Very simple multi-layer perceptron (also called FFN)

Compose a data pipeline with a sequence of transforms. Args: transforms (list[dict | callable]): Either config dicts of trans

Default formatting bundle. It simplifies the pipeline of formatting common fields, including "img", "proposals", "gt_bboxes", "gt_labels", "g

Normalize the image. Args: mean (sequence): Mean values of 3 channels. std (sequence): Std values of 3 channels. to_rgb (

Locally Connected Layer. Args: in_channels (int): the in channel of the features. out_channels (int): the

SMPL(X) body mesh vertex segmentation.

IoULoss. Computing the oks loss between a set of predicted poses and target poses. Args: linear (bool): If True, use linear scale of

Mesh structure for parametric body models, E.g., smpl, smplx, mano, flame. There are 3 ways to initialize the verts: 1): Pass the ver

Extension of the official SMPL implementation.

Stores assignments between predicted and truth boxes. Attributes: num_gts (int): the number of truth boxes considered when computing this

A wrapper of concatenated dataset. Same as :obj:`torch.utils.data.dataset.ConcatDataset`, but add `get_cat_ids` function. Args:

ExPose Decoder Decode latent representation to rotation. Args: num_angles (int): Joint num. dtype: dtype. mean (torch.ten

This function crops the HD images using bilinear interpolation.

Inherited from Pytorch3D `FoVOrthographicCameras`.

A simple pipeline to load image.

Collects parameters for optimization.

This module converts the model's output into the format expected by the coco api.

Bbox sampling result. Example: >>> # xdoctest: +IGNORE_WANT >>> from mmdet.core.bbox.samplers.sampling_result import * # NOQA

Track a series of values and provide access to smoothed values over a window or the global series average.

An interactive renderer for camera visualization.

Computes and stores the average and current value.

Render of joints.

ResNet backbone with frozen BatchNorm.

A basic Swin Transformer layer for one stage. Args: dim (int): Number of feature channels depth (int): Depths of this stage.

A custom implementation for OSX pipeline.

Apply DeciWatch framework for 10x efficiency. "DeciWatch: A Simple Baseline for 10× Efficient 2D and 3D Pose Estimation", arXiv'2022. More det

A DistributedDataParallel wrapper for models in 3D mesh estimation task. In 3D mesh estimation task, there is a need to wrap different modules i

Dictionary keeping track of the best fit per image in the training set. Ref: https://github.com/nkolot/SPIN/blob/master/train/fits_dict.py

BatchNorm2d where the batch statistics and the affine parameters are fixed.

Discriminator for SMPL pose parameters of all joints. Args: fc_layers (Tuple): Tuple of neuron count, such as (736, 1024, 1024,

High-Resolution Module for HRNet. In this module, every branch has 4 BasicBlocks/Bottlenecks. Fusion/Exchange is in this module.

Regressor for ExPose Head.

Keypoint Attention Layer. Args: use_conv (bool): whether to use conv for the attended feature map. Default: False

MLP Args: input_dim (int): Input dim of MLP. output_dim (int): Output dim of MLP. layers (List): Layer dims. activ

Multilayer perceptron.

Image to Patch Embedding Args: patch_size (int): Patch token size. Default: 4. in_chans (int): Number of input image channels. De

Discriminator for SMPL pose parameters of each joint. It is composed of discriminators for each joints. The inputs is (batch_size x joint_cou

Absolute pos embedding, learned.

This is a more standard version of the position embedding, very similar to the one used by the Attention is all you need paper, generalized to wor

This is a more standard version of the position embedding, very similar to the one used by the Attention is all you need paper, generalized to wor

This module converts the model's output into the format expected by the coco api

This module converts the model's output into the format expected by the coco api

This module converts the model's output into the format expected by the coco api

This module converts the model's output into the format expected by the coco api

A wrapper of repeated dataset. The length of repeated dataset will be `times` larger than the original dataset. This is useful when the data

ResLayer to build ResNet style backbone. Args: block (nn.Module): block used to build ResLayer. inplanes (int): inplanes of block

Render SMPL(X) with different render choices.