leandron opened a new issue #6305:
URL: https://github.com/apache/incubator-tvm/issues/6305
As part of a recent PR #6302, I noticed a test that had nothing to do with
the implementation is failing for unknown reasons.
That is
`tests/python/unittest/test_auto_scheduler_cost_model.py::test_xgb_model`, and
error is shown below:
```
________________________________ test_xgb_model
________________________________
def test_xgb_model():
task, dag, inputs, results = get_sample_records(50)
model = auto_scheduler.XGBModel(num_warmup_sample=-1)
model.update(inputs, results)
preds = model.predict(task, [x.state for x in inputs])
assert len(preds) == len(inputs)
costs = [np.mean([x.value for x in res.costs]) for res in results]
throughputs = np.min(costs) / costs
rmse = np.sqrt(np.mean([np.square(pred - label) for pred, label in
zip(preds, throughputs)]))
> assert rmse <= 0.05
E assert 0.09984155049112678 <= 0.05
tests/python/unittest/test_auto_scheduler_cost_model.py:68: AssertionError
```
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
