def test_fprop(self):
r = []
for i in xrange(self.N):
repeats = self.rng.random_integers(42)
axis = self.rng.randint(2)
input_dim, output_dim = self.rng.random_integers(2000, size=2)
x = self.get_normal_matrix(input_dim, output_dim)
output = {}
for processor_type in ['gpu', 'cpu']:
quagga.processor_type = processor_type
qx = Connector(Matrix.from_npa(x))
repeat_block = RepeatBlock(qx, repeats, axis)
qx.fprop()
repeat_block.fprop()
output[processor_type] = repeat_block.output.to_host()
r.append(np.allclose(output['gpu'], output['cpu']))
self.assertEqual(sum(r), len(r))
def test_bprop(self):
r = []
for i in xrange(self.N):
repeats = self.rng.random_integers(42)
axis = self.rng.randint(2)
input_dim, output_dim = self.rng.random_integers(2000, size=2)
x = self.get_normal_matrix(input_dim, output_dim)
input_dim = input_dim if axis else input_dim * repeats
true_labels = self.rng.randint(output_dim, size=(input_dim, 1)).astype(np.int32)
device_id = 0
output = {}
for processor_type in ['gpu', 'cpu']:
quagga.processor_type = processor_type
qx = Connector(Matrix.from_npa(x), device_id)
qtrue_labels = Connector(Matrix.from_npa(true_labels))
repeat_block = RepeatBlock(qx, repeats, axis)
sce_block = SoftmaxCeBlock(repeat_block.output, qtrue_labels)
qx.fprop()
qtrue_labels.fprop()
repeat_block.fprop()
sce_block.fprop()
sce_block.bprop()
repeat_block.bprop()
output[processor_type] = qx.backward_matrix.to_host()
r.append(np.allclose(output['gpu'], output['cpu']))
self.assertEqual(sum(r), len(r))
def test_theano_fprop(self):
r = []
for i in xrange(self.N):
repeats = self.rng.random_integers(42)
axis = self.rng.randint(2)
input_dim, output_dim = self.rng.random_integers(2000, size=2)
x = self.get_normal_matrix(input_dim, output_dim)
quagga.processor_type = 'gpu'
qx = Connector(Matrix.from_npa(x))
repeat_block = RepeatBlock(qx, repeats, axis)
qx.fprop()
repeat_block.fprop()
qoutput = repeat_block.output.to_host()
th_x = T.fmatrix()
reps = [1, 1]
reps[axis] = repeats
th_output = T.tile(th_x, reps)
th_output = theano.function([th_x], th_output)(x)
r.append(np.allclose(qoutput, th_output))
self.assertEqual(sum(r), len(r))
def test_theano_bprop(self):
r = []
for i in xrange(self.N):
repeats = self.rng.random_integers(42)
axis = self.rng.randint(2)
input_dim, output_dim = self.rng.random_integers(2000, size=2)
x = self.get_normal_matrix(input_dim, output_dim)
input_dim = input_dim if axis else input_dim * repeats
true_labels = self.rng.randint(output_dim, size=(input_dim, 1)).astype(np.int32)
device_id = 0
quagga.processor_type = 'gpu'
qx = Connector(Matrix.from_npa(x), device_id)
qtrue_labels = Connector(Matrix.from_npa(true_labels))
repeat_block = RepeatBlock(qx, repeats, axis)
sce_block = SoftmaxCeBlock(repeat_block.output, qtrue_labels)
qx.fprop()
qtrue_labels.fprop()
repeat_block.fprop()
sce_block.fprop()
sce_block.bprop()
repeat_block.bprop()
q_dL_dx = qx.backward_matrix.to_host()
th_x = T.fmatrix()
th_true_labels = T.ivector()
reps = [1, 1]
reps[axis] = repeats
th_output = T.tile(th_x, reps)
th_output = T.nnet.softmax(th_output)
loss = T.mean(T.nnet.categorical_crossentropy(th_output, th_true_labels))
get_grads = theano.function([th_x, th_true_labels], T.grad(loss, th_x))
th_dL_dx = get_grads(x, true_labels[:, 0])
r.append(np.allclose(q_dL_dx, th_dL_dx))
self.assertEqual(sum(r), len(r))
'device_id': 0
},
sce_dot_block_b={
'init': Constant(1, len(vocab)),
'device_id': 0
})
data_block = PtbMiniBatchesGenerator(ptb_train,
ptb_valid,
batch_size=64,
sentence_max_len=100,
device_id=0)
seq_embd_block = RowSlicingBlock(p['embd_W'], data_block.sentence_batch)
# remove last in the list
output = List(seq_embd_block.output[:-1], seq_embd_block.output.length - 1)
c_fwd_repeat_block = RepeatBlock(p['lstm_fwd_c0'],
data_block.sentence_batch.nrows,
axis=0,
device_id=0)
h_fwd_repeat_block = RepeatBlock(p['lstm_fwd_h0'],
data_block.sentence_batch.nrows,
axis=0,
device_id=0)
fwd_lstm_block = SequencerBlock(
block_class=LstmBlock,
params=[p['lstm_fwd_W'], p['lstm_fwd_R'], 0.5],
sequences=[output, data_block.mask],
output_names=['h'],
prev_names=['c', 'h'],
paddings=[c_fwd_repeat_block.output, h_fwd_repeat_block.output],
reverse=False,
device_id=0)
# remove first in the list
'device_id': 0},
enc_lstm_R={'init': H5pyInitializer(model_file_name, 'enc_lstm_R'),
'device_id': 0},
dec_lstm_c0={'init': H5pyInitializer(model_file_name, 'dec_lstm_c0'),
'device_id': 0},
dec_lstm_W={'init': H5pyInitializer(model_file_name, 'dec_lstm_W'),
'device_id': 0},
dec_lstm_R={'init': H5pyInitializer(model_file_name, 'dec_lstm_R'),
'device_id': 0},
sce_dot_block_W={'init': H5pyInitializer(model_file_name, 'sce_dot_block_W'),
'device_id': 0},
sce_dot_block_b={'init': H5pyInitializer(model_file_name, 'sce_dot_block_b'),
'device_id': 0})
data_block = DataBlock(train_data, valid_data, 64, word_dropout_prob=0.99, device_id=0)
enc_embd_block = RowSlicingBlock(p['embd_W'], data_block.enc_x)
enc_c_repeat_block = RepeatBlock(p['enc_lstm_c0'], data_block.enc_x.nrows, axis=0, device_id=0)
enc_h_repeat_block = RepeatBlock(p['enc_lstm_h0'], data_block.enc_x.nrows, axis=0, device_id=0)
enc_lstm_block = SequencerBlock(block_class=LstmBlock,
params=[p['enc_lstm_W'], p['enc_lstm_R'], 0.25],
sequences=[enc_embd_block.output, data_block.enc_mask],
output_names=['h'],
prev_names=['c', 'h'],
paddings=[enc_c_repeat_block.output, enc_h_repeat_block.output],
reverse=False,
device_id=0)
dec_embd_block = RowSlicingBlock(p['embd_W'], data_block.dec_x)
dec_c_repeat_block = RepeatBlock(p['dec_lstm_c0'], data_block.enc_x.nrows, axis=0, device_id=0)
last_selector_block = LastSelectorBlock(enc_lstm_block.h)
l2_reg_block = L2RegularizationBlock(last_selector_block.output, 0.001)
dec_lstm_block = SequencerBlock(block_class=LstmBlock,
params=[p['dec_lstm_W'], p['dec_lstm_R'], 0.25],
# t_lstm_W={'init': get_stacked_orth_R,
# 'device_id': 0},
# t_lstm_R={'init': get_stacked_orth_R,
# 'device_id': 0},
# sce_dot_block_W={'init': Orthogonal(1024, len(idx_to_char)),
# 'device_id': 0},
# sce_dot_block_b={'init': Constant(1, len(idx_to_char)),
# 'device_id': 0})
data_block = DataBlock(char_data,
char_to_idx,
50,
x_device_id=1,
y_device_id=0)
embd_block = RowSlicingBlock(W=p['embd_W'], row_indexes=data_block.x)
f_c_repeat_block = RepeatBlock(p['f_lstm_c0'],
data_block.x.nrows,
axis=0,
device_id=1)
f_h_repeat_block = RepeatBlock(p['f_lstm_h0'],
data_block.x.nrows,
axis=0,
device_id=1)
f_lstm_rnn_block = SequencerBlock(
block_class=LstmBlock,
params=[p['f_lstm_W'], p['f_lstm_R'], None],
sequences=[embd_block.output, data_block.mask],
output_names=['h'],
prev_names=['c', 'h'],
paddings=[f_c_repeat_block.output, f_h_repeat_block.output],
reverse=False,
device_id=1)
s_c_repeat_block = RepeatBlock(p['s_lstm_c0'],
