Question

我刚刚使用Windows 64位和Python 2.7安装了keras 1.1.2。

代码

import java.io.*;
import java.net.*;
import java.util.*;

public class ChatHandler extends Thread{
    Socket s;
    BufferedReader br;
    PrintWriter pw;
    String temp;
    ArrayList <ChatHandler>handlers;

    public ChatHandler(Socket s, ArrayList <ChatHandler>handlers){
        this.s = s;
        this.handlers = handlers;
    }


    public void run(){
        try{
            handlers.add(this);
            br = new BufferedReader(new InputStreamReader(s.getInputStream()));
            pw = new PrintWriter(s.getOutputStream(), true);
            temp = "";
            while((temp = br.readLine()) != null){
                for (ChatHandler ch : handlers){
                    ch.pw.println(temp); 
                }
                System.out.println(temp);
            }
        }catch(IOException ioe){
            System.out.println(ioe.getMessage());      
        }finally{
            handlers.remove(this);
        }
    }
}

返回以下错误：

model = Sequential()
model.add(Dense(25, input_dim=50, init='uniform', activation='relu'))

代码

Traceback (most recent call last):
  File "C:\Loopy\lib\site-packages\IPython\core\interactiveshell.py", line 2827, in run_code
    exec code_obj in self.user_global_ns, self.user_ns
  File "<ipython-input-3-850dd91f408b>", line 30, in <module>
    model.add(Dense(25, input_dim=50, init='uniform', activation='relu'))
TypeError: __init__() got multiple values for keyword argument 'input_dim'

返回：

model.add(Dense(15, init='uniform', activation='relu'))

Answer 1

尝试使用以下命令将keras升级到最新的1.1.2：

pip install keras --upgrade

对于特定用户：pip install --user keras --upgrade

Answer 2

您是否尝试过单独添加图层？输入，然后是密集，然后是初始化，然后是激活。
除此之外，请尝试使用kernel_initializer='random_uniform'而不是init='uniform'。

Python，keras新安装

2 个答案: