spacetimeformer.spacetimeformer_model package

• spacetimeformer.spacetimeformer_model.nn package
• spacetimeformer.spacetimeformer_model.utils package

class spacetimeformer.spacetimeformer_model.spacetimeformer_model.Spacetimeformer_Forecaster(d_y: int = 1, d_x: int = 4, start_token_len: int = 64, attn_factor: int = 5, d_model: int = 512, n_heads: int = 8, e_layers: int = 2, d_layers: int = 2, d_ff: int = 2048, dropout_emb: float = 0.05, dropout_token: float = 0.05, dropout_qkv: float = 0.05, dropout_ff: float = 0.05, dropout_attn_out: float = 0.05, global_self_attn: str = 'performer', local_self_attn: str = 'none', global_cross_attn: str = 'performer', local_cross_attn: str = 'none', performer_kernel: str = 'relu', embed_method: str = 'spatio-temporal', performer_relu: bool = True, performer_redraw_interval: int = 1000, activation: str = 'gelu', post_norm: bool = False, norm: str = 'layer', init_lr: float = 1e-10, base_lr: float = 0.0003, warmup_steps: float = 0, decay_factor: float = 0.25, initial_downsample_convs: int = 0, intermediate_downsample_convs: int = 0, l2_coeff: float = 0, loss: str = 'nll', linear_window: int = 0, class_loss_imp: float = 0.1, time_emb_dim: int = 6, null_value: Optional[float] = None, verbose=True)

Bases: spacetimeformer.forecaster.Forecaster

classmethod add_cli(parser)

classification_loss(logits: torch.Tensor, labels: torch.Tensor) → Tuple[torch.Tensor]

compute_loss(batch, time_mask=None, forward_kwargs={})

configure_optimizers()

Choose what optimizers and learning-rate schedulers to use in your optimization. Normally you’d need one. But in the case of GANs or similar you might have multiple.

Returns

Any of these 6 options.

• Single optimizer.

• List or Tuple of optimizers.

• Two lists - The first list has multiple optimizers, and the second has multiple LR schedulers (or multiple lr_scheduler_config).

• Dictionary, with an "optimizer" key, and (optionally) a "lr_scheduler" key whose value is a single LR scheduler or lr_scheduler_config.

• Tuple of dictionaries as described above, with an optional "frequency" key.

• None - Fit will run without any optimizer.

The lr_scheduler_config is a dictionary which contains the scheduler and its associated configuration. The default configuration is shown below.

lr_scheduler_config = {
    # REQUIRED: The scheduler instance
    "scheduler": lr_scheduler,
    # The unit of the scheduler's step size, could also be 'step'.
    # 'epoch' updates the scheduler on epoch end whereas 'step'
    # updates it after a optimizer update.
    "interval": "epoch",
    # How many epochs/steps should pass between calls to
    # `scheduler.step()`. 1 corresponds to updating the learning
    # rate after every epoch/step.
    "frequency": 1,
    # Metric to to monitor for schedulers like `ReduceLROnPlateau`
    "monitor": "val_loss",
    # If set to `True`, will enforce that the value specified 'monitor'
    # is available when the scheduler is updated, thus stopping
    # training if not found. If set to `False`, it will only produce a warning
    "strict": True,
    # If using the `LearningRateMonitor` callback to monitor the
    # learning rate progress, this keyword can be used to specify
    # a custom logged name
    "name": None,
}

When there are schedulers in which the .step() method is conditioned on a value, such as the torch.optim.lr_scheduler.ReduceLROnPlateau scheduler, Lightning requires that the lr_scheduler_config contains the keyword "monitor" set to the metric name that the scheduler should be conditioned on.

Metrics can be made available to monitor by simply logging it using self.log('metric_to_track', metric_val) in your LightningModule.

Note

The frequency value specified in a dict along with the optimizer key is an int corresponding to the number of sequential batches optimized with the specific optimizer. It should be given to none or to all of the optimizers. There is a difference between passing multiple optimizers in a list, and passing multiple optimizers in dictionaries with a frequency of 1:

• In the former case, all optimizers will operate on the given batch in each optimization step.

• In the latter, only one optimizer will operate on the given batch at every step.

This is different from the frequency value specified in the lr_scheduler_config mentioned above.

def configure_optimizers(self):
    optimizer_one = torch.optim.SGD(self.model.parameters(), lr=0.01)
    optimizer_two = torch.optim.SGD(self.model.parameters(), lr=0.01)
    return [
        {"optimizer": optimizer_one, "frequency": 5},
        {"optimizer": optimizer_two, "frequency": 10},
    ]

In this example, the first optimizer will be used for the first 5 steps, the second optimizer for the next 10 steps and that cycle will continue. If an LR scheduler is specified for an optimizer using the lr_scheduler key in the above dict, the scheduler will only be updated when its optimizer is being used.

Examples:

# most cases. no learning rate scheduler
def configure_optimizers(self):
    return Adam(self.parameters(), lr=1e-3)

# multiple optimizer case (e.g.: GAN)
def configure_optimizers(self):
    gen_opt = Adam(self.model_gen.parameters(), lr=0.01)
    dis_opt = Adam(self.model_dis.parameters(), lr=0.02)
    return gen_opt, dis_opt

# example with learning rate schedulers
def configure_optimizers(self):
    gen_opt = Adam(self.model_gen.parameters(), lr=0.01)
    dis_opt = Adam(self.model_dis.parameters(), lr=0.02)
    dis_sch = CosineAnnealing(dis_opt, T_max=10)
    return [gen_opt, dis_opt], [dis_sch]

# example with step-based learning rate schedulers
# each optimizer has its own scheduler
def configure_optimizers(self):
    gen_opt = Adam(self.model_gen.parameters(), lr=0.01)
    dis_opt = Adam(self.model_dis.parameters(), lr=0.02)
    gen_sch = {
        'scheduler': ExponentialLR(gen_opt, 0.99),
        'interval': 'step'  # called after each training step
    }
    dis_sch = CosineAnnealing(dis_opt, T_max=10) # called every epoch
    return [gen_opt, dis_opt], [gen_sch, dis_sch]

# example with optimizer frequencies
# see training procedure in `Improved Training of Wasserstein GANs`, Algorithm 1
# https://arxiv.org/abs/1704.00028
def configure_optimizers(self):
    gen_opt = Adam(self.model_gen.parameters(), lr=0.01)
    dis_opt = Adam(self.model_dis.parameters(), lr=0.02)
    n_critic = 5
    return (
        {'optimizer': dis_opt, 'frequency': n_critic},
        {'optimizer': gen_opt, 'frequency': 1}
    )

Note

Some things to know:

• Lightning calls .backward() and .step() on each optimizer and learning rate scheduler as needed.

• If you use 16-bit precision (precision=16), Lightning will automatically handle the optimizers.

• If you use multiple optimizers, training_step() will have an additional optimizer_idx parameter.

• If you use torch.optim.LBFGS, Lightning handles the closure function automatically for you.

• If you use multiple optimizers, gradients will be calculated only for the parameters of current optimizer at each training step.

• If you need to control how often those optimizers step or override the default .step() schedule, override the optimizer_step() hook.

forward_model_pass(x_c, y_c, x_t, y_t, output_attn=False)

step(batch: Tuple[torch.Tensor], train: bool)

allow_zero_length_dataloader_with_multiple_devices: bool

property eval_step_forward_kwargs

precision: int

prepare_data_per_node: bool

property train_step_forward_kwargs

training: bool

use_amp: bool