def main(model,
dictionary_target,
source_fea,
source_latex,
saveto,
wer_file,
k=5):
# load model model_options
with open('%s.pkl' % model, 'rb') as f:
options = pkl.load(f)
# load source dictionary and invert
worddicts = load_dict(dictionary_target)
worddicts_r = [None] * len(worddicts)
for kk, vv in worddicts.iteritems():
worddicts_r[vv] = kk
valid, valid_uid_list = dataIterator_valid(source_fea,
source_latex,
worddicts,
batch_size=1,
maxlen=2000)
trng = RandomStreams(1234)
params = init_params(options)
params = load_params(model, params)
tparams = init_tparams(params)
f_init, f_next = build_sampler(tparams, options, trng)
fpp_sample = open(saveto, 'w')
valid_count_idx = 0
print 'Decoding...'
ud_epoch = 0
ud_epoch_start = time.time()
for x, y in valid:
for xx in x:
print '%d : %s' % (valid_count_idx + 1,
valid_uid_list[valid_count_idx])
xx_pad = numpy.zeros((xx.shape[0] + 1, xx.shape[1]),
dtype='float32')
xx_pad[:xx.shape[0], :] = xx
stochastic = False
sample, score = gen_sample(f_init,
f_next,
xx_pad[:, None, :],
options,
trng=trng,
k=k,
maxlen=1000,
stochastic=stochastic,
argmax=False)
if stochastic:
ss = sample
else:
score = score / numpy.array([len(s) for s in sample])
ss = sample[score.argmin()]
fpp_sample.write(valid_uid_list[valid_count_idx])
valid_count_idx = valid_count_idx + 1
for vv in ss:
if vv == 0: # <eol>
break
fpp_sample.write(' ' + worddicts_r[vv])
fpp_sample.write('\n')
fpp_sample.close()
ud_epoch = (time.time() - ud_epoch_start) / 60.
print 'test set decode done, cost time ...', ud_epoch
os.system('python compute-wer.py ' + saveto + ' ' + source_latex + ' ' +
wer_file)
fpp = open(wer_file)
stuff = fpp.readlines()
fpp.close()
m = re.search('WER (.*)\n', stuff[0])
valid_per = 100. * float(m.group(1))
m = re.search('ExpRate (.*)\n', stuff[1])
valid_sacc = 100. * float(m.group(1))
print 'Valid WER: %.2f%%, ExpRate: %.2f%%' % (valid_per, valid_sacc)
def main(model, bn_model, dictionary_target, fea, latex, saveto, output, k=5):
# load model model_options
with open('%s.pkl' % model, 'rb') as f:
options = pkl.load(f)
# load source dictionary and invert
worddicts = load_dict(dictionary_target)
worddicts_r = [None] * len(worddicts)
for kk, vv in worddicts.iteritems():
worddicts_r[vv] = kk
valid, valid_uid_list = dataIterator(fea,
latex,
worddicts,
batch_size=1,
batch_Imagesize=500000,
maxlen=500,
maxImagesize=500000)
trng = RandomStreams(1234)
use_noise = theano.shared(numpy.float32(0.))
# allocate model parameters
params = init_params(options)
bn_params = init_bn_params(options)
# load model parameters and set theano shared variables
params = load_params(model, params)
bn_params = load_params(bn_model, bn_params)
tparams = init_tparams(params)
bn_tparams = init_tparams(bn_params)
f_init, f_next = build_sampler(tparams, bn_tparams, options, trng,
use_noise)
use_noise.set_value(0.)
fpp_sample = open(saveto, 'w')
valid_count_idx = 0
# FIXME: random selection?
print 'Decoding ... '
for x, y in valid:
for xx in x:
print '%d : %s' % (valid_count_idx + 1,
valid_uid_list[valid_count_idx])
xx_pad = numpy.zeros(
(xx.shape[0], xx.shape[1], xx.shape[2]),
dtype='float32') # input_channels * height * width
xx_pad[:, :, :] = xx / 255.
stochastic = False
sample, score = gen_sample(f_init,
f_next,
xx_pad[None, :, :, :],
options,
trng=trng,
k=10,
maxlen=1000,
stochastic=stochastic,
argmax=False)
if stochastic:
ss = sample
else:
score = score / numpy.array([len(s) for s in sample])
ss = sample[score.argmin()]
fpp_sample.write(valid_uid_list[valid_count_idx])
valid_count_idx = valid_count_idx + 1
for vv in ss:
if vv == 0: # <eol>
break
fpp_sample.write(' ' + worddicts_r[vv])
fpp_sample.write('\n')
fpp_sample.close()
print 'test set decode done'
os.system('python compute-wer.py ' + saveto + ' ' + latex + ' ' + output)
fpp = open(output) # %WER 31.63
stuff = fpp.readlines()
fpp.close()
m = re.search('WER (.*)\n', stuff[0])
valid_per = 100. * float(m.group(1))
m = re.search('ExpRate (.*)\n', stuff[1])
valid_sacc = 100. * float(m.group(1))
print 'Valid WER: %.2f%%, ExpRate: %.2f%%' % (valid_per, valid_sacc)
def main(model_files, dictionary_target, grammar_target, data_path, saveto, wer_file, k=5):
# load source dictionary and invert
worddicts = load_dict(dictionary_target)
worddicts_r = [None] * len(worddicts)
for kk, vv in worddicts.items():
worddicts_r[vv] = kk
grammar=compileGrammar(loadGrammar(grammar_target,worddicts))
trng = RandomStreams(1234)
models=[]
# load model model_options
for model_file in model_files:
print('Loading model: %s' % model_file)
with open('%s.pkl' % model_file, 'rb') as f:
options = pkl.load(f)
print(options)
params = init_params(options)
params = load_params(model_file, params)
tparams = init_tparams(params)
f_init, f_next = build_sampler(tparams, options, trng)
models.append((f_init,f_next,options,0.8))
for lm_file in []:
print('Loading language model: %s' % lm_file)
f_init,f_next,options=load_language_model(lm_file)
models.append((f_init,f_next,options,0.2))
valid,valid_uid_list = dataIterator_valid(data_path,
worddicts, batch_size=1, maxlen=250)
fpp_sample=[open('%s.%d'%(saveto,beam),'w') for beam in range(k)]
valid_count_idx=0
print('Decoding...')
ud_epoch = 0
ud_epoch_start = time.time()
for x,y in valid:
for xx in x:
print('%d : %s' % (valid_count_idx+1, valid_uid_list[valid_count_idx]))
xx_pad = numpy.zeros((xx.shape[0]+1,xx.shape[1]), dtype='float32')
xx_pad[:xx.shape[0],:] = xx
stochastic = False
sample, score = gen_sample(models,
xx_pad[:, None, :],
grammar,
trng=trng, k=k,
maxlen=250,
dictlen=len(worddicts),
stochastic=stochastic,
argmax=False)
score = score / numpy.array([len(s) for s in sample])
sample_rank=numpy.argsort(score)
for beam in range(k):
fpp_sample[beam].write(valid_uid_list[valid_count_idx])
if len(sample)>beam:
ss=sample[sample_rank[beam]]
else:
ss=[0]
for vv in ss:
if vv == 0: # <eol>
break
fpp_sample[beam].write(' '+worddicts_r[vv])
fpp_sample[beam].write('\n')
valid_count_idx=valid_count_idx+1
ud_epoch = (time.time() - ud_epoch_start)
print 'test set decode done, cost time ...', ud_epoch
for beam in range(k):
fpp_sample[beam].flush();
fpp_sample[beam].close();
os.system('python compute-wer.py %s.%d %s %s'%(saveto,beam,os.path.join(data_path,"caption.txt"),wer_file))
fpp=open(wer_file)
stuff=fpp.readlines()
fpp.close()
m=re.search('WER (.*)\n',stuff[0])
valid_per=100. * float(m.group(1))
m=re.search('ExpRate (.*)\n',stuff[1])
valid_sacc=100. * float(m.group(1))
print '%d Valid WER: %.2f%%, ExpRate: %.2f%%' % (beam,valid_per,valid_sacc)