h = T.dot(h.dimshuffle('x', 0), W)
h1 = h[:, 0:10] # 1x10
h2 = h[:, 10:20]
h3 = h[:, 20:30]
h4 = h[:, 30:40]
test = (T.dot(x1, T.transpose(h1)) +
T.dot(x2, T.transpose(h2)) +
T.dot(x3, T.transpose(h3)) +
T.dot(x4, T.transpose(h4)))
return test + mem
mem, updates = T.scan(step1,
sequences=[inputs, hidden],
outputs_info=[T.zeros(shape=(seq_len, 1))]
)
f1 = T.function(inputs=[], outputs=mem)
print(f1().shape)
# ====== second approach ====== #
def step2(x1, x2, x3, x4, h, mem):
h = h.dimshuffle('x', 0) # 1x20
h1 = T.dot(h, W1) # 1x10
h2 = T.dot(h, W2)
h3 = T.dot(h, W3)
h4 = T.dot(h, W4)
test = (T.dot(x1, T.transpose(h1)) +
T.dot(x2, T.transpose(h2)) +
import time
import theano
def step(s1, s2, s3, o1, o2, n1, n2):
return o1, o2
seq1 = T.variable(np.arange(10))
seq2 = T.variable(np.arange(20))
seq3 = T.variable(np.arange(5))
nonseq1 = T.variable(1.)
nonseq2 = T.variable(2.)
([o1, o2], updates) = theano.scan(
fn=step,
sequences=[seq1, seq2, seq3],
outputs_info=[T.zeros((2, 2)), T.ones((2, 2))],
non_sequences=[nonseq1, nonseq2],
n_steps=None,
truncate_gradient=-1,
go_backwards=False)
f1 = T.function(
inputs=[],
outputs=[o1, o2],
updates=updates)
a, b = f1()
print(a.shape)
o1, o2 = T.loop(step,
sequences=[seq1, seq2, seq3],
outputs_info=[T.zeros((2, 2)), T.ones((2, 2))],