use_gpu(1)
e = 0.01
lr = 0.8
drop_rate = 0.
batch_size = 20
hidden_size = [100, 100]
input_size = 9235
output_size = 104
# try: gru, lstm
cell = "gru"
# try: sgd, momentum, rmsprop, adagrad, adadelta, adam
optimizer = "adadelta"
seqs, i2w, w2i, data_xy, existing_annos = data.char_sequence("/gds/zhwang/zhwang/data/cuhk/11", batch_size, input_size, output_size)
#dim_x = len(w2i)
dim_x = input_size
dim_y = output_size
#dim_y = len(existing_annos)
print "#features = ", dim_x, "#labels = ", dim_y
print "compiling..."
model = RNN(dim_x, dim_y, hidden_size, cell, optimizer, drop_rate)
print "training..."
start = time.time()
g_error = 9999.9999
for i in xrange(100):
error = 0.0
#pylint: skip-file
import time
import sys
import numpy as np
import theano
import theano.tensor as T
from utils_pg import *
from rnn import *
use_gpu(0)
import data
drop_rate = 0.
batch_size = 20
seqs, i2w, w2i, data_xy = data.char_sequence("/data/toy.txt", batch_size)
hidden_size = [100, 100]
dim_x = len(w2i)
dim_y = len(w2i)
print dim_x, dim_y
cell = "gru" # cell = "gru" or "lstm"
optimizer = "adadelta"
print "building..."
model = RNN(dim_x, dim_y, hidden_size, cell, optimizer, drop_rate)
model = load_model("./model/char_rnn.model", model)
num_x = 0.0
acc = 0.0
for s in xrange(len(seqs)):
seq = seqs[s]
use_gpu(1)
e = 0.01
lr = 0.8
drop_rate = 0.
batch_size = 20
hidden_size = [100, 100]
input_size = 9235
output_size = 104
# try: gru, lstm
cell = "gru"
# try: sgd, momentum, rmsprop, adagrad, adadelta, adam
optimizer = "adadelta"
seqs, i2w, w2i, data_xy, existing_annos = data.char_sequence(
"/gds/zhwang/zhwang/data/cuhk/11", batch_size, input_size, output_size)
#dim_x = len(w2i)
dim_x = input_size
dim_y = output_size
#dim_y = len(existing_annos)
print "#features = ", dim_x, "#labels = ", dim_y
print "compiling..."
model = RNN(dim_x, dim_y, hidden_size, cell, optimizer, drop_rate)
print "training..."
start = time.time()
g_error = 9999.9999
for i in xrange(100):
error = 0.0
from rnn import *
import data
#use_gpu(0)
e = 0.01
lr = 4.0
drop_rate = 0.
batch_size = 128
hidden_size = [256]
# try: gru, lstm
cell = "lstm"
# try: sgd, momentum, rmsprop, adagrad, adadelta, adam, nesterov_momentum
optimizer = "sgd"
seqs, i2w, w2i, data_xy = data.char_sequence("../../data/19.txt", batch_size)
dim_x = len(w2i)
dim_y = len(w2i)
print "#features = ", dim_x, "#labels = ", dim_y
XX = theano.shared(np.asarray(data_xy[0]))
YY = theano.shared(np.asarray(data_xy[1]))
batch_l = data_xy[2]
print "compiling..."
model = RNN(dim_x, dim_y, hidden_size, XX, YY, cell, optimizer)
print "training..."
start = time.time()
g_error = 9999.9999
count = 0
for i in xrange(1):
from rnn import *
import data
use_gpu(0)
e = 0.01
lr = 0.2
drop_rate = 0.
batch_size = 20
hidden_size = [100, 100]
# try: gru, lstm
cell = "gru"
# try: sgd, momentum, rmsprop, adagrad, adadelta, adam, nesterov_momentum
optimizer = "nesterov_momentum"
seqs, i2w, w2i, data_xy = data.char_sequence("/data/toy.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)
print "training..."
start = time.time()
g_error = 9999.9999
for i in xrange(200):
error = 0.0
in_start = time.time()
for batch_id, xy in data_xy.items():
X = xy[0]
local_rnn = False # true: lstm.py; false: nn.LSTM
lr = 1
drop_rate = 0.
batch_size = 128
hidden_size = 500
emb_size = 300
cell = "lstm"
use_cuda = use_gpu and torch.cuda.is_available()
device = torch.device("cuda" if use_cuda else "cpu")
dtype = torch.FloatTensor
xy_list, i2w, w2i, batch_list = data.char_sequence("/data/shakespeare.txt",
batch_size)
dict_size = len(w2i)
num_batches = len(batch_list)
print "dict_size=", dict_size, "#batchs=", num_batches, "#batch_size", batch_size
print "compiling..."
model = RNN(dict_size, hidden_size, batch_size, emb_size, dict_size, local_rnn,
cell)
optimizer = torch.optim.Adadelta(model.parameters(), lr=lr)
weight = torch.ones(dict_size)
weight[0] = 0.0
if use_cuda:
model.cuda()
weight = weight.cuda()
criterion = nn.CrossEntropyLoss(weight)
import time
import sys
import numpy as np
import theano
import theano.tensor as T
from utils import *
from rnn import *
import data
import jieba
reload(sys)
sys.setdefaultencoding('utf8')
theano.config.optimizer = "fast_compile"
theano.config.exception_verbosity = "high"
seqs, i2w, w2i, data_xy = data.char_sequence("./data/computer.txt")
e = 0.01
lr = 0.1
drop_rate = 0.3
batch_size = 1
hidden_size = [400, 400]
dim_x = len(w2i)
dim_y = len(w2i)
print dim_x, dim_y
cell = "gru"
print "building..."
model = RNN(dim_x, dim_y, hidden_size, cell, drop_rate) # cell = "gru" or "lstm"
use_gpu = True
lr = 1
drop_rate = 0.
batch_size = 3
hidden_size = 100
emb_size = 200
cell = "lstm"
use_cuda = use_gpu and torch.cuda.is_available()
device = torch.device("cuda" if use_cuda else "cpu")
dtype = torch.FloatTensor
xy_list, i2w, w2i, batch_list = data.char_sequence("/data/toy.txt", batch_size)
dict_size = len(w2i)
num_batches = len(batch_list)
print "dict_size=", dict_size, "#batchs=", num_batches, "#batch_size", batch_size
print "compiling..."
model = RNN(dict_size, hidden_size, batch_size, emb_size, dict_size, cell)
optimizer = torch.optim.Adadelta(model.parameters(), lr=lr)
criterion = nn.CrossEntropyLoss()
if use_cuda:
model.cuda()
#def train(x, y):
print "training..."
start = time.time()
