def _coupling_transform_forward(self, inputs, transform_params):
scale, shift = self._scale_and_shift(transform_params)
log_scale = torch.log(scale)
outputs = inputs * scale + shift
logabsdet = torchutils.sum_except_batch(log_scale, num_batch_dims=1)
return outputs, logabsdet
def _coupling_transform_inverse(self, inputs, transform_params):
scale, shift = self._scale_and_shift(transform_params)
log_scale = torch.log(scale)
outputs = (inputs - shift) / scale
logabsdet = -torchutils.sum_except_batch(log_scale, num_batch_dims=1)
return outputs, logabsdet
def forward(self, inputs, context=None):
outputs = (1 / np.pi) * torch.atan(inputs) + 0.5
logabsdet = torchutils.sum_except_batch(-np.log(np.pi) -
torch.log(1 + inputs**2))
return outputs, logabsdet
def forward(self, inputs, context=None):
outputs = torch.tanh(inputs)
logabsdet = torch.log(1 - outputs**2)
logabsdet = torchutils.sum_except_batch(logabsdet, num_batch_dims=1)
return outputs, logabsdet
def forward(self, inputs, context=None):
outputs = F.leaky_relu(inputs, negative_slope=self.negative_slope)
mask = (inputs < 0).type(torch.Tensor)
logabsdet = self.log_negative_slope * mask
logabsdet = torchutils.sum_except_batch(logabsdet, num_batch_dims=1)
return outputs, logabsdet