预期 input_2 的形状为 (512,) 但得到的数组的形状为 (1,)

Question

我用 Keras 训练了一个 GRU。跑的时候报错

nxt = model.predict([features,embedding_matrix[enc_map[cur]]])

ValueError: Error when checking : expected input_2 to have shape (512,) but got array with shape (1,)

但是 特征.形状 (512,)` 还有

embedding_matrix[enc_map[cur]].shape (50,)

以下是模型摘要：

model.summary()

________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to
================================================================================
input_2 (InputLayer)            (None, 512)          0
________________________________________________________________________________
input_1 (InputLayer)            (None, 50)           0
________________________________________________________________________________
merge_1 (Merge)                 (None, 562)          0           input_2[0][0]
                                                                 input_1[0][0]
________________________________________________________________________________
reshape_1 (Reshape)             (None, 1, 562)       0           merge_1[0][0]
________________________________________________________________________________
gru_1 (GRU)                     (None, 128)          265344      reshape_1[0][0]
_______________________________________________________________________________
dense_1 (Dense)                 (None, 50)           6450        gru_1[0][0]
================================================================================
Total params: 271,794
Trainable params: 271,794
Non-trainable params: 0

---

Answer 1

输入必须是 numpy 数组，形状为 (any, 512)

查看您用于训练的X_train 数据的形状，它必须遵循相同的规则。

如果这会产生正确的形状，您可以：

input_data = np.array([features,embedding_matrix[enc_map[cur]]])

但如果此数据有任何问题，并且不符合要求的(any,512)，模型将无法使用它。

Answer 2

您需要将input_data 数组重塑为(512,1) 并转置它。

input_data = input_data.reshape(512,1).T