Skip to content

P
pytensor
提交 cca41015 authored 作者: Razvan Pascanu's avatar Razvan Pascanu
浏览文件
操作

fixed some bug in scan_test

上级 668f41e0
隐藏空白字符变更
内嵌 并排
正在显示 包含 60 行增加 和 170 行删除
theano/sandbox/my_test_scan.py deleted 100644 → 0
浏览文件 @ 668f41e0
import numpy
import theano
import theano.sandbox.scan
# generator network, only one output , type scalar ; no sequence or
# non sequence arguments
def test_1():
def f_pow2(x_tm1):
return (2*x_tm1, {})
s = theano.tensor.dvector()
n_steps = theano.tensor.dscalar()
Y = theano.sandbox.scan.scan(f_pow2, [],s, [],n_steps = n_steps)
f1 = theano.function([s,n_steps], Y)
assert( numpy.any(f1([1],3)== [2,4,8]) )
# simple rnn, one input, one state, weights for each; input/state are
# vectors, weights are scalars
def test_2():
def f_rnn(u_t,x_tm1,W_in, W):
return (u_t*W_in+x_tm1*W, {})
u = theano.tensor.dvector()
x0 = theano.tensor.dvector()
W_in = theano.tensor.dscalar()
W = theano.tensor.dscalar()
Y = theano.sandbox.scan.scan(f_rnn, u,x0,[W_in,W])
f2 = theano.function([u,x0,W_in,W], Y)
assert(numpy.any(f2([1,2,3,4],[1],.1,1)== numpy.array([1.1,1.3,1.6,2.])))
# simple rnn, one input, one state, weights for each; input/state are
# vectors, weights are scalars; using shared variables
def test_3():
u = theano.tensor.dvector()
x0 = theano.tensor.dvector()
W_in = theano.shared(.1, name = 'w_in')
W = theano.shared(1., name ='w')
def f_rnn_shared(u_t,x_tm1):
return (u_t*W_in+x_tm1*W, {})
Y = theano.sandbox.scan.scan(f_rnn_shared, u,x0,[])
f3 = theano.function([u,x0], Y)
assert(numpy.any(f3([1,2,3,4],[1])== numpy.array([1.1,1.3,1.6,2.])))
# some rnn with multiple outputs and multiple inputs; other dimension
# instead of scalars/vectors
def test_4():
W_in2 = theano.shared(numpy.array([1.,2.]), name='win2')
W = theano.shared(numpy.array([[2.,1.],[1.,1.]]), name='w')
W_out = theano.shared(numpy.array([.5,1.]), name = 'wout')
W_in1 = theano.tensor.dmatrix('win')
u1 = theano.tensor.dmatrix('u1')
u2 = theano.tensor.dvector('u2')
x0 = theano.tensor.dmatrix('x0')
y0 = theano.tensor.dvector('y0')
## Why dot doesn;t work with scalars !??
## Why * doesn't support SharedVariable and TensorVariable
def f_rnn_cmpl(u1_t, u2_t, x_tm1, y_tm1, W_in1):
return ({}, [theano.dot(u1_t,W_in1) + u2_t* W_in2 + \
theano.dot(x_tm1, W), theano.dot(x_tm1, W_out)])
Y = theano.sandbox.scan.scan(f_rnn_cmpl,[u1,u2],[x0,y0],W_in1)
f4 = theano.function([u1,u2,x0,y0,W_in1], Y)
(x,y) = f4( numpy.array([[1,2],[1,2],[1,2]]), \
numpy.array([1,2,3]), \
numpy.array([[0,0]]), \
numpy.array([1]), \
numpy.array([[1,1],[1,1]]))
assert( numpy.all(x == numpy.array([[4.,5.],[18.,16.],[58.,43.]])))
assert( numpy.all(y == numpy.array([0.,7.,25.])))
# basic ESN using updates
def test_5():
W_in = theano.shared(numpy.array([1.,1.]), name='win')
W = theano.shared(numpy.array([[.1,0.],[.0,.1]]),name='w')
W_out= theano.shared(numpy.array([.5,1.]), name='wout')
u = theano.tensor.dvector('u')
x = theano.shared(numpy.array([0.,0.]),'x')
y0 = theano.tensor.dvector('y0')
def f_ESN(u_t):
return ( theano.dot(x,W_out), \
{ x: W_in*u_t + theano.dot(x,W) } )
Y = theano.sandbox.scan.scan(f_ESN,u,y0,[],outputs_taps={0:[]})
f5 = theano.function([u,y0],Y)
assert( f5( numpy.array([1,2,3]), numpy.array([0])) == \
numpy.array([0.,1.4,3.15]))
# basic ESN using updates ; moving backwards
def test_6():
W_in = theano.shared(numpy.array([1.,1.]), name='win')
W = theano.shared(numpy.array([[.1,0.],[.0,.1]]),name='w')
W_out= theano.shared(numpy.array([.5,1.]), name='wout')
u = theano.tensor.dvector('u')
x = theano.shared(numpy.array([0.,0.]),'x')
y0 = theano.tensor.dvector('y0')
def f_ESN(u_t):
return ( theano.dot(x,W_out), \
{ x: W_in*u_t + theano.dot(x,W) } )
Y = theano.sandbox.scan.scan(f_ESN,u,y0,[],outputs_taps={0:[]}, \
go_backwards = True)
f6 = theano.function([u,y0],Y)
assert( f6( numpy.array([1,2,3]), numpy.array([0])) == \
numpy.array([0., 4.5, 3.45]))
'''
TO TEST:
- test taps (for sequences and outputs )
- test gradient (one output)
- test gradient (multiple outputs)
- test gradient (go_bacwards)
- test gradient (multiple outputs / some uncomputable )
- test gradient (truncate_gradient)
- test gradient (force_gradient)
- test inplace map
'''
if __name__=='__main__':
test_1()
test_2()
test_3()
test_4()
test_5()
test_6()
theano/sandbox/scan.py
浏览文件 @ cca41015
......@@ -174,7 +174,8 @@ class Scan(theano.Op):
self.destroy_map = {}
if inplace:
self.destroy_map = inplace_map
for i in inplace_map.keys():
self.destroy_map.update({i: [inplace_map[i]] } )
self.seqs_taps = seqs_taps
self.outs_taps = outs_taps
......@@ -192,13 +193,25 @@ class Scan(theano.Op):
self.fn = theano.function(inputs,outputs, \
updates = updates, mode = mode)
g_y = [outputs[0].type()]
g_args = theano.tensor.grad(outputs[0],inputs, g_cost = g_y[-1])
def compute_gradient(y, g_y):
gmap = theano.gradient.grad_sources_inputs( \
[(y,g_y)], theano.gof.graph.inputs([y]), False)
def zero(p):
return theano.tensor.TensorConstant(theano.tensor.TensorType(\
dtype=p.type.dtype, broadcastable=[]),
numpy.asarray(0,dtype = p.type.dtype))
return [gmap.get(p, zero(p)) for p in inputs]
g_args = compute_gradient( outputs[0], g_y[-1])
# for all outputs compute gradients and then sum them up
for y in outputs[1:]:
g_y += [y.type()]
g_args_y = theano.tensor.grad(y,inputs, g_cost=g_y[-1])
g_args_y = compute_gradient( y,g_y[-1])
for i in xrange(len(g_args)):
g_args[i] += g_args_y[i]
......@@ -244,6 +257,7 @@ class Scan(theano.Op):
(self.n_outs == other.n_outs) and\
(self.n_args == other.n_args)
return rval
def __hash__(self):
return hash(type(self)) ^ \
......
theano/sandbox/test_scan.py
浏览文件 @ cca41015
......@@ -91,7 +91,6 @@ class T_Scan(unittest.TestCase):
utt.seed_rng()
# generator network, only one output , type scalar ; no sequence or
# non sequence arguments
def test_1(self):
......@@ -243,9 +242,11 @@ class T_Scan(unittest.TestCase):
Y = theano.sandbox.scan.scan(f_rnn_shared, u,x0, [], \
sequences_taps = {0:[-2]}, outputs_taps = {0:[-1,-2]})
f7 = theano.function([u,x0], Y)
#print f7([1,2,3,4],[1,2])
f7 = theano.function([u,x0], Y)
v_u = numpy.asarray([1.,2.,3.,4.])
v_x0 = numpy.asarray([1.,2.])
out = numpy.asarray([3.1,5.3])
assert (compareArrays( out, f7(v_u, v_x0)))
# simple rnn, one input, one state, weights for each; input/state are
# vectors, weights are scalars; using shared variables and past
......@@ -263,16 +264,48 @@ class T_Scan(unittest.TestCase):
Y = theano.sandbox.scan.scan(f_rnn_shared, u,x0, [], \
sequences_taps = {0:[-2,2]}, outputs_taps = {0:[-1,-2]})
f8 = theano.function([u,x0], Y)
#print f8([1,2,3,4,5,6],[1,2])
f8 = theano.function([u,x0], Y)
v_u = numpy.array([1.,2.,3.,4.,5.,6.])
v_x0 = numpy.array([1.,2.])
out = numpy.array([3.6, 6.4])
assert (compareArrays( out, f8(v_u, v_x0) ) )
'''
NOTE : BROKEN .. inplace doesn't work due to a stochasticOpimization
TODO : talk james
# simple rnn ; compute inplace
def test_9(self):
u = theano.tensor.dvector()
mu = theano.Param( u, mutable = True)
x0 = theano.tensor.dvector()
W_in = theano.shared(.1)
W = theano.shared(1.)
def f_rnn_shared(u_t, x_tm1):
return (u_t*W_in + x_tm1*W, {})
Y = theano.sandbox.scan.scan(f_rnn_shared, u, x0,[], \
inplace_map={0:0} )
f9 = theano.function([mu,x0], Y , #mode = 'FAST_RUN')
mode = 'DEBUG_MODE')
v_u = numpy.array([1.,2.,3.])
v_x0 = numpy.array([1.])
out = f9(v_u, v_x0)
v_out = numpy.array([1.1,1.3,1.6])
assert (compareArrays(out, v_out))
print v_u
assert (compareArrays(v_u, out))
'''
# test gradient simple network
def test_10(self):
pass
'''
TO TEST:
- test taps (for sequences and outputs )
- test gradient (one output)
- test gradient (multiple outputs)
- test gradient (go_bacwards)
......@@ -280,7 +313,6 @@ class T_Scan(unittest.TestCase):
- test gradient (truncate_gradient)
- test gradient (force_gradient)
- test_gradient (taps past/future)
- test inplace map
'''
......
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论