For now only strings are accepted as the measures parameter in GridSearchCV, RandomizedSearchCV, and cross_validate. It's thus impossible to use those with measures that take specific parameters as input (e.g. #156 ), or to use custom measures.
We should then accept callables in addition to strings.
Each callable should only take the predictions parameter. In order to handle measur
Our eye tracking code is currently written in Python. It needs to be ported to C++ for both performance and integration reasons. PyTorch has a nice C++ API that is pretty much identical to the Python API. So most of the porting process won't be on changing the neural net but rather the code that invokes it.
cBench provides a unified CLI and API to reproduce results from ML&systems research papers on bare-metal platforms and participate in collaborative benchmarking and optimization using live scoreboards. See the real-world example for the MLPerf benchmark:
For now only strings are accepted as the
measuresparameter inGridSearchCV,RandomizedSearchCV, andcross_validate. It's thus impossible to use those with measures that take specific parameters as input (e.g. #156 ), or to use custom measures.We should then accept callables in addition to strings.
Each callable should only take the
predictionsparameter. In order to handle measur