Question

我想建立一个只有一层的简单神经网络。我认为代码本身没有问题，但是存储了训练数据和其他内容的数组。我得到了这个奇怪的ValueError，我不知道为什么。这是我的代码：

     import numpy as np 
     def sigmoid(x):
         return 1 / (1 + np.exp(-x))
     training_inputs = np.array([[0,0,1],
                                 [1,1,1],
                                 [1,0,1],
                                 [0,1,1]])
     training_output = np.array([[0,
                                  1,
                                  1,
                                  0]])
    synaptic_weights = 2 * np.random.random((3,1)) - 1
    for iterantion in range(2000):
       input_layer = training_inputs
       outputs = sigmoid(np.dot(input_layer, synaptic_weights))
       synaptic_weights += np.dot(input_layer,((training_output - outputs) 
       * (outputs * (1 - outputs))))
       print(outputs)
print("Session closed")

我收到此错误：

(base) c:\Users\juliu\AppData\Local\Programs\Python\Python37-32\Lib\curses>cd c:\Users\juliu\AppData\Local\Programs\Python\Python37-32\Lib\curses && cmd /C "set "PYTHONIOENCODING=UTF-8" && set "PYTHONUNBUFFERED=1" && C:\Users\juliu\Anaconda3\python.exe c:\Users\juliu\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd_launcher.py --default --nodebug --client --host localhost --port 50932 c:\Users\juliu\AppData\Local\Programs\Python\Python37-32\Lib\curses\AI.py "
Traceback (most recent call last):
  File "c:\Users\juliu\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd_launcher.py", line 45, in <module>
    main(ptvsdArgs)
  File "c:\Users\juliu\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd\ptvsd\__main__.py", line 265, in main
    wait=args.wait)
  File "c:\Users\juliu\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd\ptvsd\__main__.py", line 256, in handle_args
    run_main(addr, name, kind, *extra, **kwargs)
  File "c:\Users\juliu\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd\ptvsd\_local.py", line 52, in run_main
    runner(addr, name, kind == 'module', *extra, **kwargs)
  File "c:\Users\juliu\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd\ptvsd\runner.py", line 32, in run
    set_trace=False)
  File "c:\Users\juliu\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd\ptvsd\_vendored\pydevd\pydevd.py", line 1283, in run
    return self._exec(is_module, entry_point_fn, module_name, file, globals, locals)
  File "c:\Users\juliu\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd\ptvsd\_vendored\pydevd\pydevd.py", line 1290, in _exec
    pydev_imports.execfile(file, globals, locals)  # execute the script
  File "c:\Users\juliu\.vscode\extensions\ms-python.python-2018.11.0\pythonFiles\experimental\ptvsd\ptvsd\_vendored\pydevd\_pydev_imps\_pydev_execfile.py", line 25, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "c:\Users\juliu\AppData\Local\Programs\Python\Python37-32\Lib\curses\AI.py", line 25, in <module>
    synaptic_weights += np.dot(input_layer,((training_output - outputs) * (outputs * (1 - outputs))))
ValueError: shapes (4,3) and (4,4) not aligned: 3 (dim 1) != 4 (dim 0)

如果有人对我可以进行更改有任何想法，请写下来！

Answer 1

您的training_inputs和training_output矩阵维不适合相乘。 training_inputs应该换位。

尝试构建简单的神经网络时出现ValueError

1 个答案: