if batch_id == 1:
accumulators[:] = np.array([accuracy_val, loss_val, alt_accuracy_val, alt_loss_val, gen_loss_val, recon_gen_loss_val, adv_gen_loss_val, cos_gen_loss_val, float(skip_generator), float(skip_discriminator), preout_grad_norm_val])
else:
accumulators[:] = ACCUMULATOR_EXPAVG * np.array([accuracy_val, loss_val, alt_accuracy_val, alt_loss_val, gen_loss_val, recon_gen_loss_val, adv_gen_loss_val, cos_gen_loss_val, float(skip_generator), float(skip_discriminator), preout_grad_norm_val]) + (1.0 - ACCUMULATOR_EXPAVG) * accumulators
if batch_id % print_every_n == 0:
print >> sys.stderr, 'batch: %s, acc: %s, loss: %s, alt acc: %s, alt loss: %s, gloss: %s, grloss: %s, galoss: %s, gcloss: %s, gskip: %s, dskip: %s, gn: %s' % tuple([batch_id] + accumulators.tolist())
def save_model():
params_vals = lasagne.layers.get_all_param_values([discriminator_0.l_out, discriminator_1.l_out, gen_l_out])
cPickle.dump(params_vals, open(MODEL_FILENAME, 'wb'), protocol=cPickle.HIGHEST_PROTOCOL)
print >> sys.stderr, 'Loading Italian embeddings...'
we_it = WordEmbeddings()
we_it.load_from_word2vec('./it')
we_it.downsample_frequent_words()
skn_it = StandardScaler()
we_it.vectors = skn_it.fit_transform(we_it.vectors).astype(theano.config.floatX)
we_batches_it = we_it.sample_batches(batch_size=HALF_BATCH_SIZE, random_state=rng)
print >> sys.stderr, 'Loading English embeddings...'
we_en = WordEmbeddings()
we_en.load_from_word2vec('./en')
we_en.downsample_frequent_words()
skn_en = StandardScaler()
we_en.vectors = skn_en.fit_transform(we_en.vectors).astype(theano.config.floatX)
we_batches_en = we_en.sample_batches(batch_size=HALF_BATCH_SIZE, random_state=rng)
print >> sys.stderr, 'Ready to train.'
if batch_id % print_every_n == 0:
print >> sys.stderr, 'batch: %s, acc: %s, loss: %s, alt acc: %s, alt loss: %s, gloss: %s, grloss: %s, galoss: %s, gcloss: %s, gskip: %s, dskip: %s, gn: %s' % tuple(
[batch_id] + accumulators.tolist())
def save_model():
params_vals = lasagne.layers.get_all_param_values(
[discriminator_0.l_out, discriminator_1.l_out, gen_l_out])
cPickle.dump(params_vals,
open(MODEL_FILENAME, 'wb'),
protocol=cPickle.HIGHEST_PROTOCOL)
print >> sys.stderr, 'Loading Italian embeddings...'
we_it = WordEmbeddings()
we_it.load_from_word2vec('./it')
we_it.downsample_frequent_words()
skn_it = StandardScaler()
we_it.vectors = skn_it.fit_transform(we_it.vectors).astype(
theano.config.floatX)
we_batches_it = we_it.sample_batches(batch_size=HALF_BATCH_SIZE,
random_state=rng)
print >> sys.stderr, 'Loading English embeddings...'
we_en = WordEmbeddings()
we_en.load_from_word2vec('./en')
we_en.downsample_frequent_words()
skn_en = StandardScaler()
we_en.vectors = skn_en.fit_transform(we_en.vectors).astype(
theano.config.floatX)
we_batches_en = we_en.sample_batches(batch_size=HALF_BATCH_SIZE,
def save_model():
params_vals = lasagne.layers.get_all_param_values([discriminator_0.l_out, discriminator_1.l_out, gen_l_out])
cPickle.dump(params_vals, open(MODEL_FILENAME, 'wb'), protocol=cPickle.HIGHEST_PROTOCOL)
def save_embeddings_to_Klementiev_format(filename, we, vectors=None):
if vectors == None:
vectors = we.vectors
outFs = open(filename, 'w')
for i, word in enumerate(we.words):
print >> outFs, word, ':', ' '.join([str(e) for e in vectors[i]])
outFs.close()
print >> sys.stderr, 'Loading English embeddings...'
we_it = WordEmbeddings()
we_it.load_from_word2vec('./en-m50000')
we_it.downsample_frequent_words()
skn_it = StandardScaler()
we_it.vectors = skn_it.fit_transform(we_it.vectors).astype(theano.config.floatX)
we_batches_it = we_it.sample_batches(batch_size=HALF_BATCH_SIZE, random_state=rng)
print >> sys.stderr, 'Loading German embeddings...'
we_en = WordEmbeddings()
we_en.load_from_word2vec('./de-m50000')
we_en.downsample_frequent_words()
skn_en = StandardScaler()
we_en.vectors = skn_en.fit_transform(we_en.vectors).astype(theano.config.floatX)
we_batches_en = we_en.sample_batches(batch_size=HALF_BATCH_SIZE, random_state=rng)
print >> sys.stderr, 'Ready to train.'
if batch_id == 1:
accumulators[:] = np.array([accuracy_val, loss_val, alt_accuracy_val, alt_loss_val, gen_loss_val, recon_gen_loss_val, adv_gen_loss_val, cos_gen_loss_val, float(skip_generator), float(skip_discriminator), preout_grad_norm_val])
else:
accumulators[:] = ACCUMULATOR_EXPAVG * np.array([accuracy_val, loss_val, alt_accuracy_val, alt_loss_val, gen_loss_val, recon_gen_loss_val, adv_gen_loss_val, cos_gen_loss_val, float(skip_generator), float(skip_discriminator), preout_grad_norm_val]) + (1.0 - ACCUMULATOR_EXPAVG) * accumulators
if batch_id % print_every_n == 0:
print >> sys.stderr, 'batch: %s, acc: %s, loss: %s, alt acc: %s, alt loss: %s, gloss: %s, grloss: %s, galoss: %s, gcloss: %s, gskip: %s, dskip: %s, gn: %s' % tuple([batch_id] + accumulators.tolist())
def save_model():
params_vals = lasagne.layers.get_all_param_values([discriminator_0.l_out, discriminator_1.l_out, gen_l_out])
cPickle.dump(params_vals, open(MODEL_FILENAME, 'wb'), protocol=cPickle.HIGHEST_PROTOCOL)
print >> sys.stderr, 'Loading German embeddings...'
we_it = WordEmbeddings()
we_it.load_from_word2vec('./de-m50000')
we_it.downsample_frequent_words()
skn_it = StandardScaler()
we_it.vectors = skn_it.fit_transform(we_it.vectors).astype(theano.config.floatX)
we_batches_it = we_it.sample_batches(batch_size=HALF_BATCH_SIZE, random_state=rng)
print >> sys.stderr, 'Loading English embeddings...'
we_en = WordEmbeddings()
we_en.load_from_word2vec('./en-m50000')
we_en.downsample_frequent_words()
skn_en = StandardScaler()
we_en.vectors = skn_en.fit_transform(we_en.vectors).astype(theano.config.floatX)
we_batches_en = we_en.sample_batches(batch_size=HALF_BATCH_SIZE, random_state=rng)
print >> sys.stderr, 'Ready to train.'
b=None,
name='gen_l_out')
self.dec_l_out = lasagne.layers.DenseLayer(self.gen_l_out,
num_units=n_input,
nonlinearity=None,
W=self.gen_l_out.W.T,
b=None,
name='dec_l_out')
dataDir = './'
rng = check_random_state(0)
we1 = WordEmbeddings()
we1.load_from_word2vec(dataDir, 'zh')
we1.downsample_frequent_words()
we1.vectors = normalize(we1.vectors)
we_batches1 = we1.sample_batches(batch_size=HALF_BATCH_SIZE, random_state=rng)
we2 = WordEmbeddings()
we2.load_from_word2vec(dataDir, 'en')
we2.downsample_frequent_words()
we2.vectors = normalize(we2.vectors)
we_batches2 = we2.sample_batches(batch_size=HALF_BATCH_SIZE, random_state=rng)
assert we1.embedding_dim == we2.embedding_dim
d = we1.embedding_dim
discriminator = Discriminator()
generator = Generator()
DISCR_NUM_HIDDEN_LAYERS = args.Dlayers DISCR_HIDDEN_DIM = args.Ddim HALF_BATCH_SIZE = 128 MODEL_FILENAME = 'model.pkl' rng = check_random_state(0) lang1 = args.lang1 lang2 = args.lang2 dataDir = 'data/' + args.config + '/' print >> sys.stderr, 'Loading', lang1, 'embeddings...' we1 = WordEmbeddings() we1.load_from_word2vec(dataDir, lang1) we1.downsample_frequent_words() we1.vectors = normalize(we1.vectors).astype(theano.config.floatX) we_batches1 = we1.sample_batches(batch_size=HALF_BATCH_SIZE, random_state=rng) print >> sys.stderr, 'Loading', lang2, 'embeddings...' we2 = WordEmbeddings() we2.load_from_word2vec(dataDir, lang2) we2.downsample_frequent_words() we2.vectors = normalize(we2.vectors).astype(theano.config.floatX) we_batches2 = we2.sample_batches(batch_size=HALF_BATCH_SIZE, random_state=rng) assert we1.embedding_dim == we2.embedding_dim d = we1.embedding_dim discriminator = Discriminator(d, DISCR_NUM_HIDDEN_LAYERS, DISCR_HIDDEN_DIM,