pytorch_extra_mhirano.nn.DotProductAttention

class pytorch_extra_mhirano.nn.DotProductAttention(qdim: int, output_dim: Optional[int] = None, dropout: float = 0.0, transform: bool = True, bias: bool = True, same_embd: bool = True, add_bias_kv: Optional[bool] = None, kdim: Optional[int] = None, vdim: Optional[int] = None, batch_first: bool = True, scaled: bool = False)

DotProductAttention.

\[ \begin{align}\begin{aligned}\mathrm{DotProductAttention}(Q, K, V) &=& \mathrm{softmax}(qk^T) v\\q &=& QW_1 + b_1\\k &=& KW_2 + b_2\\v &=& VW_3 + b_3\end{aligned}\end{align} \]

Parameters

• qdim – dimension of the model, i.e., dimension of Q

• output_dim – dimension of output layer, i.e., dimension of output. Default: None

• dropout – a Dropout layer on attn_output_weights. Default: 0.0.

• transform – q = Q, k = K, v = V if it is False. Default: True

• bias – add bias as module parameter. Default: True.

• same_embd – W1 = W2 = W3, b1 = b2 = b3 if it is True. Default: True

• add_bias_kv – add bias to the key and value sequences at dim=0.

• kdim – total number of features in key. Default: None.

• vdim –

  total number of features in key. Default: None. Note: if kdim and vdim are None, they will be set to embed_dim such that

  query, key, and value have the same number of features.

• batch_first – If True, then the input and output tensors are provided as (batch, seq, feature). Default: False (seq, batch, feature)

• scaled – If True, this performs as scaled dot product attention

Examples::

>>> attn = DotProductAttention(query_dim)
>>> attn_output, attn_output_weights = attn(query, key, value)

__init__(qdim: int, output_dim: Optional[int] = None, dropout: float = 0.0, transform: bool = True, bias: bool = True, same_embd: bool = True, add_bias_kv: Optional[bool] = None, kdim: Optional[int] = None, vdim: Optional[int] = None, batch_first: bool = True, scaled: bool = False) → None

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

Methods

__init__(qdim[, output_dim, dropout, ...])	Initializes internal Module state, shared by both nn.Module and ScriptModule.
add_module(name, module)	Adds a child module to the current module.
apply(fn)	Applies fn recursively to every submodule (as returned by .children()) as well as self.
bfloat16()	Casts all floating point parameters and buffers to bfloat16 datatype.
buffers([recurse])	Returns an iterator over module buffers.
children()	Returns an iterator over immediate children modules.
cpu()	Moves all model parameters and buffers to the CPU.
cuda([device])	Moves all model parameters and buffers to the GPU.
double()	Casts all floating point parameters and buffers to double datatype.
eval()	Sets the module in evaluation mode.
extra_repr()	Set the extra representation of the module
float()	Casts all floating point parameters and buffers to float datatype.
forward(query, key, value[, ...])	param query Query embeddings of shape \((L, E_q)\) for unbatched input, \((L, N, E_q)\) when batch_first=False
generate_square_subsequent_mask(sz)	Generate a square mask for the sequence.
get_buffer(target)	Returns the buffer given by target if it exists, otherwise throws an error.
get_extra_state()	Returns any extra state to include in the module's state_dict.
get_parameter(target)	Returns the parameter given by target if it exists, otherwise throws an error.
get_submodule(target)	Returns the submodule given by target if it exists, otherwise throws an error.
half()	Casts all floating point parameters and buffers to half datatype.
ipu([device])	Moves all model parameters and buffers to the IPU.
load_state_dict(state_dict[, strict])	Copies parameters and buffers from state_dict into this module and its descendants.
modules()	Returns an iterator over all modules in the network.
named_buffers([prefix, recurse, ...])	Returns an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
named_children()	Returns an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
named_modules([memo, prefix, remove_duplicate])	Returns an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
named_parameters([prefix, recurse, ...])	Returns an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
parameters([recurse])	Returns an iterator over module parameters.
register_backward_hook(hook)	Registers a backward hook on the module.
register_buffer(name, tensor[, persistent])	Adds a buffer to the module.
register_forward_hook(hook, *[, prepend, ...])	Registers a forward hook on the module.
register_forward_pre_hook(hook, *[, ...])	Registers a forward pre-hook on the module.
register_full_backward_hook(hook[, prepend])	Registers a backward hook on the module.
register_full_backward_pre_hook(hook[, prepend])	Registers a backward pre-hook on the module.
register_load_state_dict_post_hook(hook)	Registers a post hook to be run after module's load_state_dict is called.
register_module(name, module)	Alias for add_module().
register_parameter(name, param)	Adds a parameter to the module.
register_state_dict_pre_hook(hook)	These hooks will be called with arguments: self, prefix, and keep_vars before calling state_dict on self.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
set_extra_state(state)	This function is called from load_state_dict() to handle any extra state found within the state_dict.
share_memory()	See torch.Tensor.share_memory_()
state_dict(*args[, destination, prefix, ...])	Returns a dictionary containing references to the whole state of the module.
to(*args, **kwargs)	Moves and/or casts the parameters and buffers.
to_empty(*, device)	Moves the parameters and buffers to the specified device without copying storage.
train([mode])	Sets the module in training mode.
type(dst_type)	Casts all parameters and buffers to dst_type.
xpu([device])	Moves all model parameters and buffers to the XPU.
zero_grad([set_to_none])	Sets gradients of all model parameters to zero.

Attributes

T_destination	alias of TypeVar('T_destination', bound=Dict[str, Any])
call_super_init
dump_patches

previous

API reference

next

pytorch_extra_mhirano.nn.SelfAttention