def __init__(
self,
input_names: List[str],
prediction_net: BlockType,
batch_size: int,
prediction_length: int,
freq: str,
ctx: mx.Context,
input_transform: Transformation,
lead_time: int = 0,
forecast_generator: ForecastGenerator = SampleForecastGenerator(),
output_transform: Optional[OutputTransform] = None,
dtype: DType = np.float32,
) -> None:
super().__init__(
freq=freq,
lead_time=lead_time,
prediction_length=prediction_length,
)
self.input_names = input_names
self.prediction_net = prediction_net
self.batch_size = batch_size
self.input_transform = input_transform
self.forecast_generator = forecast_generator
self.output_transform = output_transform
self.ctx = ctx
self.dtype = dtype
def __init__(
self,
prediction_net: BlockType,
batch_size: int,
prediction_length: int,
freq: str,
ctx: mx.Context,
input_transform: Transformation,
lead_time: int = 0,
forecast_generator: ForecastGenerator = SampleForecastGenerator(),
output_transform: Optional[Callable[[DataEntry, np.ndarray],
np.ndarray]] = None,
dtype: DType = np.float32,
) -> None:
super().__init__(
input_names=get_hybrid_forward_input_names(prediction_net),
prediction_net=prediction_net,
batch_size=batch_size,
prediction_length=prediction_length,
freq=freq,
ctx=ctx,
input_transform=input_transform,
lead_time=lead_time,
forecast_generator=forecast_generator,
output_transform=output_transform,
dtype=dtype,
)
def __init__(
self,
prediction_net: BlockType,
batch_size: int,
prediction_length: int,
freq: str,
ctx: mx.Context,
input_transform: Transformation,
input_names: Optional[List[str]] = None,
lead_time: int = 0,
forecast_generator: ForecastGenerator = SampleForecastGenerator(),
output_transform: Optional[
Callable[[DataEntry, np.ndarray],
np.ndarray]] = DeepRenewalProcessSampleOutputTransform(),
dtype: Type = np.float32,
) -> None:
super().__init__(
prediction_net=prediction_net,
batch_size=batch_size,
prediction_length=prediction_length,
freq=freq,
ctx=ctx,
input_transform=input_transform,
lead_time=lead_time,
forecast_generator=forecast_generator,
output_transform=output_transform,
dtype=dtype,
)
if input_names is not None:
self.input_names = input_names
def __init__(
self,
input_names: List[str],
prediction_net: nn.Module,
batch_size: int,
prediction_length: int,
freq: str,
device: torch.device,
input_transform: Transformation,
forecast_generator: SampleForecastGenerator = SampleForecastGenerator(),
output_transform: Optional[OutputTransform] = None,
) -> None:
super().__init__(prediction_length, freq)
self.input_names = input_names
self.prediction_net = prediction_net
self.batch_size = batch_size
self.input_transform = input_transform
self.forecast_generator = forecast_generator
self.output_transform = output_transform
self.device = device
def __init__(
self,
input_names: List[str],
prediction_net: nn.Module,
batch_size: int,
prediction_length: int,
freq: str,
input_transform: Transformation,
forecast_generator: ForecastGenerator = SampleForecastGenerator(),
output_transform: Optional[OutputTransform] = None,
lead_time: int = 0,
device: Optional[torch.device] = torch.device("cpu"),
) -> None:
super().__init__(prediction_length, freq=freq, lead_time=lead_time)
self.input_names = input_names
self.prediction_net = prediction_net.to(device)
self.batch_size = batch_size
self.input_transform = input_transform
self.forecast_generator = forecast_generator
self.output_transform = output_transform
self.device = device