def train_generator_step(self, configuration: Configuration, metadata: Metadata,
architecture: Architecture) -> float:
# clean previous gradients
architecture.generator_optimizer.zero_grad()
# conditional
if "conditional" in architecture.arguments:
# for now uniform distribution is used but could be controlled in a different way
# also this works for both binary and categorical dependent variables
number_of_conditions = metadata.get_dependent_variable().get_size()
condition = to_gpu_if_available(FloatTensor(configuration.batch_size).uniform_(0, number_of_conditions))
# non-conditional
else:
condition = None
# generate a full batch of fake features
fake_features = self.sample_fake(architecture, configuration.batch_size, condition=condition)
# calculate loss
loss = architecture.generator_loss(architecture, fake_features, condition=condition)
# calculate gradients
loss.backward()
# update the generator weights
architecture.generator_optimizer.step()
# return the loss
return to_cpu_if_was_in_gpu(loss).item()
def train_generator_step(configuration: Configuration, metadata: Metadata,
architecture: Architecture,
batch: Batch) -> float:
# clean previous gradients
architecture.generator_optimizer.zero_grad()
# generate a batch of fake features with the same size as the real feature batch
generated = architecture.generator(batch["features"],
missing_mask=batch["missing_mask"])
# replace the missing features by the generated
imputed = compose_with_mask(
mask=batch["missing_mask"],
differentiable=True, # now there are no NaNs and this should be used
where_one=generated,
where_zero=batch["raw_features"])
# generate hint
hint = generate_hint(batch["missing_mask"],
configuration.hint_probability, metadata)
# calculate loss
loss = architecture.generator_loss(architecture=architecture,
features=batch["raw_features"],
generated=generated,
imputed=imputed,
hint=hint,
non_missing_mask=inverse_mask(
batch["missing_mask"]))
# calculate gradients
loss.backward()
# update the generator weights
architecture.generator_optimizer.step()
# return the loss
return to_cpu_if_was_in_gpu(loss).item()