为什么超出范围？

Question

有人可以告诉我为什么会收到此错误？

output_shape = tf.pack([batch_size, 24, 24, 5])

result = tf.nn.deconv2d(..., filter, output_shape=output_shape,
                        strides=[1, 2, 2, 1], padding='SAME')

这是我的代码：

result[i][j+1]=X[i][j]
IndexError: list assignment index out of range

Answer 1

您无法在result处为len(X[0])+1编制索引，因为其尺寸为len(X) len(X[0])。此外，您的matrixTranpose函数似乎没有采用X的转置。大概你的意思是：

def  matrixTranspose(X):
    result=[[0 for k in range (len(X))] for l in range (len(X[0]))]
    for i in range(len(X)):
        for  j in range (len(X[0])):
            result[j][i]=X[i][j]
    return result