TypeError: Value passed to parameter 'paddings' has DataType float32 not in list of allowed values: int32, int64

[chenguanqi]

Hi, when I run the code in tf=1.3.0, I met the following error: File "NLDF.py", line 126, in ContrastLayer return tf.subtract(input, tf.nn.avgpool(tf.pad(input, [[0, 0], [h_s, h_s], [h_s, h_s], [0, 0]], 'SYMMETRIC'), TypeError: Value passed to parameter 'paddings' has DataType float32 not in list of allowed values: int32, int64. How can I fix it?

[chenguanqi]

I modified the function ContrastLayer(self, input, k_s=3) as follow: def ContrastLayer(self, input, k_s=3):

h_s = k_s / 2

    # return tf.subtract(input_, tf.nn.avg_pool(tf.pad(input_, [[0, 0], [h_s, h_s], [h_s, h_s], [0, 0]], 'SYMMETRIC') ,ksize=[1, k_s, k_s, 1], strides=[1, 1, 1, 1], padding='VALID'))
    h_s = k_s // 2
    if k_s % 2 == 0:
        return tf.subtract(input_, tf.nn.avg_pool(tf.pad(input_, [[0, 0], [h_s, h_s], [h_s, h_s], [0, 0]], 'SYMMETRIC'), ksize=[1, k_s, k_s, 1], strides=[1, 1, 1, 1], padding='VALID'))
    else:
        return tf.subtract(input_, tf.nn.avg_pool(tf.pad(input_, [[0, 0], [h_s, h_s+1], [h_s, h_s+1], [0, 0]], 'SYMMETRIC'),ksize=[1, k_s, k_s, 1], strides=[1, 1, 1, 1], padding='VALID'))

Is it right?

[zhanpx]

我也遇到这个问题，我直接改成 h_s = int(k_s / 2) 了

[chenguanqi]

我也遇到这个问题，我直接改成 h_s = int(k_s / 2) 了

好的，谢谢