vis4d.op.base.dla

DLA base model.

Classes

BasicBlock(inplanes, planes[, stride, ...])	BasicBlock.
Bottleneck(inplanes, planes[, stride, ...])	Bottleneck.
BottleneckX(inplanes, planes[, stride, ...])	BottleneckX.
DLA(name[, out_indices, with_cp, ...])	DLA base model.
Root(in_channels, out_channels, kernel_size, ...)	Root.
Tree(levels, block, in_channels, out_channels)	Tree.

class BasicBlock(inplanes, planes, stride=1, dilation=1, with_cp=False)

BasicBlock.

__init__(inplanes, planes, stride=1, dilation=1, with_cp=False)

Creates an instance of the class.

forward(input_x, residual=None)

Forward.

Return type:

Tensor

class Bottleneck(inplanes, planes, stride=1, dilation=1, with_cp=False)

Bottleneck.

__init__(inplanes, planes, stride=1, dilation=1, with_cp=False)

Creates an instance of the class.

forward(input_x, residual=None)

Forward.

Return type:

Tensor

class BottleneckX(inplanes, planes, stride=1, dilation=1, with_cp=False)

BottleneckX.

__init__(inplanes, planes, stride=1, dilation=1, with_cp=False)

Creates an instance of the class.

forward(input_x, residual=None)

Forward.

Return type:

Tensor

class Root(in_channels, out_channels, kernel_size, residual, with_cp=False)

Root.

__init__(in_channels, out_channels, kernel_size, residual, with_cp=False)

Creates an instance of the class.

forward(*input_x)

Forward.

Return type:

Tensor

class Tree(levels, block, in_channels, out_channels, stride=1, level_root=False, root_dim=0, root_kernel_size=1, dilation=1, root_residual=False, with_cp=False)

Tree.

__init__(levels, block, in_channels, out_channels, stride=1, level_root=False, root_dim=0, root_kernel_size=1, dilation=1, root_residual=False, with_cp=False)

Creates an instance of the class.

forward(input_x, residual=None, children=None)

Forward.

Return type:

Tensor

class DLA(name, out_indices=(0, 1, 2, 3), with_cp=False, pretrained=False, weights=None)

DLA base model.

__init__(name, out_indices=(0, 1, 2, 3), with_cp=False, pretrained=False, weights=None)

Creates an instance of the class.

forward(images)

DLA forward.

Parameters:

images (Tensor[N, C, H, W]) – Image input to process. Expected to type float32 with values ranging 0..255.

Returns:

The output feature pyramid. The list index represents the level, which has a downsampling raio of 2^index.

Return type:

fp (list[Tensor])

property out_channels: list[int]

Get the numbers of channels for each level of feature pyramid.

Returns:

number of channels

Return type:

list[int]