6a455db8f33ceefa0f8c544dc427ba6402f85588,gpflow/conditionals/util.py,,fully_correlated_conditional_repeat,#Any#Any#Any#Any#,273

Before Change

        - variance: [R, N, P], [R, N, P, P], [R, P, N, N], [R, N, P, N, P]
    
    R = f.shape[1]
    M, N, K = [Kmn.shape[i] for i in range(Kmn.shape.ndims)]
    Lm = tf.linalg.cholesky(Kmm)

    // Compute the projection matrix A
    // Lm: [M, M]    Kmn: [M, K]

After Change

        - variance: [R, N, P], [R, N, P, P], [R, P, N, N], [R, N, P, N, P]
    
    R = tf.shape(f)[1]
    M, N, K = tf.unstack(tf.shape(Kmn), num=Kmn.shape.ndims, axis=0)
    Lm = tf.linalg.cholesky(Kmm)

    // Compute the projection matrix A
    // Lm: [M, M]    Kmn: [M, K]

Instances