Supplying shape parameters don't seem to have any effect.

[shash29-dev]

Thanks for sharing the code.
Supplying shape parameters don't seem to have any effect.

Following if else condition reads th_beta instead of default self.th_betas, but rendering mesh does not have shape-specific changes. What may be the issue?

        # Below does: v_shaped = v_template + shapedirs * betas
        # If shape parameters are not provided
        if th_betas is None or bool(torch.norm(th_betas) == 0):
            th_v_shaped = self.th_v_template + torch.matmul(
                self.th_shapedirs, self.th_betas.transpose(1, 0)).permute(2, 0, 1)
            th_j = torch.matmul(self.th_J_regressor, th_v_shaped).repeat(
                batch_size, 1, 1)
        else:
            th_v_shaped = self.th_v_template + torch.matmul(
                self.th_shapedirs, th_betas.transpose(1, 0)).permute(2, 0, 1)
            th_j = torch.matmul(self.th_J_regressor, th_v_shaped)

How do you get shape variations?