paddlets.models.representation.dl.ts2vec
- class TS2Vec(segment_size: int, sampling_stride: int = 1, optimizer_fn: ~typing.Callable[[...], ~paddle.optimizer.optimizer.Optimizer] = <class 'paddle.optimizer.adamw.AdamW'>, optimizer_params: ~typing.Dict[str, ~typing.Any] = {'learning_rate': 0.001}, callbacks: ~typing.List[~paddlets.models.common.callbacks.callbacks.Callback] = [], batch_size: int = 128, max_epochs: int = 10, verbose: int = 1, seed: ~typing.Union[None, int] = None, repr_dims: int = 320, hidden_dims: int = 64, num_layers: int = 10, temporal_unit: int = 0)[source]
Bases:
ReprBaseModelTS2Vec[1] is a time series representation model introduced in 2021, It is a universal framework for learning representations of time series in an arbitrary semantic level. TS2Vec performs contrastive learning in a hierarchical way over augmented context views, which enables a robust contextual representation for each timestamp.
[1] Yue Z, et al. “TS2Vec: Towards universal representation of time series”, https://arxiv.org/abs/2106.10466
- Parameters
segment_size (int) – The size of time series segment.
sampling_stride (int) – Sampling intervals between two adjacent samples.
optimizer_fn (Callable[..., Optimizer]) – Optimizer algorithm.
optimizer_params (Dict[str, Any]) – Optimizer parameters.
callbacks (List[Callback]) – Customized callback functions.
batch_size (int) – Number of samples per batch.
max_epochs (int) – Max epochs during training.
verbose (int) – Verbosity mode.
seed (int|None) – Global random seed.
repr_dims (int) – The dimension of representation.
hidden_dims (int) – The number of channels in the hidden layer.
num_layers (int) – The number of ConvLayer to be stacked.
temporal_unit (int) – The minimum unit to perform temporal contrast.
- _segment_size
The size of time series segment.
- Type
int
- _sampling_stride
Sampling intervals between two adjacent samples.
- Type
int
- _optimizer_fn
Optimizer algorithm.
- Type
Callable[…, Optimizer]
- _optimizer_params
Optimizer parameters.
- Type
Dict[str, Any]
- _batch_size
Number of samples per batch.
- Type
int
- _max_epochs
Max epochs during training.
- Type
int
- _verbose
Verbosity mode.
- Type
int
- _seed
Global random seed.
- Type
int|None
- _repr_dims
The dimension of representation.
- Type
int
The number of channels in the hidden layer.
- Type
int
- _num_layers
The number of ConvLayer to be stacked.
- Type
int
- _temporal_unit
The minimum unit to perform temporal contrast.
- Type
int