csdn_black 2018-04-24 23:01 采纳率: 50%
浏览 9968
已结题

kears 运行一个最简单的demo报错

按照书上的代码如下:

 import numpy as np
import pandas as pd
from keras.utils import np_utils
np.random.seed(10)
from keras.models import Sequential
from keras.layers import Dense
from keras.datasets import mnist

#数据准备-------------------
(x_train_image, y_train_label), \
(x_test_image, y_test_label) = mnist.load_data()

x_Train =x_train_image.reshape(60000, 784).astype('float32')
x_Test = x_test_image.reshape(10000, 784).astype('float32')

#标准化
x_Train_normalize = x_Train/ 255
x_Test_normalize = x_Test/ 255

y_TrainOne_Hot = np_utils.to_categorical(y_train_label)
y_TestOne_Hot = np_utils.to_categorical(y_test_label)
print(x_Train_normalize)
print('sss')
print(y_TrainOne_Hot)

#建立模型-------------------

model = Sequential()
model.add(Dense(units=256,
                input_dim=784,
                kernel_initializer='normal',
                activation='relu'))

model.add(Dense(units=10,
                kernel_initializer='normal',
                activation='softmax'))

model.compile(loss='categorical_crossentropy',
              optimizer='adam', metrics=['accuracy'])

train_history =model.fit(x=x_Train_normalize,
                         y=y_TrainOne_Hot,validation_split=0.2,
                         epochs=10, batch_size=200,verbose=2)

报错:softmax() got an unexpected keyword argument 'axis'

详细的报错:
Traceback (most recent call last):
File "C:/Users/51530/PycharmProjects/ML/keras/K-MNIST/train.py", line 36, in
activation='softmax'))
File "E:\anaconda\lib\site-packages\keras\models.py", line 522, in add
output_tensor = layer(self.outputs[0])
File "E:\anaconda\lib\site-packages\keras\engine\topology.py", line 619, in call
output = self.call(inputs, **kwargs)
File "E:\anaconda\lib\site-packages\keras\layers\core.py", line 881, in call
output = self.activation(output)
File "E:\anaconda\lib\site-packages\keras\activations.py", line 29, in softmax
return K.softmax(x)
File "E:\anaconda\lib\site-packages\keras\backend\tensorflow_backend.py", line 2963, in softmax
return tf.nn.softmax(x, axis=axis)
TypeError: softmax() got an unexpected keyword argument 'axis'

有知道为什么会报错吗?先谢了

展开全部

  • 写回答

4条回答 默认 最新

  • csdn_black 2018-04-24 23:44
    关注

    跪求大神帮助啊,感激不尽!!!!

    评论
  • _1_1_7_ 2018-04-25 00:32
    关注

    axis是关键字,搜索一下代码,哪里用到了 。
    借鉴 : https://blog.csdn.net/s_sunnyy/article/details/70469600

    评论
  • csdn_black 2018-04-25 00:53
    关注

    问题自己解决了,没想到是Keras与tensorflow版本不相符,神坑啊,搞了半天

    评论
  • Papers6 2018-10-18 04:13
    关注

    tensorflow版本不同导致的,只需要修改最后一行就行了: tf.nn.softmax(x, axis=axis) -> tf.nn.softmax(x, dim=axis)

    评论
编辑
预览

报告相同问题?

手机看
程序员都在用的中文IT技术交流社区

程序员都在用的中文IT技术交流社区

专业的中文 IT 技术社区,与千万技术人共成长

专业的中文 IT 技术社区,与千万技术人共成长

关注【CSDN】视频号,行业资讯、技术分享精彩不断,直播好礼送不停!

关注【CSDN】视频号,行业资讯、技术分享精彩不断,直播好礼送不停!

客服 返回
顶部