Create batches

Create batches

Create batches

Create batches

Create batches

error listener

error listener

error listener

error listener

error listener

只使用filter_pred值为True的example

只使用filter_pred值为True的example

只使用filter_pred值为True的example

?

只使用filter_pred值为True的example

output (FloatTensor): batch_size x n_classes target (LongTensor): batch_size

Compute the context vector and the attention vectors. Args: key (`FloatTensor`): set of `key_len` key vectors `[batch, ke

Layer definition. Args: input: [ batch_size, input_len, model_dim ] Returns: output: [ batch_size, input_len, model_di

Transformer Encoder Layer definition. Args: inputs (`FloatTensor`): `[batch_size x src_len x model_dim]`

See :obj:`EncoderBase.forward()`

Computes the embeddings for words and features. Args: source (`LongTensor`): index tensor `[len x batch]` Return: `Float

See :obj:`onmt.modules.RNNDecoderBase.forward()`

output (FloatTensor): batch_size x n_classes target (LongTensor): batch_size

Compute the context vector and the attention vectors. Args: key (`FloatTensor`): set of `key_len` key vectors `[batch, ke

Layer definition. Args: input: [ batch_size, input_len, model_dim ] Returns: output: [ batch_size, input_len, model_di

Transformer Encoder Layer definition. Args: inputs (`FloatTensor`): `[batch_size x src_len x model_dim]` 146 *

See :obj:`EncoderBase.forward()`

Computes the embeddings for words and features. Args: source (`LongTensor`): index tensor `[len x batch]` Return: `Float

See :obj:`onmt.modules.RNNDecoderBase.forward()`

output (FloatTensor): batch_size x n_classes target (LongTensor): batch_size

Compute the context vector and the attention vectors. Args: key (`FloatTensor`): set of `key_len` key vectors `[batch, ke

Layer definition. Args: input: [ batch_size, input_len, model_dim ] Returns: output: [ batch_size, input_len, model_di

Transformer Encoder Layer definition. Args: inputs (`FloatTensor`): `[batch_size x src_len x model_dim]` 146 *

See :obj:`EncoderBase.forward()`

Computes the embeddings for words and features. Args: source (`LongTensor`): index tensor `[len x batch]` Return: `Float

See :obj:`onmt.modules.RNNDecoderBase.forward()`

output (FloatTensor): batch_size x n_classes target (LongTensor): batch_size

Compute the context vector and the attention vectors. Args: key (`FloatTensor`): set of `key_len` key vectors `[batch, ke

Layer definition. Args: input: [ batch_size, input_len, model_dim ] Returns: output: [ batch_size,

See :obj:`EncoderBase.forward()`

Computes the embeddings for words and features. Args: source (`LongTensor`): index tensor `[len x batch]` Return: `Float

See :obj:`onmt.modules.RNNDecoderBase.forward()`

output (FloatTensor): batch_size x n_classes target (LongTensor): batch_size

Compute the context vector and the attention vectors. Args: key (`FloatTensor`): set of `key_len` key vectors `[batch, ke

Layer definition. Args: input: [ batch_size, input_len, model_dim ] Returns: output: [ batch_size, input_len, model_di

Transformer Encoder Layer definition. Args: inputs (`FloatTensor`): `[batch_size x src_len x model_dim]` 146 *

See :obj:`EncoderBase.forward()`

Computes the embeddings for words and features. Args: source (`LongTensor`): index tensor `[len x batch]` Return: `Float

See :obj:`onmt.modules.RNNDecoderBase.forward()`

Get the outputs for the current timestep.

Get the outputs for the current timestep.

Get the outputs for the current timestep.

Get the outputs for the current timestep.

Get the outputs for the current timestep.

Indicate the position of an instance in a tensor.

Indicate the position of an instance in a tensor.

Indicate the position of an instance in a tensor.

Indicate the position of an instance in a tensor.

Indicate the position of an instance in a tensor.

These options are passed to the construction of the model. Be careful with these as they will be used during translation.

These options are passed to the construction of the model. Be careful with these as they will be used during translation.

These options are passed to the construction of the model. Be careful with these as they will be used during translation.

These options are passed to the construction of the model. Be careful with these as they will be used during translation.