python - Keras - 如何根据一个实例进行预测？

Question

我已经创建了一个模型(h5 和 tfjs/model.json)来预测定价室。问题是我不知道如何根据一个实例进行预测？通常，根据所有测试数据进行预测。已经尝试过这个，但不起作用......

model.predict(np.array([0.347669, 0.048266, 0.515875, -0.166667, 0.000000, 0.378772]))

错误信息

ValueError: Error when checking input: expected dense_1_input to have shape (6,) but got array with shape (1,)

据我所知，实例/值应该标准化(我使用线性回归)并转换为 numpy 数组。不知道如何继续。这里有一些线索，但我对此一无所知。 expected dense to have shape but got array with shape

模型摘要

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_1 (Dense)              (None, 200)               1400      
_________________________________________________________________
dense_2 (Dense)              (None, 100)               20100     
_________________________________________________________________
dense_3 (Dense)              (None, 50)                5050      
_________________________________________________________________
dense_4 (Dense)              (None, 25)                1275      
_________________________________________________________________
dense_5 (Dense)              (None, 1)                 26        
=================================================================
Total params: 27,851
Trainable params: 27,851
Non-trainable params: 0
_________________________________________________________________
None

Answer 1

这具有预期的形状

import numpy as np
a=np.array([[0.347669, 0.048266, 0.515875, -0.166667, 0.000000, 0.378772]])
print(a.shape) #(6,)

b=model.predict(a)
print(b)