MCPcopy
hub / github.com/GPflow/GPflow / predict_all

Function predict_all

tests/gpflow/conditionals/test_multioutput.py:44–55  ·  view source on GitHub ↗

Returns the mean and variance of f(Xnew) for each model in `models`.

(
    models: Sequence[SVGP], Xnew: tf.Tensor, full_cov: bool, full_output_cov: bool
)

Source from the content-addressed store, hash-verified

42 "return[1]: [n_models, N, P] if (not full_cov) and (not full_output_cov)",
43)
44def predict_all(
45 models: Sequence[SVGP], Xnew: tf.Tensor, full_cov: bool, full_output_cov: bool
46) -> Tuple[List[tf.Tensor], List[tf.Tensor]]:
47 """
48 Returns the mean and variance of f(Xnew) for each model in `models`.
49 """
50 ms, vs = [], []
51 for model in models:
52 m, v = model.predict_f(Xnew, full_cov=full_cov, full_output_cov=full_output_cov)
53 ms.append(m)
54 vs.append(v)
55 return ms, vs
56
57
58@check_shapes(

Callers 1

Calls 1

predict_fMethod · 0.45

Tested by

no test coverage detected

Used in the wild real call sites across dependent graphs

searching dependent graphs…