tiny_diff.models.unet.model.UNet

class tiny_diff.models.unet.model.UNet(time_channels: int | None = None, attn_at_layer: list[bool] | None = None, zero_init: bool = True, mid_attention_factory: LayerFactory | None = None, **kwargs)

Bases: ConvModel

UNet model used for diffusion tasks.

Parameters:

• time_channels – channels of the time embedding dimension

• attn_at_layer – list of layer indexes in which attention should be used

• zero_init – whether to init weights to zero or not

__init__(time_channels: int | None = None, attn_at_layer: list[bool] | None = None, zero_init: bool = True, mid_attention_factory: LayerFactory | None = None, **kwargs)

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

Methods

__init__([time_channels, attn_at_layer, ...])	Initialize internal Module state, shared by both nn.Module and ScriptModule.
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().
conv_kwargs(in_ch, out_ch[, pop])	Kwargs to pass to convolutional blocks init.
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, t, **kwargs)	Define the computation performed at every call.
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.
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_module(name, module)	Alias for add_module().
register_parameter(name, param)	Add a parameter to the module.
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.
res_kwargs(*args[, attention, pop])	Kwargs to pass to residual layer's init.
save(path)	Saves himself at path.
set_extra_state(state)	Set extra state contained in the loaded state_dict.
share_memory()	See torch.Tensor.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.
up_res_kwargs(*args, **kwargs)	Kwargs for residual layers of the second half of the net.
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
channels	Input channels + Conv channels.
conv_channels	Channels in convolutional layers.
down_channels	Channels of the first half of the UNet.
dump_patches
n_conv_layers	How many conv layers does the model have.
r_channels	Channels property reversed.
scale_factor	Scale factor used in in interpolation layers.
stride	Stride used in convolutional blocks.
up_channels	Channels of the second half of the UNet.
training