Question

X和Y的形状分别为（89362，5）和（89362，）。

x_train, x_test, y_train, y_test = train_test_split(X, Y,
                                                    test_size = 0.3, 
                                                    random_state = 1)


x_train.shape, y_train.shape = ((62553, 5), (62553,))
x_test.shape, y_test.shape = ((26809, 5), (26809,))

将向量重塑为：

torch.Size([1, 62553, 5]), torch.Size([1, 62553])
torch.Size([1, 26809, 5]), torch.Size([1, 26809])

模型定义为

n_steps = 62553
n_features = 5


model = Sequential()
model.add(Conv1D(filters=64, kernel_size=2, activation='relu', input_shape=(n_steps, n_features)))
model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())
model.add(Dense(50, activation='relu'))
model.add(Dense(62553))
model.compile(optimizer='adam', loss='mse')
model.fit(x_train, y_train, epochs=10, verbose=0)

使用x_test进行预测时，会引发值错误

yhat = model.predict(x_test, verbose=0)
print(yhat)

ValueError: Error when checking input: expected conv1d_4_input to have shape (62553, 5) but got array with shape torch.Size([26809, 5])

Answer 1

之所以会这样，是因为您在此处指定了固定大小：

model.add(Conv1D(filters=64, kernel_size=2, activation='relu', input_shape=(n_steps, n_features)))

将其他内容传递给模型后，模型仍然期望尺寸固定不变：

n_steps = 62553
n_features = 5

删除input_shape参数应解决此问题：

model.add(Conv1D(filters=64, kernel_size=2, activation='relu'))

希望对您有帮助。

Keras model.predict（）抛出ValueError

1 个答案: