def get_data( fn, n_vis, n_val ):
if fn.isdigit():
#random
num_data = int(fn)
prob = nd.ones([num_data * n_vis, n_val]) / n_val
dat_lst = nd.sample_multinomial(prob)
sys.stderr.write("Generating random data: nv= %d, nd= %d\n" % (n_vis, num_data))
else:
#read from file
with open(fn, 'r') as fp:
lines = fp.readlines()
es = lines[0].split()
nl = int(es[0])
nv = int(es[1])
dat_lst = []
sys.stderr.write("Loading data: nv= %d, nd= %d\n" % (nv, nl))
for l in range(1, nl+1):
dat_lst.append([])
for i in range(nv):
bin_val = int2binary(lines[l][i])
for j in range(2):
dat_lst[l-1].append(int(bin_val[j]))
data = nd.array(dat_lst)
#data = nd.one_hot(dat_lst, n_val).reshape([-1, n_vis * n_val])
return data
def sample_v_given_h(self, h0):
v1_prob = self.propdown(h0).reshape([-1, self.n_val])
v1_prob = nd.softmax(v1_prob)
v1_args = nd.sample_multinomial(v1_prob)
v1 = nd.one_hot(v1_args, self.n_val)
return [
v1_prob.reshape([-1, self.n_node]),
v1.reshape([-1, self.n_node])
]
if step % 100 == 0:
print('Epoch [%d/%d], Step[%d/%d], Loss: %.3f, Perplexity: %5.2f' %
(epoch + 1, num_epochs, step, num_batches,
(loss / 1000).sum().asscalar(),
(loss / 1000).sum().exp().asscalar()))
# Sampling
with open(sample_path, 'w') as f:
# Set intial hidden ane memory states
states = [
nd.zeros((num_layers, 1, hidden_size), ctx=ctx),
nd.zeros((num_layers, 1, hidden_size), ctx=ctx)
]
# Select one word id randomly
prob = nd.ones((vocab_size, )) / vocab_size
input1 = nd.sample_multinomial(prob).reshape((1, 1)).as_in_context(ctx)
for i in range(num_samples):
output, state = model(input1, states)
# Sample a word id
prob = nd.exp(output).reshape((-1, ))
prob = prob / prob.sum()
word_id = nd.sample_multinomial(prob, 1)
input1 = word_id.reshape((1, 1))
word = corpus.dictionary.idx2word[word_id.asscalar()]
word = '\n' if word == '<eos>' else word + ' '
f.write(word)
if (i + 1) % 100 == 0:
print('Sampled [%d/%d] words and save to %s' %
(i + 1, num_samples, sample_path))