Vision Transformer with support for patch or hybrid CNN input stage

r"""Applies a spatial temporal graph convolution over an input graph sequence. Args: in_channels (int): Number of channels in the input se

Multi-Head Attention module from "Attention is All You Need" Implementation modified from OpenNMT-py. https://github.com/OpenNMT/OpenNMT

Original Code from: https://discuss.pytorch.org/t/batchnorm-for-different-sized-samples-in-batch/44251/8

Position-wise Feed-forward layer Projects to ff_size and then back down to input_size.

r"""The basic module for applying a graph convolution. Args: in_channels (int): Number of channels in the input sequence data out_

The Graph to model the skeletons extracted by the openpose Args: strategy (string): must be one of the follow candidates - unifor

CNN Feature Map Embedding Extract feature map from CNN, flatten, project to embedding dim.

MLD Loss

Image to Patch Embedding

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 t

Extension of the official SMPL implementation to support more joints

Implementation of SMPLify, use 3D joints.

Loss Modify loss

Simple embeddings class