Help Debugging Dirichlet Process Mixture of Multivariate Normal

I’d like to create a Dirichlet Process Mixture Model, where each mixture component is a Multivariate Normal distribution with means drawn from an isotropic prior. However, I’m running into an error that I don’t understand.

The error is: Input dimension mis-match. (input[0].shape[1] = 13, input[1].shape[1] = 2)

My code is:

    num_obs, obs_dim = observations.shape
    max_num_clusters = 13

    def stick_breaking(beta):
        portion_remaining = tt.concatenate([[1], tt.extra_ops.cumprod(1 - beta)[:-1]])
        return beta * portion_remaining

    with pm.Model() as model:
        w = pm.Deterministic("w", stick_breaking(beta))
        cluster_means = pm.MvNormal(f'cluster_means',
                                    mu=pm.floatX(np.zeros(obs_dim)),
                                    cov=pm.floatX(gaussian_mean_prior_cov_scaling * np.eye(obs_dim)),
                                    shape=(max_num_clusters, obs_dim))

        comp_dists = pm.MvNormal.dist(mu=cluster_means,
                                      cov=gaussian_cov_scaling * np.eye(obs_dim),
                                      shape=(max_num_clusters, obs_dim))

        obs = pm.Mixture(
            "obs",
            w=w,
            comp_dists=comp_dists,
            observed=observations,
            shape=obs_dim)

Can someone clarify how to get my shapes to work properly?

I posted on StackOverflow (pymc - PyMC3 Dirichlet Process Multivariate Gaussian Mixture Model - Stack Overflow) but hopefully posting here gets me a faster answer.