This is a variant of torch.quantile() that “ignores” NaN values, computing the quantiles q as if NaN values in input did not exist. If all values in a reduced row are NaN then the quantiles for that reduction will be NaN. See the documentation for torch.quantile().
>>> t = torch.tensor([float('nan'), 1, 2])
>>> t.quantile(0.5)
tensor(nan)
>>> t.nanquantile(0.5)
tensor(1.5000)
>>> t = torch.tensor([[float('nan'), float('nan')], [1, 2]])
>>> t
tensor([[nan, nan],
[1., 2.]])
>>> t.nanquantile(0.5, dim=0)
tensor([1., 2.])
>>> t.nanquantile(0.5, dim=1)
tensor([ nan, 1.5000])
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4