def neuralnetpredict(pm, bs, nc, numd, seed, zz=0):
'''For the given box, mesh, numd, seed and redshift, do the neural network prediction
from the network saved in cfg file and return predict, nnpred, nnmass
'''
dpath = '/global/project/projectdirs/astro250/chmodi/cosmo4d/'
import yaml
import nettools as ntools
with open(dpath + 'train/models.yaml', 'r') as ymlfile:
cfg = yaml.load(ymlfile)
ptpath = dpath + 'train/' + cfg['%s-%s' %
(int(bs), int(nc))][0][numd]['ppath']
mtpath = ptpath + cfg['%s-%s' % (int(bs), int(nc))][0][numd]['mpath']
# mtpath = ptpath + cfg['%s-%s'%(bs,nc)][0][numd]['mpathnf']
ptup, pftname, plocal, pdict = ntools.setuppos2(ptpath)
mtup, mftname, mlocal, mdict = ntools.setupmass(mtpath)
R1, R2 = pdict['R1'], pdict['R2']
num = int(numd * bs**3)
meshdict, hdict = ntools.readfiles(
pm,
dpath + '/data/z%02d/L%04d_N%04d_S%04d_05step/' % (zz, bs, nc, seed),
R1=R1,
R2=R2,
mexp=None)
ftt = ntools.createdata(pm, meshdict, pdict['pftname'], plocal)
mftt = ntools.createdata(pm, meshdict, mftname, mlocal)
nnpred = ntools.applynet(ftt, ptup).reshape(nc, nc, nc)
nnmass = ntools.applynet(mftt, mtup).reshape(nc, nc, nc)
predict = nnpred * nnmass
##
return pm.create(mode='real', value=predict), nnpred, nnmass
sgs = [0.1, 0.20]
for seed in [100, 500, 900, 800]:
meshdict, dummy = ntools.readfiles(
pm,
scratch + '/data/L%04d_N%04d_S%04d_05step/' % (bs, nc, seed),
R1=R1,
R2=R2,
abund=abund,
doexp=doexp,
mexp=mexp,
cc=cc,
stellar=stellar)
ftt = ntools.createdata(pm, meshdict, pdict['pftname'], plocal)
mftt = ntools.createdata(pm, meshdict, mftname, mlocal)
nnpred = ntools.applynet(ftt, ptup).reshape(nc, nc, nc)
if regression:
nnmass = ntools.applymassreg(mftt, mtup).reshape(nc, nc, nc)
else:
nnmass = ntools.applynet(mftt, mtup).reshape(nc, nc, nc)
if doexp:
nnmass = mf.fmexp(ntools.relu(nnmass), mexp, cc)
predict = pm.create(mode='real')
predict[...] = nnpred * nnmass
predictR = ft.smooth(predict, Rsm, 'fingauss')
#data
hdictf = ntools.gridhalos(pm,
scratch + '/data/L%04d_N%04d_S%04d_40step/' %
(bs, fine * nc, seed),
sfac = pdict['sfac']
R2 = R1 * sfac
#model
print('Reading Files')
meshdict, dummy = ntools.readfiles(pm,
scratch +
'/data/z%02d/L%04d_N%04d_S%04d_05step/' %
(zz * 10, bs, nc, seed),
R1=R1,
R2=R2,
abund=abund)
ftt = ntools.createdata(pm, meshdict, pdict['pftname'], plocal)
mftt = ntools.createdata(pm, meshdict, mftname, mlocal)
nnpred = ntools.applynet(ftt, ptup).reshape(nc, nc, nc)
predict = pm.create(mode='real', value=nnpred)
predictR = ft.smooth(predict, Rsm, 'fingauss')
if ovd: predictR[...] = (predictR[...] - predictR.cmean()) / (predictR.cmean())
#data
print('Generating data')
hdictf = ntools.gridhalos(pm,
dpath=scratch +
'/data/z%02d/L%04d_N%04d_S%04d_40step/' %
(zz * 10, bs, sfine * nc, seed),
R1=R1,
R2=R2,
pmesh=False,
