change resampler attention to scale_dot_product_attention

[Benkovichnikita]

I noticed two issues:

1. PerceiverAttention consumes a huge amount of memory while calculating an attention map
2. There are two operations of math.srqt when scale calculating: scale = 1 / math.sqrt(math.sqrt(self.dim_head))

Both of them can be fixed using more effective implementation: F.scaled_dot_product_attention(q, k, v).

PS
If you need scale with two sqrt, it can be provided as an additional argument to F.scaled_dot_product_attention.