mwptoolkit.model.Seq2Seq.transformer

class mwptoolkit.model.Seq2Seq.transformer.Transformer(config, dataset)

Bases: Module

Reference:

Vaswani et al. “Attention Is All You Need”.

Initializes internal Module state, shared by both nn.Module and ScriptModule.

calculate_loss(batch_data: dict) → float

Finish forward-propagating, calculating loss and back-propagation.

Parameters

batch_data – one batch data.

Returns

loss value.

batch_data should include keywords ‘question’, ‘equation’.

convert_idx2symbol(output, num_list)

convert_in_idx_2_out_idx(output)

convert_out_idx_2_in_idx(output)

decode(output)

decoder_forward(encoder_outputs, seq_mask, target=None, output_all_layers=False)

encoder_forward(seq_emb, seq_mask, output_all_layers=False)

forward(src, target=None, output_all_layers=False) → Tuple[Tensor, Tensor, Dict[str, Any]]

Parameters

• src (torch.Tensor) – input sequence, shape: [batch_size, seq_length].

• target (torch.Tensor|None) – target, shape: [batch_size, target_length], default None.

• output_all_layers (bool) – default False, return output of all layers if output_all_layers is True.

Returns

token_logits, symbol_outputs, model_all_outputs.

:rtype tuple(torch.Tensor, torch.Tensor, dict)

init_decoder_inputs(target, device, batch_size)

model_test(batch_data: dict) → tuple

Model test.

Parameters

batch_data – one batch data.

Returns

predicted equation, target equation.

batch_data should include keywords ‘question’, ‘equation’ and ‘num list’.

predict(batch_data: dict, output_all_layers=False)

predict samples without target.

Parameters

• batch_data (dict) – one batch data.

• output_all_layers (bool) – return all layer outputs of model.

Returns

token_logits, symbol_outputs, all_layer_outputs

training: bool