lightning_pose.models.backbones

lightning_pose.models.backbones.torchvision Module

Functions

build_backbone(backbone_arch[, pretrained, ...])	Load backbone weights for resnets, efficientnets, and other models from torchvision.
grab_layers_sequential(model, last_layer_ind)	Package selected number of layers into a torch.nn.Sequential object.

lightning_pose.models.backbones.vit_sam Module

Load vision encoder from Facebook SAM model using HuggingFace.

Classes

SamVisionEncoder

Wrapper around HuggingFace's SAM Vision Encoder.

lightning_pose.models.backbones.vits Module

Functions

build_backbone(backbone_arch[, image_size])

Load backbone weights for resnet models.