def start_denotation(opts):
print "Loading data..."
# load training data
# trees, vocab = tr.loadTrees(opts.dataset,opts.data)
# chunked_lines = tr.get_chunked_lines(opts.dataset, opts.data)
opts.numWords = len(tr.loadWordMap(opts.dataset))
print "vocab size: %d" % opts.numWords
print "Loading word2vec vectors..."
# Load pre-built word matrix using cPickle
x = pickle.load(open("mr_%s.p" % opts.dataset, "rb"))
W = x[0]
rnn = nnet_rte.RNNRTE(opts.wvecDim, opts.outputDim, 200, opts.numWords, opts.minibatch)
rnn.initParams(W)
sgd = optimizer.SGD(rnn, alpha=opts.step, minibatch=opts.minibatch, optimizer=opts.optimizer)
for e in range(opts.epochs):
start = time.time()
print "Running epoch %d" % e
sgd.run_denotation(tr.get_lines(opts.dataset, opts.data))
end = time.time()
print "Time per epoch : %f" % (end - start)
with open(opts.outFile, "w") as fid:
pickle.dump(opts, fid)
pickle.dump(sgd.costt, fid)
# debug
if e == opts.epochs - 1:
rnn.toFile(fid, True)
else:
rnn.toFile(fid)
def test_denotation(netFile, data, dataset):
# trees, vocab = tr.loadTrees(dataset,data)
assert netFile is not None, "Must give model to test"
with open(netFile, "r") as fid:
opts = pickle.load(fid)
_ = pickle.load(fid)
x = pickle.load(open("mr_%s.p" % dataset, "rb"))
W = x[0]
W2 = 0.01 * np.random.randn(opts.wvecDim, opts.numWords)
rnn = nnet_rte.RNNRTE(opts.wvecDim, opts.outputDim, 200, opts.numWords, opts.minibatch)
rnn.initParams(W)
rnn.fromFile(fid)
lines = tr.get_lines(opts.dataset, opts.data)
m = len(lines)
CHUNK_SIZE = 10000
minibatch = opts.minibatch
print "Testing..."
cost = correct = total = 0
for i in xrange(0, m - CHUNK_SIZE + 1, CHUNK_SIZE):
# Get data as much as it's specified by minibatch num
# Load&parse trees beforehand
# Get data as much as it's specified by minibatch num
# Parse&load tree data beforehand
trees = list(tr.inputarray(lines[i : i + CHUNK_SIZE], dataset))
# map word indices to loaded trees
tr.map_words_to_trees(trees, dataset)
c, cor, tot = rnn.costAndGrad(trees, test=True)
cost += c
correct += cor
total += tot
if i % CHUNK_SIZE == 0:
print "tested: %d" % i
print "Cost %f, Correct %d/%d, Acc %f" % (cost, correct, total, correct / float(total))
def start(opts):
print "Loading data..."
# load training data
trees, vocab = tr.loadTrees(opts.dataset, opts.data) # sick, train_parsed
opts.numWords = len(tr.loadWordMap(opts.dataset))
print "Loading word2vec vectors..."
# Load pre-built word matrix using cPickle
# w2v_file = "/Users/pentiumx/Projects/word2vec/GoogleNews-vectors-negative300.bin"
# word_vecs = process_data.load_bin_vec(w2v_file, vocab)
# revs, W, W2, word_idx_map, vocab = x[0], x[1], x[2], x[3], x[4]
x = pickle.load(open("mr_%s.p" % opts.dataset, "rb"))
W = x[0]
W2 = 0.01 * np.random.randn(opts.wvecDim, opts.numWords)
# rnn = nnet.RNN(opts.wvecDim,opts.outputDim,opts.numWords,opts.minibatch)
# embeddingDim=200 for now
if opts.use_denotation == 0:
rnn = nnet_rte.RNNRTE(opts.wvecDim, opts.outputDim, 200, opts.numWords, opts.minibatch)
rnn.initParams(W) # Use W2 for experiments with randomly initialized vectors
sgd = optimizer.SGD(rnn, alpha=opts.step, minibatch=opts.minibatch, optimizer=opts.optimizer)
else:
"""with open('models/denotation_sample.bin','r') as fid:
_ = pickle.load(fid)# skip opts data
__ = pickle.load(fid)
x = pickle.load(open("mr_%s.p" % opts.dg_dataset, "rb"))
W_dg = x[0]
rnn = nnet_rte.RNNRTE(opts.wvecDim,opts.outputDim,200,opts.numWords,opts.minibatch)
rnn.initParams(W, W_dg)
rnn.from_file_denotation(fid)
sgd = optimizer.SGD(rnn,alpha=opts.step,minibatch=opts.minibatch,
optimizer=opts.optimizer)"""
rnn = nnet_rte.RNNRTE(opts.wvecDim, opts.outputDim, 200, opts.numWords, opts.minibatch)
rnn.initParams(W, True)
x = pickle.load(open("mr_%s.p" % opts.dg_dataset, "rb"))
W_dg = x[0]
rnn_dg = nnet_rte.RNNRTE(opts.wvecDim, 2, 200, opts.numWords, opts.minibatch)
rnn_dg.initParams(W_dg, True)
sgd = optimizer.SGD(rnn, alpha=opts.step, minibatch=opts.minibatch, optimizer=opts.optimizer, model_dg=rnn_dg)
for e in range(opts.epochs):
start = time.time()
print "Running epoch %d" % e
if opts.use_denotation == 0:
sgd.run(trees)
else:
lines = tr.get_lines(opts.dg_dataset, opts.data)
sgd.run_using_denotation(trees, lines)
end = time.time()
print "Time per epoch : %f" % (end - start)
with open(opts.outFile, "w") as fid:
pickle.dump(opts, fid)
pickle.dump(sgd.costt, fid)
# debug
if e == opts.epochs - 1:
rnn.toFile(fid, True)
else:
rnn.toFile(fid)
