vis4d.op.base.dla

DLA base model.

Classes

BasicBlock(inplanes, planes[, stride, dilation])	BasicBlock.
Bottleneck(inplanes, planes[, stride, dilation])	Bottleneck.
BottleneckX(inplanes, planes[, stride, dilation])	BottleneckX.
DLA([name, levels, channels, block, ...])	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)

BasicBlock.

Creates an instance of the class.

forward(input_x, residual=None)

Forward.

Return type:

Tensor

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

Bottleneck.

Creates an instance of the class.

forward(input_x, residual=None)

Forward.

Return type:

Tensor

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

BottleneckX.

Creates an instance of the class.

forward(input_x, residual=None)

Forward.

Return type:

Tensor

class DLA(name=None, levels=(1, 1, 1, 2, 2, 1), channels=(16, 32, 64, 128, 256, 512), block='BasicBlock', residual_root=False, cardinality=32, weights=None, style='imagenet')

DLA base model.

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. fp[0] is a feature map with the image resolution instead of the original image.

Return type:

fp (list[Tensor])

load_pretrained_model(weights)

Load pretrained weights.

Return type:

None

property out_channels: list[int]

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

Returns:

number of channels

Return type:

list[int]

class Root(in_channels, out_channels, kernel_size, residual)

Root.

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)

Tree.

Creates an instance of the class.

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

Forward.

Return type:

Tensor