norse.torch.module.receptive_field.SpatialReceptiveField2d#

class norse.torch.module.receptive_field.SpatialReceptiveField2d(in_channels: int, n_scales: int, n_angles: int, n_ratios: int, size: int, derivatives: Union[int, List[Tuple[int, int]]] = 0, min_scale: float = 0.2, max_scale: float = 1.5, min_ratio: float = 0.2, max_ratio: float = 1, aggregate: bool = True, **kwargs)[source]#

Creates a spatial receptive field as 2-dimensional convolutions. The parameters decide the number of combinations to scan over, i. e. the number of receptive fields to generate. Specifically, we generate n_scales * n_angles * (n_ratios - 1) + n_scales output_channels with aggregation, and in_channels * (n_scales * n_angles * (n_ratios - 1) + n_scales) without aggregation.

The (n_ratios - 1) + n_scales terms exist because at ratio = 1, fields are perfectly symmetrical, and there is therefore no reason to scan over the angles and scales for ratio = 1. However, n_scales receptive field still needs to be added (one for each scale-space).

Parameters:

n_scales (int): Number of scaling combinations (the size of the receptive field) drawn from a logarithmic distribution n_angles (int): Number of angular combinations (the orientation of the receptive field) n_ratios (int): Number of eccentricity combinations (how “flat” the receptive field is) size (int): The size of the square kernel in pixels derivatives (Union[int, List[Tuple[int, int]]]): The number of derivatives to use in the receptive field. aggregate (bool): If True, sums the input channels over all output channels. If False, every output channel is mapped to every input channel, which may blow up in complexity. **kwargs: Arguments passed on to the underlying torch.nn.Conv2d

__init__(in_channels: int, n_scales: int, n_angles: int, n_ratios: int, size: int, derivatives: Union[int, List[Tuple[int, int]]] = 0, min_scale: float = 0.2, max_scale: float = 1.5, min_ratio: float = 0.2, max_ratio: float = 1, aggregate: bool = True, **kwargs) None[source]#

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

Methods

__init__(in_channels, n_scales, n_angles, ...)

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.

compile(*args, **kwargs)

Compile this Module's forward using torch.compile().

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(x)

Defines the computation performed at every call.

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, assign])

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[, recurse])

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])

Resets gradients of all model parameters.

Attributes

T_destination

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

call_super_init

dump_patches