在 CNN 中重塑图像时出错Googel Colab

如何解决在 CNN 中重塑图像时出错Googel Colab

我有一个数字识别的 CNN 项目。我正在 colab 中尝试它。我有一个 784 像素的一维向量，在将它传递给 CNN 之前，我必须将其重塑为 (28x28x1)。但我无法重塑它。我有一个错误。这是我的代码-

 x_train = x_train.reshape(-1,28,1)
    x_test = x_test.reshape(-1,1)
    test_df=test_df.reshape(-1,1)

我得到了错误，它是 -

AttributeError                            Traceback (most recent call last)
<ipython-input-31-fc5920daac40> in <module>()
      9 # reshape(examples,height,width,channels)
     10 x_train = x_train.reshape(-1,1)
---> 11 x_test = x_test.reshape(-1,1)
     12 test_df=test_df.reshape(-1,1)

/usr/local/lib/python3.6/dist-packages/pandas/core/generic.py in __getattr__(self,name)
   5139             if self._info_axis._can_hold_identifiers_and_holds_name(name):
   5140                 return self[name]
-> 5141             return object.__getattribute__(self,name)
   5142 
   5143     def __setattr__(self,name: str,value) -> None:

AttributeError: 'DataFrame' object has no attribute 'reshape'

我阅读了 this question 并且当我使用此代码时-

x_train = x_train.values.reshape(-1,1)
x_test = x_test.values.reshape(-1,1)
test_df=test_df.values.reshape(-1,1)

我也有错误，它是 -

AttributeError                            Traceback (most recent call last)
<ipython-input-32-93a2a0b4627a> in <module>()
      8 ##first param in reshape is number of examples. We can pass -1 here as we want numpy to figure that out by itself ###################
      9 # reshape(examples,channels)
---> 10 x_train = x_train.values.reshape(-1,1)
     11 x_test = x_test.values.reshape(-1,1)
     12 test_df=test_df.values.reshape(-1,1)

AttributeError: 'numpy.ndarray' object has no attribute 'values'

有时它会出错，有时它会运行。我不知道问题出在哪里，我该怎么办？

我的数据集取自 kaggle，数据集是 here。