Closed brando90 closed 2 years ago
I was wondering why call contiguous after flattening?
self_tensor = self_tensor.flatten(start_dim=2, end_dim=-1).contiguous() other_tensor = other_tensor.flatten(start_dim=2, end_dim=-1).contiguous()
but why not after downsampling:
downsample_method = downsample_method or 'avg_pool' self_tensor = self._downsample_4d(self_tensor, size, downsample_method) other_tensor = self._downsample_4d(other_tensor, size, downsample_method)
and thus wondering if I should always call continuous.
No specific reason.
I was wondering why call contiguous after flattening?
but why not after downsampling:
and thus wondering if I should always call continuous.