Method forward

util/smplx/smplx/body_models.py:739–811

(self,
                betas: Optional[Tensor] = None,
                global_orient: Optional[Tensor] = None,
                body_pose: Optional[Tensor] = None,
                left_hand_pose: Optional[Tensor] = None,
                right_hand_pose: Optional[Tensor] = None,
                transl: Optional[Tensor] = None,
                return_verts: bool = True,
                return_full_pose: bool = False,
                pose2rot: bool = True,
                **kwargs)

                                         **kwargs)

    def forward(self,
                betas: Optional[Tensor] = None,
                global_orient: Optional[Tensor] = None,
                body_pose: Optional[Tensor] = None,
                left_hand_pose: Optional[Tensor] = None,
                right_hand_pose: Optional[Tensor] = None,
                transl: Optional[Tensor] = None,
                return_verts: bool = True,
                return_full_pose: bool = False,
                pose2rot: bool = True,
                **kwargs) -> SMPLHOutput:
        """"""
        device, dtype = self.shapedirs.device, self.shapedirs.dtype
        if global_orient is None:
            batch_size = 1
            global_orient = torch.zeros(3, device=device, dtype=dtype).view(
                1, 1, 3).expand(batch_size, -1, -1).contiguous()
        else:
            batch_size = global_orient.shape[0]
        if body_pose is None:
            body_pose = torch.zeros(3, device=device, dtype=dtype).view(
                1, 1, 3).expand(batch_size, 21, -1).contiguous()
        if left_hand_pose is None:
            left_hand_pose = torch.zeros(3, device=device, dtype=dtype).view(
                1, 1, 3).expand(batch_size, 15, -1).contiguous()
        if right_hand_pose is None:
            right_hand_pose = torch.zeros(3, device=device, dtype=dtype).view(
                1, 1, 3).expand(batch_size, 15, -1).contiguous()
        if betas is None:
            betas = torch.zeros([batch_size, self.num_betas],
                                dtype=dtype,
                                device=device)
        if transl is None:
            transl = torch.zeros([batch_size, 3], dtype=dtype, device=device)

        # Concatenate all pose vectors
        full_pose = torch.cat([
            global_orient.reshape(-1, 1, 3),
            body_pose.reshape(-1, self.NUM_BODY_JOINTS, 3),
            left_hand_pose.reshape(-1, self.NUM_HAND_JOINTS, 3),
            right_hand_pose.reshape(-1, self.NUM_HAND_JOINTS, 3)
        ],
                              dim=1)

        vertices, joints = lbs(betas,
                               full_pose,
                               self.v_template,
                               self.shapedirs,
                               self.posedirs,
                               self.J_regressor,
                               self.parents,
                               self.lbs_weights,
                               pose2rot=True)

        # Add any extra joints that might be needed
        joints = self.vertex_joint_selector(vertices, joints)
        if self.joint_mapper is not None:
            joints = self.joint_mapper(joints)