def train(model, data, words, params):
start_time = time.time()
counter = 0
try:
for eidx in xrange(params.epochs):
kf = utils.get_minibatches_idx(len(data), params.batchsize, shuffle=True)
uidx = 0
for _, train_index in kf:
uidx += 1
batch = [data[t] for t in train_index]
for i in batch:
i[0].populate_embeddings(words)
i[1].populate_embeddings(words)
(g1x, g1mask, g2x, g2mask, p1x, p1mask, p2x, p2mask) = getpairs(model, batch, params)
cost = model.train_function(g1x, g2x, p1x, p2x, g1mask, g2mask, p1mask, p2mask)
if np.isnan(cost) or np.isinf(cost):
print 'NaN detected'
if (utils.checkIfQuarter(uidx, len(kf))):
if (params.save):
counter += 1
utils.saveParams(model, params.outfile + str(counter) + '.pickle')
if (params.evaluate):
evaluate_all(model, words)
sys.stdout.flush()
#undo batch to save RAM
for i in batch:
i[0].representation = None
i[1].representation = None
i[0].unpopulate_embeddings()
i[1].unpopulate_embeddings()
#print 'Epoch ', (eidx+1), 'Update ', (uidx+1), 'Cost ', cost
if (params.save):
counter += 1
utils.saveParams(model, params.outfile + str(counter) + '.pickle')
if (params.evaluate):
evaluate_all(model, words)
print 'Epoch ', (eidx + 1), 'Cost ', cost
except KeyboardInterrupt:
print "Training interupted"
end_time = time.time()
print "total time:", (end_time - start_time)
def train(model, data, words, params):
start_time = time.time()
counter = 0
try:
for eidx in xrange(params.epochs):
kf = utils.get_minibatches_idx(len(data), params.batchsize, shuffle=True)
uidx = 0
for _, train_index in kf:
uidx += 1
batch = [data[t] for t in train_index]
for i in batch:
i[0].populate_embeddings(words)
i[1].populate_embeddings(words)
(g1x, g1mask, g2x, g2mask, p1x, p1mask, p2x, p2mask) = getpairs(model, batch, params)
cost = model.train_function(g1x, g2x, p1x, p2x, g1mask, g2mask, p1mask, p2mask)
if np.isnan(cost) or np.isinf(cost):
print 'NaN detected'
if (utils.checkIfQuarter(uidx, len(kf))):
if (params.save):
counter += 1
utils.saveParams(model, params.outfile + str(counter) + '.pickle')
if (params.evaluate):
evaluate_all(model, words)
sys.stdout.flush()
# undo batch to save RAM
for i in batch:
i[0].representation = None
i[1].representation = None
i[0].unpopulate_embeddings()
i[1].unpopulate_embeddings()
# print 'Epoch ', (eidx+1), 'Update ', (uidx+1), 'Cost ', cost
if (params.save):
counter += 1
utils.saveParams(model, params.outfile + str(counter) + '.pickle')
if (params.evaluate):
evaluate_all(model, words)
print 'Epoch ', (eidx + 1), 'Cost ', cost
except KeyboardInterrupt:
print "Training interupted"
end_time = time.time()
print "total time:", (end_time - start_time)
def train(model, data, words, params):
start_time = time.time()
counter = 0
pre_ss = 0
try:
for eidx in xrange(params.epochs):
#10 cross validation
#nc = len(data)/10
#test_nn = range((eidx%10)*nc, ((eidx%10)+1)*nc)
#train_nn = list(set(xrange(len(data)))-set(test_nn))
#test = [data[i] for i in test_nn]
#data = [data[i] for i in train_nn]
kf = utils.get_minibatches_idx(len(data),
params.batchsize,
shuffle=True)
uidx = 0
for _, train_index in kf:
uidx += 1
batch = [data[t] for t in train_index]
for i in batch:
i[0].populate_embeddings(words)
i[1].populate_embeddings(words)
(g1x, g2x, p1x, p2x) = utils.getpairs(model, batch, params)
cost = model.train_function(g1x, g2x, p1x, p2x)
if np.isnan(cost) or np.isinf(cost):
print 'NaN detected'
#if (utils.checkIfQuarter(uidx, len(kf))):
# ss = utils.evaluate(model, words, test)
# if (params.save) and ss > pre_ss:
# counter += 1
# utils.saveParams(model, params.outfile + '.pickle')
# pre_ss = ss
# sys.stdout.flush()
# undo batch to save RAM
for i in batch:
i[0].representation = None
i[1].representation = None
i[0].unpopulate_embeddings()
i[1].unpopulate_embeddings()
# print 'Epoch ', (eidx+1), 'Update ', (uidx+1), 'Cost ', cost
#ss = utils.evaluate(model, words, test)
#if (params.save) and ss > pre_ss:
# counter += 1
# utils.saveParams(model, params.outfile + '.pickle')
# pre_ss = ss
utils.saveParams(model, params.outfile + str(eidx) + '.pickle')
print 'Epoch ', (eidx + 1), 'Cost ', cost
except KeyboardInterrupt:
print "Training interupted"
end_time = time.time()
print "total time:", (end_time - start_time)