def identity_mapping(self, shape, normalize=True):
grid = np.mgrid[tuple(map(slice, shape))].astype('float32')
if normalize:
grid = grid / (np.array(shape) - 1).reshape((-1,) + (1,) * len(shape))
grid = 2 * grid - 1
return to_var(grid, is_on_cuda(self)).float()
def z_to_curve(self, z, input):
self.model_core.eval()
with torch.no_grad():
input_shape = input.shape
batch_size = input_shape[0]
z = to_var(z, self.model_core)
x = self.autoencoder.decoder_lin(z)
x = x.reshape(batch_size, 128, 32)
x = self.autoencoder.decoder_conv(x)
reproduced_curve = nn.functional.interpolate(x, input_shape[2:])
return to_np(reproduced_curve)
def do_inf_step(self, batch_of_images):
"""
Returns the prediction for the given ``inputs``.
Notes
-----
Note that both input and output are **not** of type `torch.Tensor` - the conversion
to torch.Tensor is made inside this function.
"""
self.model_core.eval()
with torch.no_grad():
batch_of_images = to_var(batch_of_images, self.model_core)
u_out = self.u_net(batch_of_images)
return to_np(self.logits2pred(u_out))
def get_trio(self, batch_of_images):
"""
Returns the prediction for the given ``inputs``.
Notes
-----
Note that both input and output are **not** of type `torch.Tensor` - the conversion
to torch.Tensor is made inside this function.
"""
self.model_core.eval()
with torch.no_grad():
batch_of_images = to_var(batch_of_images, self.model_core)
u_out = self.u_net(batch_of_images)
u_curve = self.to_curve(u_out)
z, reconstructed = self.autoencoder(u_curve)
return to_np(
self.logits2pred(u_out)), to_np(z), to_np(reconstructed)