'aevsize': aevsize,
'num_nets': Nnets,
'atomtyp': ['H', 'C', 'N', 'O']
}
## Train the ensemble ##
aet = alt.alaniensembletrainer(netdir, netdict, h5stor, Nnets)
aet.build_strided_training_cache(Nblock, Nbvald, Nbtest, False)
aet.train_ensemble(GPU)
if i < 5:
ldtdir = root_dir # local data directories
if not os.path.exists(root_dir + datdir + str(i + 1).zfill(2)):
os.mkdir(root_dir + datdir + str(i + 1).zfill(2))
## Run active learning sampling ##
acs = alt.alconformationalsampler(ldtdir, datdir + str(i + 1).zfill(2),
optlfile, fpatoms, netdict)
#acs.run_sampling_cluster(gcmddict, GPU)
#acs.run_sampling_dimer(dmrparams, GPU)
#acs.run_sampling_nms(nmsparams, GPU)
#acs.run_sampling_md(mdsparams, perc=0.5, gpus=GPU)
acs.run_sampling_TS(tsparams, gpus=GPU, perc=0.5)
#acs.run_sampling_dhl(dhparams, gpus=GPU+GPU)
#acs.run_sampling_TS(tsparams, gpus=GPU)
#exit(0)
## Submit jobs, return and pack data
ast.generateQMdata(hostname, username, swkdir, ldtdir,
datdir + str(i + 1).zfill(2), h5stor, mae, jtime)
except FileExistsError:
pass
try:
os.mkdir(new_datdir)
except FileExistsError:
pass
netdict = {
'iptfile': iptfile_path,
'cnstfile': cstfile_path,
'saefile': saefile_path,
'nnfprefix': nnfprefix,
'aevsize': aevsize,
'num_nets': Nnets,
'atomtyp': ['H', 'C', 'N', 'O']
}
# Train the ensemble
ani_ensemble_trainer = alt.alaniensembletrainer(netdir, netdict,
h5dataset_path, Nnets)
ani_ensemble_trainer.build_strided_training_cache(Nblock, Nbvald, Nbtest,
False)
ani_ensemble_trainer.train_ensemble(GPU)
local_data_dir = root_dir
# Run active learning sampling
ani_conformational_sampler = alt.alconformationalsampler(
local_data_dir, dat, optlfile_path, fpatoms, netdict)
ani_conformational_sampler.run_sampling_dhl(dhparams, gpus=GPU + GPU)
# Submit jobs, return and pack data
aniserver.generateQMdata(hostname, username, swkdir, local_data_dir, dat,
h5dataset_path, mae, jtime)
