A BlockPacker node

r""" Default processor for performing attention-related computations.

Creates a component allows users to upload or view 3D Model files (.glb). Demos: model3D Guides: how-to-use-3D-model-component

Feature fusion block.

Feature fusion block.

Interpolation module.

r""" Processor for implementing scaled dot-product attention (enabled by default if you're using PyTorch 2.0).

r""" Default processor for performing attention-related computations.

A Local Feature Transformer (LoFTR) module.

Mobile Inverted Residual Bottleneck Block. Args: block_args (namedtuple): BlockArgs, defined in utils.py. global_params (namedtup

Residual convolution module.

Residual convolution module.

Transformer.

A rectangular block, to be packed

Packs blocks of varying sizes into a single, larger block

Constructs a ECA module. Args: channel: Number of channels of the input feature map k_size: Adaptive selection of kernel size

FineMatching with s2d paradigm

Fast gelu implementation.

r""" Attention processor for IP-Adapater. Args: hidden_size (`int`): The hidden size of the attention layer. cross

Args: floor_inds_plus_one_mask (torch.Tensor): Shape (batch_size, *spatial_shape + 1) floor_inds_plus_one (torch.Tensor): Shape (

Upsampling block.

This is a sinusoidal position encoding that generalized to 2-dimensional images

Attention block.

ResNet+FPN, output resolution are 1/16 and 1/4. Each block has 2 layers.

ResNet+FPN, output resolution are 1/8 and 1/2. Each block has 2 layers.

A compact VGG-style network structure for super-resolution. It is a compact network structure, which performs upsampling in the last layer and no

Tracer Decoder