2017-10-19 58 views
1

我写一个神经元用于确定手写数字错误时检查:预计dense_3_input有2个维度,但得到阵列形状(28,28,1)

import numpy as np 
from keras.utils import np_utils 
from keras.models import model_from_json 
from keras.preprocessing import image 
import matplotlib.pyplot as plt 

json_file = open("mnist_model.json", "r") 
loaded_model_json = json_file.read() 
json_file.close() 
loaded_model = model_from_json(loaded_model_json) 
loaded_model.load_weights("mnist_model.h5") 


loaded_model.compile(loss= "categorical_crossentropy", optimizer="adam", metrics=["accuracy"]) 


img_path ="5.png" 
img = image.load_img(img_path, target_size=(28,28), grayscale=True) 
plt.imshow(img, cmap='gray') 
plt.show 

x =image.img_to_array(img) 
x = 255 - x 
x/= 255 
np.expand_dims(x, axis=0) 
prediction = loaded_model.predict(x) 
prediction = np_utils.categorical_pobabs_to_classes(prediction) 
print(prediction) 

我所做的只是教她使用它,但随后的问题得到了出来: 1.结果是一个曲线图,并在线路'img = image.load_img错误ValueError: Error when checking : expected dense_3_input to have 2 dimensions, but got array with shape (28, 28, 1)(img_path,target_size =(28,28),灰度= TRUE)'

+0

在哪条线路会出现这种错误发生的呢? –

+0

Line'img = image.load_img(img_path,target_size =(28,28),grayscale = True)' – StarLord

+0

您可以提供图像文件吗? –

回答

0

我认为你的错在这一行

np.expand_dims(x, axis=0) 

它应该是:

x = np.expand_dims(x, axis=0) 
相关问题