nntoolbox.vision.components.attention module

class nntoolbox.vision.components.attention.SAGANAttention(in_channels: int, reduction_ratio: int = 8)

Bases: torch.nn.modules.module.Module

Implement SAGAN attention module.

References:

Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena. “Self-Attention Generative Adversarial Networks.” https://arxiv.org/pdf/1805.08318.pdf

forward(input: torch.Tensor) → torch.Tensor

Defines 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.

training: bool

class nntoolbox.vision.components.attention.StandAloneMultiheadAttention(num_heads: int, in_channels: int, out_channels: int, kernel_size, stride=1, padding: int = 0, dilation: int = 1, bias: bool = True, padding_mode: str = 'zeros')

Bases: torch.nn.modules.module.Module

Stand-Alone Multihead Self-Attention for Vision Model

References:

Prajit Ramachandran, Niki Parmar, Ashish Vaswani, Irwan Bello, Anselm Levskaya, Jonathon Shlens. “Stand-Alone Self-Attention in Vision Models.” https://arxiv.org/pdf/1906.05909.pdf.

forward(input: torch.Tensor) → torch.Tensor

Defines 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.

training: bool

class nntoolbox.vision.components.attention.StandAloneSelfAttention(in_channels: int, out_channels: int, kernel_size, stride=1, padding: int = 0, dilation: int = 1, bias: bool = True, padding_mode: str = 'zeros')

Bases: torch.nn.modules.conv.Conv2d

A single head of Stand-Alone Self-Attention for Vision Model

References:

Prajit Ramachandran, Niki Parmar, Ashish Vaswani, Irwan Bello, Anselm Levskaya, Jonathon Shlens. “Stand-Alone Self-Attention in Vision Models.” https://arxiv.org/pdf/1906.05909.pdf.

bias: Optional[torch.Tensor]

compute_output_shape(height, width)

dilation: Tuple[int, …]

forward(input: torch.Tensor) → torch.Tensor

Defines 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.

get_rel_embedding() → torch.Tensor

groups: int

kernel_size: Tuple[int, …]

out_channels: int

output_padding: Tuple[int, …]

padding: Tuple[int, …]

padding_mode: str

stride: Tuple[int, …]

to(*args, **kwargs)

Moves and/or casts the parameters and buffers.

This can be called as

to(device=None, dtype=None, non_blocking=False)

to(dtype, non_blocking=False)

to(tensor, non_blocking=False)

to(memory_format=torch.channels_last)

Its signature is similar to torch.Tensor.to(), but only accepts floating point desired dtype s. In addition, this method will only cast the floating point parameters and buffers to dtype (if given). The integral parameters and buffers will be moved device, if that is given, but with dtypes unchanged. When non_blocking is set, it tries to convert/move asynchronously with respect to the host if possible, e.g., moving CPU Tensors with pinned memory to CUDA devices.

See below for examples.

Note

This method modifies the module in-place.

Args:

device (torch.device): the desired device of the parameters

and buffers in this module

dtype (torch.dtype): the desired floating point type of

the floating point parameters and buffers in this module

tensor (torch.Tensor): Tensor whose dtype and device are the desired

dtype and device for all parameters and buffers in this module

memory_format (torch.memory_format): the desired memory

format for 4D parameters and buffers in this module (keyword only argument)

Returns:

Module: self

Example:

>>> linear = nn.Linear(2, 2)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
        [-0.5113, -0.2325]])
>>> linear.to(torch.double)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
        [-0.5113, -0.2325]], dtype=torch.float64)
>>> gpu1 = torch.device("cuda:1")
>>> linear.to(gpu1, dtype=torch.half, non_blocking=True)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
        [-0.5112, -0.2324]], dtype=torch.float16, device='cuda:1')
>>> cpu = torch.device("cpu")
>>> linear.to(cpu)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
        [-0.5112, -0.2324]], dtype=torch.float16)

transposed: bool

weight: torch.Tensor