Keras功能API：需要多个输入的拟合和测试模型

Question

我构建了一个Keras模型，该模型具有2个分支，每个分支对同一数据采用不同的特征表示。任务是将句子分为6类。

我已经测试了直到model.fit的代码，该代码接受一个包含两个输入要素矩阵的列表，分别为X。一切正常。但是在预测时，当我将两个输入特征矩阵传递给测试数据时，会生成错误。

代码如下：

X_train_feature1 = ... # shape: (2200, 100) each row a sentence and each column a feature
X_train_feature2 = ... # shape: (2200, 13) each row a sentence and each column a feature
y_train= ... # shape: (2200,6)


X_test_feature1 = ... # shape: (587, 100) each row a sentence and each column a feature
X_test_feature2 = ... # shape: (587, 13) each row a sentence and each column a feature
y_test= ... # shape: (587,6)

model= ... #creating a model with 2 branches, see the image below

model.fit([X_train_feature1, X_train_feature2],y_train,epochs=100, batch_size=10, verbose=2) #Model trains ok
model.predict([X_test_feature1, X_test_feature2],y_test,epochs=100, batch_size=10, verbose=2) #error here

该模型如下所示：

错误是：

predictions = model.predict([X_test_feature1,X_test_feature2], y_test, verbose=2)
  File "/home/zz/Programs/anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 1748, in predict
    verbose=verbose, steps=steps)
  File "/home/zz/Programs/anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 1290, in _predict_loop
    batches = _make_batches(num_samples, batch_size)
  File "/home/zz/Programs/anaconda3/lib/python3.6/site-packages/keras/engine/training.py", line 384, in _make_batches
    num_batches = int(np.ceil(size / float(batch_size)))
TypeError: only length-1 arrays can be converted to Python scalars

我非常感谢您提供一些帮助，以了解该错误以及如何解决该错误。

Answer 1

predict method仅将数据（即x）和batch_size（无需设置）作为输入。它不使用标签或纪元作为输入。

如果要预测类别，则应使用predict_classes方法，该方法为您提供预测的类别标签（而不是predict方法提供的概率）：

preds_prob = model.predict([X_test_feature1, X_test_feature2])
preds = model.predict_classes([X_test_feature1, X_test_feature2])

如果您要根据测试数据评估模型以找到损耗和度量值，则应使用evaluate方法：

loss_metrics = model.evaluate([X_test_feature1, X_test_feature2], y_test)