# batch train
start = time.time()
for i in xrange(100):
acc = 0.0
in_start = time.time()
# for s in xrange(len(seqs)):
# seq = seqs[s]
# X = seq[0 : len(seq) - 1, ]
# Y = seq[1 : len(seq), ]
# model.batch_train(X, Y, lr)
# in_time = time.time() - in_start
for batch_id, xy in data_xy.items():
# print xy[0]
X, Y, zero_m, seqs_len = data.index2seqs(seqs, xy[0], w2i)
print len(X), len(Y)
concat_X = np.zeros((seqs_len, len(X) * len(w2i)), dtype=theano.config.floatX)
concat_Y = concat_X.copy()
for b_i in xrange(len(X)):
iX = X[b_i]
iY = Y[b_i]
for r in xrange(seqs_len - iX.shape[0]):
iX = np.concatenate((iX, zero_m), axis=0)
iY = np.concatenate((iY, zero_m), axis=0)
model.batch_train(iX, iY, lr)
# print X, Y
# model.batch_train(X, Y, lr)
seqs, i2w, w2i, data_xy = data.load_hlm("/data/hlm/hlm.txt", batch_size)
dim_x = len(w2i)
dim_y = len(w2i)
print "#features = ", dim_x, "#labels = ", dim_y
print "compiling..."
model = RNN(dim_x, dim_y, hidden_size, cell, optimizer, drop_rate)
#model = load_model("./model/rnn_hlm.model", model)
print "training..."
start = time.time()
g_error = 9999.9999
for i in xrange(100):
error = 0.0
in_start = time.time()
for batch_id, xy in data_xy.items():
X, Y, mask, local_batch_size = data.index2seqs(seqs, xy[0], w2i)
cost = model.train(X, mask, Y, lr, local_batch_size)[0]
error += cost
print i, g_error, batch_id, "/", len(data_xy), cost
in_time = time.time() - in_start
error /= len(seqs);
if error < g_error:
g_error = error
save_model("./model/rnn_hlm.model_" + str(i), model)
print "Iter = " + str(i) + ", Error = " + str(error) + ", Time = " + str(in_time)
if error <= e:
break
print "Finished. Time = " + str(time.time() - start)
