rnd = random.random()
for i,p in enumerate(dist):
rnd -= p
if rnd <= 0: break
res.append(i)
cw = i
if cw == stop: break
if nchars and len(res) > nchars: break
return res
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('corpus', help='Path to the corpus file.')
args = parser.parse_args()
train = util.CharsCorpusReader(args.corpus, begin="<s>")
vocab = util.Vocab.from_corpus(train)
VOCAB_SIZE = vocab.size()
model = Model()
trainer = SimpleSGDTrainer(model)
#lm = RNNLanguageModel(model, LAYERS, INPUT_DIM, HIDDEN_DIM, VOCAB_SIZE, builder=SimpleRNNBuilder)
lm = RNNLanguageModel(model, LAYERS, INPUT_DIM, HIDDEN_DIM, VOCAB_SIZE, builder=LSTMBuilder)
train = list(train)
chars = loss = 0.0
for ITER in range(100):
random.shuffle(train)
r_t = bias + (R * y_t)
ydist = softmax(r_t)
dist = ydist.vec_value()
rnd = random.random()
for i, p in enumerate(dist):
rnd -= p
if rnd <= 0: break
res.append(i)
cw = i
if cw == stop: break
if nchars and len(res) > nchars: break
return res
if __name__ == '__main__':
train = util.CharsCorpusReader(sys.argv[1], begin="<s>")
vocab = util.Vocab.from_corpus(train)
VOCAB_SIZE = vocab.size()
model = Model()
sgd = SimpleSGDTrainer(model)
#lm = RNNLanguageModel(model, builder=LSTMBuilder)
lm = RNNLanguageModel(model,
LAYERS,
INPUT_DIM,
HIDDEN_DIM,
VOCAB_SIZE,
builder=SimpleRNNBuilder)
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('train', help='Path to the corpus file.')
parser.add_argument('dev', help='Path to the validation corpus file.')
parser.add_argument('test', help='Path to the test corpus file.')
parser.add_argument(
'--print_probs',
action="store_true",
help=
'whether to print the probabilities per word over the validation set')
parser.add_argument('--perform_train',
action="store_true",
help='whether to perform training')
args, unknown = parser.parse_known_args()
train = util.CharsCorpusReader(args.train, begin="<s>")
dev = util.CharsCorpusReader(args.dev, begin="<s>")
test = util.CharsCorpusReader(args.test, begin="<s>")
vocab = util.Vocab.from_corpus(train)
VOCAB_SIZE = vocab.size()
model = dy.Model()
trainer = dy.SimpleSGDTrainer(model, learning_rate=1.0)
lm = RNNLanguageModel(model,
LAYERS,
INPUT_DIM,
HIDDEN_DIM,
VOCAB_SIZE,
