Closed corochann closed 4 years ago
converter
Currently it is difficult to unify deciding which converter
to use.
Current implementation is as follows:
NumpyTupleDataset
->use converter_method_dict
to switch converter based on modeldataset.converter
to use converter on dataset.I confirmed following example runs.
bash -x test_mp.sh 0
: train megnet & cgcnn with mp dataset, on GPU.bash -x test_qm9.sh 0
: train megnet works well, as well as sparse gin_sparse
model.bash -x test_molnet.sh
wtih modified --method megnet
: train megnet with molnet.bash -x test_tox21.sh 0
: training code works without backward compatibility break.I dropped testing py27 & py35 as well. When pymatgen
is installed, it seems pandas
version will change and work only when py36~ is used.
/test
Successfully created a job for commit 34779fc:
/test
Successfully created a job for commit ffe59f9:
Let me re-organize code and submit PR later.
From PR https://github.com/pfnet-research/chainer-chemistry/pull/396