,:,ii:ii+1], arguments={'ii':ii})