def main(_):
"""
Start either train or eval. Note hardcoded parts of path for training and eval data
"""
hps = LM.get_default_hparams().parse(FLAGS.hpconfig)
hps._set("num_gpus", FLAGS.num_gpus)
print('*****HYPER PARAMETERS*****')
print(hps)
print('**************************')
print_debug('our training DataSetDir=%s , LogDir=%s' %
(FLAGS.datadir, FLAGS.logdir))
#vocab = Vocabulary.from_file(os.path.join(FLAGS.datadir, "1b_word_vocab.txt"))
vocab = Vocabulary.from_file(os.path.join(FLAGS.datadir, "vocabulary.txt"))
FLAGS.mode = "train"
for i in range(10):
print("Iteration ", i, " phase: ", FLAGS.mode)
if FLAGS.mode == "train":
#hps.batch_size = 256
# dataset = Dataset(vocab, os.path.join(FLAGS.datadir,
# "training-monolingual.tokenized.shuffled/*"))
dataset = Dataset(vocab,
os.path.join(FLAGS.datadir, "ptb.train.txt"))
trainlogdir = (
FLAGS.logdir + str("/") + "train"
) #(FLAGS.logdir+str("\\")+"train")#os.path.join(FLAGS.logdir, "train")
print_debug('train log dir=%s' % (trainlogdir))
run_train(dataset, hps, trainlogdir, ps_device="/gpu:0")
print_debug('Finished run_train !!!!!!!!!!!')
elif FLAGS.mode.startswith("eval"):
print_debug('eval mode')
# if FLAGS.mode.startswith("eval_train"):
# data_dir = os.path.join(FLAGS.datadir, "training-monolingual.tokenized.shuffled/*")
# elif FLAGS.mode.startswith("eval_full"):
# data_dir = os.path.join(FLAGS.datadir, "heldout-monolingual.tokenized.shuffled/*")
# else:
# data_dir = os.path.join(FLAGS.datadir, "heldout-monolingual.tokenized.shuffled/news.en.heldout-00000-of-00050")
dataset = Dataset(vocab,
os.path.join(FLAGS.datadir, "ptb.test.txt"),
deterministic=True)
run_eval(dataset, hps, FLAGS.logdir, FLAGS.mode, FLAGS.eval_steps)
print_debug('Finished run_eval !!!!!!!!!!!')
if FLAGS.mode == "train":
FLAGS.mode = "eval_full"
else:
FLAGS.mode = "train"
def main(_):
hps = Sentiment.get_default_hparams().parse(FLAGS.hpconfig)
vocab = Vocabulary.from_file( os.path.join(FLAGS.data_dir, "sent.vocab.freq.dict"))
if FLAGS.mode == "train":
dataset = Dataset(os.path.join(FLAGS.data_dir, "train.sent_data.txt"), vocab)
run_train(dataset, ## dataset
hps, ## configurations
FLAGS.log_dir + "/train") ## loging dir
elif FLAGS.mode.startswith("eval"):
dataset = Dataset(os.path.join(FLAGS.data_dir, "test.sent_data.txt"), vocab)
run_eval(dataset, ## dataset
hps, ## configurations
FLAGS.log_dir) ## loging dir
def main(_):
hps = LM.get_default_hparams().parse(FLAGS.hpconfig)
hps.num_gpus = FLAGS.num_gpus
vocab = Vocabulary.from_file("1b_word_vocab.txt")
if FLAGS.mode == "train":
hps.batch_size = 256
dataset = Dataset(vocab, FLAGS.datadir + "/training-monolingual.tokenized.shuffled/*")
run_train(dataset, hps, FLAGS.logdir + "/train", ps_device="/gpu:0")
elif FLAGS.mode.startswith("eval_"):
if FLAGS.mode.startswith("eval_train"):
data_dir = FLAGS.datadir + "/training-monolingual.tokenized.shuffled/*"
else:
data_dir = FLAGS.datadir + "/heldout-monolingual.tokenized.shuffled/news.en.heldout-00000-of-00050"
dataset = Dataset(vocab, data_dir, deterministic=True)
run_eval(dataset, hps, FLAGS.logdir, FLAGS.mode, FLAGS.eval_steps)
def main(_):
"""
Start either train or eval. Note hardcoded parts of path for training and eval data
"""
hps = LM.get_default_hparams().parse(FLAGS.hpconfig)
hps._set("num_gpus", FLAGS.num_gpus)
print('*****HYPER PARAMETERS*****')
print(hps)
print('**************************')
vocab = Vocabulary.from_file(
os.path.join(FLAGS.datadir, "1b_word_vocab.txt"))
if FLAGS.mode == "train":
#hps.batch_size = 256
dataset = Dataset(
vocab,
os.path.join(FLAGS.datadir,
"training-monolingual.tokenized.shuffled/*"))
run_train(dataset,
hps,
os.path.join(FLAGS.logdir, "train"),
ps_device="/gpu:0")
elif FLAGS.mode.startswith("eval_"):
if FLAGS.mode.startswith("eval_train"):
data_dir = os.path.join(
FLAGS.datadir, "training-monolingual.tokenized.shuffled/*")
elif FLAGS.mode.startswith("eval_full"):
data_dir = os.path.join(
FLAGS.datadir,
"heldout-monolingual.tokenized.shuffled/news.en.heldout-00000-of-00050"
)
else:
data_dir = os.path.join(
FLAGS.datadir,
"heldout-monolingual.tokenized.shuffled/news.en.heldout-00000-of-00050"
)
dataset = Dataset(vocab, data_dir, deterministic=True)
run_eval(dataset, hps, FLAGS.logdir, FLAGS.mode, FLAGS.eval_steps)
elif FLAGS.mode.startswith("infer"):
data_dir = os.path.join(
FLAGS.datadir,
"heldout-monolingual.tokenized.shuffled/news.en.heldout-00000-of-00050"
)
dataset = Dataset(vocab, data_dir, deterministic=True)
run_infer(dataset, hps, FLAGS.logdir, FLAGS.mode, vocab)
def main(_):
hps = LM.get_default_hparams().parse(FLAGS.hpconfig)
hps.num_gpus = FLAGS.num_gpus
vocab = Vocabulary.from_file(FLAGS.datadir + "/lm_vocab.txt", hps.vocab_size)
if FLAGS.mode == "train":
hps.batch_size = 256 # reset batchsize
dataset = Dataset(vocab, FLAGS.datadir + "/train/*")
run_train(dataset, hps, FLAGS.logdir + "/train", ps_device="/gpu:0")
elif FLAGS.mode.startswith("eval_"):
if FLAGS.mode.startswith("eval_train"):
data_dir = FLAGS.datadir + "/train/*"
elif FLAGS.mode.startswith("eval_test"):
data_dir = FLAGS.datadir + "/heldout/*"
print("data_dir:",data_dir)
dataset = Dataset(vocab, data_dir, deterministic=True)
run_eval(dataset, hps, FLAGS.logdir, FLAGS.mode, FLAGS.eval_steps)
elif FLAGS.mode.startswith("predict_next"):
data_dir = "data/news.en.heldout-00001-of-00050"
dataset = Dataset(vocab, data_dir)
predict_next(dataset, hps, FLAGS.logdir, FLAGS.mode, FLAGS.eval_steps,vocab)