MCPcopy Create free account
hub / github.com/BorealisAI/scaleformer / sparseKernelFT1d

Class sparseKernelFT1d

layers/MultiWaveletCorrelation.py:271–302  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

269
270
271class sparseKernelFT1d(nn.Module):
272 def __init__(self,
273 k, alpha, c=1,
274 nl=1,
275 initializer=None,
276 **kwargs):
277 super(sparseKernelFT1d, self).__init__()
278
279 self.modes1 = alpha
280 self.scale = (1 / (c * k * c * k))
281 self.weights1 = nn.Parameter(self.scale * torch.rand(c * k, c * k, self.modes1, dtype=torch.cfloat))
282 self.weights1.requires_grad = True
283 self.k = k
284
285 def compl_mul1d(self, x, weights):
286 # (batch, in_channel, x ), (in_channel, out_channel, x) -> (batch, out_channel, x)
287 return torch.einsum("bix,iox->box", x, weights)
288
289 def forward(self, x):
290 B, N, c, k = x.shape # (B, N, c, k)
291
292 x = x.view(B, N, -1)
293 x = x.permute(0, 2, 1)
294 x_fft = torch.fft.rfft(x)
295 # Multiply relevant Fourier modes
296 l = min(self.modes1, N // 2 + 1)
297 # l = N//2+1
298 out_ft = torch.zeros(B, c * k, N // 2 + 1, device=x.device, dtype=torch.cfloat)
299 out_ft[:, :, :l] = self.compl_mul1d(x_fft[:, :, :l], self.weights1[:, :, :l])
300 x = torch.fft.irfft(out_ft, n=N)
301 x = x.permute(0, 2, 1).view(B, N, c, k)
302 return x
303
304
305# ##

Callers 1

__init__Method · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected