Args: kernel_size (int or tuple): kernel size for two direction of each axis. For example, (2, 3), the first 2 means will add 2 at the beginning and also 2 at the end for its axis.and if a int is accepted, the kernel size will be i
(self, kernel_size, stride=None, padding=0, pad_mode="NOTSET")
| 1033 | class AvgPool2d(Pooling2d): |
| 1034 | |
| 1035 | def __init__(self, kernel_size, stride=None, padding=0, pad_mode="NOTSET"): |
| 1036 | """ |
| 1037 | Args: |
| 1038 | kernel_size (int or tuple): kernel size for two direction of each |
| 1039 | axis. For example, (2, 3), the first 2 means will add 2 at the |
| 1040 | beginning and also 2 at the end for its axis.and if a int is |
| 1041 | accepted, the kernel size will be initiated as (int, int) |
| 1042 | stride (int or tuple): stride, the logic is the same as kernel size. |
| 1043 | padding (int): tuple, list or None, padding, the logic is the same |
| 1044 | as kernel size. However, if you set pad_mode as "SAME_UPPER" or |
| 1045 | "SAME_LOWER" mode, you can set padding as None, and the padding |
| 1046 | will be computed automatically. |
| 1047 | pad_mode (string): can be NOTSET, SAME_UPPER, or SAME_LOWER, where |
| 1048 | default value is NOTSET, which means explicit padding is used. |
| 1049 | SAME_UPPER or SAME_LOWER mean pad the input so that the output |
| 1050 | spatial size match the input. In case of odd number add the extra |
| 1051 | padding at the end for SAME_UPPER and at the beginning for SAME_LOWER. |
| 1052 | """ |
| 1053 | super(AvgPool2d, self).__init__(kernel_size, stride, padding, False, |
| 1054 | pad_mode) |
| 1055 | |
| 1056 | |
| 1057 | class MaxPool1d(Pooling2d): |