Open feiyunzhang opened 4 years ago
hi, https://github.com/openai/glow/blob/eaff2177693a5d84a1cf8ae19e8e0441715b82f8/model.py#L576-L584 Why use cross h to get mean and logs? Is there any difference to get mean and logs from its contiguous splits of h? I guess maybe you want to "cross split" the featuremap to get the z1, z2 in the previous lines: https://github.com/openai/glow/blob/eaff2177693a5d84a1cf8ae19e8e0441715b82f8/model.py#L545-L555 As feature feed to split2d are concated from two parts of formerly revnet2d layer, the first half and second half of which are not that equal, doing a "cross split" to get z1, z2 may be a better choice.
hi, https://github.com/openai/glow/blob/eaff2177693a5d84a1cf8ae19e8e0441715b82f8/model.py#L576-L584 Why use cross h to get mean and logs? Is there any difference to get mean and logs from its contiguous splits of h? I guess maybe you want to "cross split" the featuremap to get the z1, z2 in the previous lines: https://github.com/openai/glow/blob/eaff2177693a5d84a1cf8ae19e8e0441715b82f8/model.py#L545-L555 As feature feed to split2d are concated from two parts of formerly revnet2d layer, the first half and second half of which are not that equal, doing a "cross split" to get z1, z2 may be a better choice.