def main():
args = get_args()
setup_logger(args)
dset = Dset(**args)
feat = featchar.Feat(args['feat'])
feat.fit(dset)
batcher = Batcher(args['n_batch'], feat)
reporter = Reporter(dset, feat)
validator = Validator(dset, batcher, reporter)
RNN = RDNN_Dummy if args['rnn'] == 'dummy' else RDNN
rdnn = RNN(feat.NC, feat.NF, args)
if not args['load'] == '':
dat = np.load(args['load'])
dat_args = dat['argsd'].tolist()
rnn_param_values = dat['rnn_param_values']
params = lasagne.layers.get_all_params(rdnn.layers[-1])
lasagne.layers.set_all_param_values(rdnn.layers[-1],
rnn_param_values[:len(params)])
logger = logging.getLogger()
logger.info('Parameters loaded')
validator.validate(rdnn, args)
def main():
args = get_args()
setup_logger(args)
logging.info('loading params')
dat = np.load(args['model_file'])
dat_args = dat['argsd'].tolist()
rnn_param_values = dat['rnn_param_values'].tolist()
logging.info('params loaded')
dat_args['fepoch'] = args['fepoch'] # TODO
dat_args['save'] = args['save'] # TODO
for k,v in sorted(dat_args.iteritems()):
logging.info('{}:\t{}'.format(k,v))
dset = Dset(**args)
feat = featchar.Feat(dat_args['feat'])
feat.fit(dset, xdsets=[Dset(dname) for dname in dat_args['charset']])
batcher = Batcher(dat_args['n_batch'], feat)
reporter = Reporter(dset, feat)
validator = Validator(dset, batcher, reporter)
rdnn = RDNN(feat.NC, feat.NF, dat_args)
params = lasagne.layers.get_all_params(rdnn.layers[-1])
lasagne.layers.set_all_param_values(rdnn.layers[-1], rnn_param_values[:len(params)])
validator.validate(rdnn, dat_args)
def __init__(self, model_file):
dat = np.load(model_file)
args = dat['argsd'].tolist()
rnn_param_values = dat['rnn_param_values'].tolist()
trn, dev, tst = get_sents(args['lang'])
repclass = getattr(rep, 'Rep' + args['rep'])
repobj = repclass()
for d in (trn, dev, tst):
for sent in d:
sent.update({
'cseq': repobj.get_cseq(sent),
'wiseq': repobj.get_wiseq(sent),
'tseq': repobj.get_tseq(sent)
})
trn = sorted(trn, key=lambda sent: len(sent['cseq']))
dev = sorted(dev, key=lambda sent: len(sent['cseq']))
tst = sorted(tst, key=lambda sent: len(sent['cseq']))
self.feat = featchar.Feat(args['feat'])
self.feat.fit(trn, dev, tst)
self.vdecoder = decoder.ViterbiDecoder(trn, self.feat)
batcher = Batcher(args['n_batch'], self.feat) # batch size 1
devdat = batcher.get_batches(dev)
tstdat = batcher.get_batches(tst)
rdnn = RNN(self.feat.NC, self.feat.NF, args)
cost, dev_predictions = rdnn.predict(devdat)
cost, tst_predictions = rdnn.predict(tstdat)
self.predictions = {}
self.predictions['dev'] = dev_predictions
self.predictions['tst'] = tst_predictions
self.dset = {}
self.dset['dev'] = dev
self.dset['tst'] = tst
self.repobj = repobj
self.reporter = exper.Reporter(self.feat, rep.get_ts_bio)
print rdnn.l_soft_out.get_params()
print rdnn.blayers[0][0].get_params()
params = lasagne.layers.get_all_param_values(rdnn.layers[-1])
print map(np.shape, params)
lasagne.layers.set_all_param_values(rdnn.layers[-1],
rnn_param_values[:len(params)])
logger = logging.getLogger()
logger.setLevel(logging.INFO)
shandler = logging.StreamHandler()
shandler.setLevel(logging.INFO)
logger.addHandler(shandler)
validator = Validator(trn, dev, tst, batcher, self.reporter)
validator.validate(rdnn, args, self.vdecoder)
def main():
from utils import get_sents
from dataset import Dset
import featchar, rep
trn, dev, tst = get_sents('toy')
dset = Dset('toy')
r = rep.Repstd()
for sent in trn:
sent.update({
'cseq': r.get_cseq(sent),
'wiseq': r.get_wiseq(sent),
'tseq': r.get_tseq(sent)
})
r.pprint(trn[0])
print
r.pprint(trn[1])
print rep.get_ts_bio(trn[0]['wiseq'], trn[0]['tseq'])
feat = featchar.Feat('basic')
feat.fit(dset)
vdecoder = ViterbiDecoder(trn, feat)
vdecoder.pprint()
sent = trn[0]
vdecoder.decode(sent, randlogprob(sent, feat.NC), debug=True)
"""
def main(args, rnn_param_values):
# args = get_args()
setup_logger(args)
try:
if args['seed']:
rng = np.random.RandomState(args['seed'])
lasagne.random.set_rng(rng)
dset = Dset(**args)
feat = featchar.Feat(args['feat'])
feat.fit(dset, xdsets=[Dset(dname) for dname in args['charset']])
batcher = Batcher(args['n_batch'], feat)
reporter = Reporter(dset, feat)
validator = Validator(dset, batcher, reporter)
RNN = RDNN_Dummy if args['rnn'] == 'dummy' else RDNN
rdnn = RNN(feat.NC, feat.NF, args)
rdnn.set_param_values(rnn_param_values)
validator.validate(rdnn, args)
except Exception as e:
print e
logging.exception('an error occured.')
def main():
args = get_args()
setup_logger(args)
dset = Dset(**args)
feat = featchar.Feat(args['feat'])
feat.fit(dset)
batcher = Batcher(args['n_batch'], feat)
reporter = Reporter(dset, feat)
validator = Validator(dset, batcher, reporter)
RNN = RDNN_Dummy if args['rnn'] == 'dummy' else RDNN
rdnn = RNN(feat.NC, feat.NF, args)
validator.validate(rdnn, args)
