trajdl.algorithms.t2vec module

class trajdl.algorithms.t2vec.DecoderWithAttention(hidden_size: int, num_layers: int, embedding_layer: BaseTokenEmbeddingLayer, dropout: float = 0.0)

Bases: Module

forward(x: LongTensor, hidden_state: Tensor, all_encoder_hidden_states: Tensor)

Parameters:

• x (torch.LongTensor, shape is (batch_size, seq_length))

• hidden_state ((num_layers, batch_size, hidden_size))

• all_encoder_hidden_states ((batch_size, seq_len, hidden_size))

• Output

• ----------

• output ((batch_size, seq_len, hidden_size))

class trajdl.algorithms.t2vec.GlobalAttention(hidden_size: int)

Bases: Module

$$a = sigma((W_1 q)H)$$ $$c = tanh(W_2 [a H, q])$$

forward(query: Tensor, context: Tensor)

Parameters:

• query ((batch_size, hidden_size))

• context ((batch_size, seq_len, hidden_size))

• Output

• ----------

• (batch_size (output)

• hidden_size)

class trajdl.algorithms.t2vec.StackingGRU(input_size: int, hidden_size: int, num_layers: int, dropout: float = 0.0)

Bases: Module

Multi-layer CRU Cell

forward(src: Tensor, hidden_state: Tensor)

Parameters:

• src ((batch_size, input_size))

• hidden_state ((num_layers, batch_size, hidden_size))

• Output

• ----------

• output ((batch_size, hidden_size))

• hidden_states ((num_layers, batch, hidden_size))

class trajdl.algorithms.t2vec.T2VEC(embedding_dim: int, hidden_size: int, tokenizer: str | AbstractTokenizer, knn_indices_path: str, knn_distances_path: str, num_layers: int = 1, bidirectional_encoder: bool = False, embedding_path: str | None = None, freeze_embedding: bool = False, dropout: float = 0.0)

Bases: BaseLightningModel

compute_loss(batch: T2VECSample)

Parameters:

batch (T2VECSample)

Returns:

• loss (torch.Tensor) – shape is (1,)

• batch_size (int)

encode(batch: T2VECSample) → Tuple[Tensor, Tensor]

forward(batch: T2VECSample) → Tensor

推理的逻辑

Parameters:

batch (T2VECSample)

Return type:

torch.Tensor, shape is (batch_size, hidden_size)

training_step(batch: T2VECSample, batch_idx: int) → Tensor

Parameters:

batch (T2VECSample)

validation_step(batch: T2VECSample, batch_idx: int) → Tensor

Operates on a single batch of data from the validation set. In this step you’d might generate examples or calculate anything of interest like accuracy.

Parameters:

• batch – The output of your data iterable, normally a DataLoader.

• batch_idx – The index of this batch.

• dataloader_idx – The index of the dataloader that produced this batch. (only if multiple dataloaders used)

Returns:

• Tensor - The loss tensor

• dict - A dictionary. Can include any keys, but must include the key 'loss'.

• None - Skip to the next batch.

# if you have one val dataloader:
def validation_step(self, batch, batch_idx): ...


# if you have multiple val dataloaders:
def validation_step(self, batch, batch_idx, dataloader_idx=0): ...

Examples:

# CASE 1: A single validation dataset
def validation_step(self, batch, batch_idx):
    x, y = batch

    # implement your own
    out = self(x)
    loss = self.loss(out, y)

    # log 6 example images
    # or generated text... or whatever
    sample_imgs = x[:6]
    grid = torchvision.utils.make_grid(sample_imgs)
    self.logger.experiment.add_image('example_images', grid, 0)

    # calculate acc
    labels_hat = torch.argmax(out, dim=1)
    val_acc = torch.sum(y == labels_hat).item() / (len(y) * 1.0)

    # log the outputs!
    self.log_dict({'val_loss': loss, 'val_acc': val_acc})

If you pass in multiple val dataloaders, validation_step() will have an additional argument. We recommend setting the default value of 0 so that you can quickly switch between single and multiple dataloaders.

# CASE 2: multiple validation dataloaders
def validation_step(self, batch, batch_idx, dataloader_idx=0):
    # dataloader_idx tells you which dataset this is.
    ...

Note

If you don’t need to validate you don’t need to implement this method.

Note

When the validation_step() is called, the model has been put in eval mode and PyTorch gradients have been disabled. At the end of validation, the model goes back to training mode and gradients are enabled.

class trajdl.algorithms.t2vec.T2VECEncoder(embedding_layer: BaseTokenEmbeddingLayer, padding_value: int, hidden_size: int, num_layers: int, bidirectional: bool = False, dropout: float = 0.0)

Bases: Module

forward(src: LongTensor, src_lengths: List[int])

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.