torchcvnn.nn.ViTLayer¶
- class torchcvnn.nn.ViTLayer(num_heads: int, hidden_dim: int, mlp_dim: int, dropout: float = 0.0, attention_dropout: float = 0.0, norm_layer: ~typing.Callable[[...], ~torch.nn.modules.module.Module] = <class 'torchcvnn.nn.modules.normalization.LayerNorm'>, device: ~torch.device | None = None, dtype: ~torch.dtype = torch.complex64)[source]¶
- __init__(num_heads: int, hidden_dim: int, mlp_dim: int, dropout: float = 0.0, attention_dropout: float = 0.0, norm_layer: ~typing.Callable[[...], ~torch.nn.modules.module.Module] = <class 'torchcvnn.nn.modules.normalization.LayerNorm'>, device: ~torch.device | None = None, dtype: ~torch.dtype = torch.complex64) None [source]¶
The ViT layer cascades a multi-head attention block with a feed-forward network.
- Parameters:
num_heads – Number of heads in the multi-head attention block.
hidden_dim – Hidden dimension of the transformer.
mlp_dim – Hidden dimension of the feed-forward network.
dropout – Dropout rate (default: 0.0).
attention_dropout – Dropout rate in the attention block (default: 0.0).
norm_layer – Normalization layer (default
LayerNorm
).
\[\begin{split}x & = x + \text{attn}(\text{norm1}(x))\\ x & = x + \text{ffn}(\text{norm2}(x))\end{split}\]The FFN block is a two-layer MLP with a modReLU activation function.
Methods
__init__
(num_heads, hidden_dim, mlp_dim[, ...])The ViT layer cascades a multi-head attention block with a feed-forward network.
add_module
(name, module)Add a child module to the current module.
apply
(fn)Apply
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])Return an iterator over module buffers.
children
()Return an iterator over immediate children modules.
compile
(*args, **kwargs)Compile this Module's forward using
torch.compile()
.cpu
()Move all model parameters and buffers to the CPU.
cuda
([device])Move all model parameters and buffers to the GPU.
double
()Casts all floating point parameters and buffers to
double
datatype.eval
()Set 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
(x)Performs the forward pass through the layer using pre-normalization.
get_buffer
(target)Return the buffer given by
target
if it exists, otherwise throw an error.get_extra_state
()Return any extra state to include in the module's state_dict.
get_parameter
(target)Return the parameter given by
target
if it exists, otherwise throw an error.get_submodule
(target)Return the submodule given by
target
if it exists, otherwise throw an error.half
()Casts all floating point parameters and buffers to
half
datatype.ipu
([device])Move all model parameters and buffers to the IPU.
load_state_dict
(state_dict[, strict, assign])Copy parameters and buffers from
state_dict
into this module and its descendants.modules
()Return an iterator over all modules in the network.
mtia
([device])Move all model parameters and buffers to the MTIA.
named_buffers
([prefix, recurse, ...])Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
named_children
()Return 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])Return 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, ...])Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
parameters
([recurse])Return an iterator over module parameters.
register_backward_hook
(hook)Register a backward hook on the module.
register_buffer
(name, tensor[, persistent])Add a buffer to the module.
register_forward_hook
(hook, *[, prepend, ...])Register a forward hook on the module.
register_forward_pre_hook
(hook, *[, ...])Register a forward pre-hook on the module.
register_full_backward_hook
(hook[, prepend])Register a backward hook on the module.
register_full_backward_pre_hook
(hook[, prepend])Register a backward pre-hook on the module.
register_load_state_dict_post_hook
(hook)Register a post-hook to be run after module's
load_state_dict()
is called.register_load_state_dict_pre_hook
(hook)Register a pre-hook to be run before module's
load_state_dict()
is called.register_module
(name, module)Alias for
add_module()
.register_parameter
(name, param)Add a parameter to the module.
register_state_dict_post_hook
(hook)Register a post-hook for the
state_dict()
method.register_state_dict_pre_hook
(hook)Register a pre-hook for the
state_dict()
method.requires_grad_
([requires_grad])Change if autograd should record operations on parameters in this module.
set_extra_state
(state)Set extra state contained in the loaded state_dict.
set_submodule
(target, module)Set the submodule given by
target
if it exists, otherwise throw an error.share_memory
()state_dict
(*args[, destination, prefix, ...])Return a dictionary containing references to the whole state of the module.
to
(*args, **kwargs)Move and/or cast the parameters and buffers.
to_empty
(*, device[, recurse])Move the parameters and buffers to the specified device without copying storage.
train
([mode])Set the module in training mode.
type
(dst_type)Casts all parameters and buffers to
dst_type
.xpu
([device])Move all model parameters and buffers to the XPU.
zero_grad
([set_to_none])Reset gradients of all model parameters.
Attributes
T_destination
call_super_init
dump_patches
training