Skip to content

P
pytensor
提交 1d2eec53 authored 作者: Sina Honari's avatar Sina Honari
浏览文件
操作

applying the changes for the case of ignore_border plus the changes for pep8 for issue #2196

上级 26c105c9
显示空白字符变更
内嵌 并排
正在显示 包含 66 行增加 和 42 行删除
theano/tensor/signal/downsample.py
浏览文件 @ 1d2eec53
......@@ -102,9 +102,9 @@ class DownsampleFactorMax(Op):
st = ds
r, c = imgshape[-2:]
if ignore_border:
out_r = (r - ds[0]) // st[0] + 1
out_c = (c - ds[1]) // st[1] + 1
if isinstance(r, theano.Variable):
nr = tensor.maximum(out_r, 0)
else:
......@@ -113,17 +113,22 @@ class DownsampleFactorMax(Op):
nc = tensor.maximum(out_c, 0)
else:
nc = numpy.maximum(out_c, 0)
if not ignore_border:
else:
if isinstance(r, theano.Variable):
nr = tensor.switch(tensor.ge(st[0], ds[0]), (r - 1) // st[0] + 1, tensor.maximum(0, (r - 1 - ds[0]) // st[0] + 1) + 1)
nr = tensor.switch(tensor.ge(st[0], ds[0]),
(r - 1) // st[0] + 1,
tensor.maximum(0, (r - 1 - ds[0])
// st[0] + 1) + 1)
elif st[0] >= ds[0]:
nr = (r - 1) // st[0] + 1
else:
nr = max(0, (r - 1 - ds[0]) // st[0] + 1) + 1
if isinstance(c, theano.Variable):
nc = tensor.switch(tensor.ge(st[1], ds[1]), (c - 1) // st[1] + 1, tensor.maximum(0, (c - 1 - ds[1]) // st[1] + 1) + 1)
nc = tensor.switch(tensor.ge(st[1], ds[1]),
(c - 1) // st[1] + 1,
tensor.maximum(0, (c - 1 - ds[1])
// st[1] + 1) + 1)
elif st[1] >= ds[1]:
nc = (c - 1) // st[1] + 1
else:
......@@ -134,7 +139,8 @@ class DownsampleFactorMax(Op):
def __init__(self, ds, ignore_border=False, st=None):
"""
:param ds: downsample factor over rows and column. ds indicates the pool region size
:param ds: downsample factor over rows and column.
ds indicates the pool region size.
:type ds: list or tuple of two ints
: param st: stride size, which is the number of shifts
......@@ -167,7 +173,8 @@ class DownsampleFactorMax(Op):
self.ignore_border == other.ignore_border)
def __hash__(self):
return hash(type(self)) ^ hash(self.ds) ^ hash(self.st) ^ hash(self.ignore_border)
return hash(type(self)) ^ hash(self.ds) ^ \
hash(self.st) ^ hash(self.ignore_border)
def __str__(self):
return '%s{%s,%s,%s}' % (self.__class__.__name__,
......@@ -196,8 +203,10 @@ class DownsampleFactorMax(Op):
## zz needs to be initialized with -inf for the following to work
zz -= numpy.inf
pr = zz.shape[-2] # number of pooling output rows
pc = zz.shape[-1] # number of pooling output cols
#number of pooling output rows
pr = zz.shape[-2]
#number of pooling output cols
pc = zz.shape[-1]
ds0, ds1 = self.ds
st0, st1 = self.st
img_rows = x.shape[-2]
......@@ -213,11 +222,13 @@ class DownsampleFactorMax(Op):
col_end = __builtin__.min(col_st + ds1, img_cols)
for row_ind in xrange(row_st, row_end):
for col_ind in xrange(col_st, col_end):
zz[n, k, r, c] = __builtin__.max(zz[n, k, r, c],
zz[n, k, r, c] = \
__builtin__.max(zz[n, k, r, c],
x[n, k, row_ind, col_ind])
def infer_shape(self, node, in_shapes):
shp = self.out_shape(in_shapes[0], self.ds, self.ignore_border, self.st)
shp = self.out_shape(in_shapes[0], self.ds,
self.ignore_border, self.st)
return [shp]
def grad(self, inp, grads):
......
theano/tensor/signal/tests/test_downsample.py
浏览文件 @ 1d2eec53
......@@ -15,7 +15,7 @@ class TestDownsampleFactorMax(utt.InferShapeTester):
'''Helper function, implementing max_pool_2d in pure numpy'''
if len(input.shape) < 2:
raise NotImplementedError('input should have at least 2 dim,'
' shape is %s'\
' shape is %s'
% str(input.shape))
xi = 0
yi = 0
......@@ -45,10 +45,10 @@ class TestDownsampleFactorMax(utt.InferShapeTester):
for the pooling regions. if not indicated, st == sd.'''
if len(input.shape) < 2:
raise NotImplementedError('input should have at least 2 dim,'
' shape is %s'\
' shape is %s'
% str(input.shape))
if st == None:
if st is None:
st = ds
xi = 0
yi = 0
......@@ -64,19 +64,18 @@ class TestDownsampleFactorMax(utt.InferShapeTester):
if not ignore_border:
if out_r > 0:
if img_rows - ((out_r - 1) * st[0] + ds[0]) > 0 :
if img_rows - ((out_r - 1) * st[0] + ds[0]) > 0:
rr = img_rows - out_r * st[0]
if rr > 0:
out_r += 1
else:
if img_rows > 0:
out_r += 1
if out_c > 0:
if img_cols - ((out_c - 1) * st[1] + ds[1]) > 0 :
if img_cols - ((out_c - 1) * st[1] + ds[1]) > 0:
cr = img_cols - out_c * st[1]
if cr > 0:
out_c +=1
out_c += 1
else:
if img_cols > 0:
out_c += 1
......@@ -119,7 +118,8 @@ class TestDownsampleFactorMax(utt.InferShapeTester):
#DownsampleFactorMax op
maxpool_op = DownsampleFactorMax(maxpoolshp,
ignore_border=ignore_border)(images)
ignore_border=
ignore_border)(images)
f = function([images], maxpool_op)
output_val = f(imval)
utt.assert_allclose(output_val, numpy_output_val)
......@@ -130,11 +130,12 @@ class TestDownsampleFactorMax(utt.InferShapeTester):
stridesizes = ((1, 1), (3, 3), (5, 7))
# generate random images
imval = rng.rand(4, 10, 16, 16)
outputshps = ((4, 10, 16, 16), (4, 10, 6, 6), (4, 10, 4, 3), (4, 10, 16, 16), \
(4, 10, 6, 6), (4, 10, 4, 3), (4, 10, 14, 14), (4, 10, 5, 5), \
(4, 10, 3, 2), (4, 10, 14, 14), (4, 10, 6, 6), (4, 10, 4, 3), \
(4, 10, 12, 14), (4, 10, 4, 5), (4, 10, 3, 2), (4, 10, 12, 14), \
(4, 10, 5, 6), (4, 10, 4, 3))
outputshps = ((4, 10, 16, 16), (4, 10, 6, 6), (4, 10, 4, 3),
(4, 10, 16, 16), (4, 10, 6, 6), (4, 10, 4, 3),
(4, 10, 14, 14), (4, 10, 5, 5), (4, 10, 3, 2),
(4, 10, 14, 14), (4, 10, 6, 6), (4, 10, 4, 3),
(4, 10, 12, 14), (4, 10, 4, 5), (4, 10, 3, 2),
(4, 10, 12, 14), (4, 10, 5, 6), (4, 10, 4, 3))
images = tensor.dtensor4()
indx = 0
for maxpoolshp in maxpoolshps:
......@@ -143,13 +144,16 @@ class TestDownsampleFactorMax(utt.InferShapeTester):
outputshp = outputshps[indx]
indx += 1
#DownsampleFactorMax op
numpy_output_val = self.numpy_max_pool_2d_stride(imval, maxpoolshp,
numpy_output_val = \
self.numpy_max_pool_2d_stride(imval, maxpoolshp,
ignore_border, stride)
assert numpy_output_val.shape == outputshp, (
"outshape is %s, calculated shape is %s"
%(outputshp, numpy_output_val.shape))
maxpool_op = DownsampleFactorMax(maxpoolshp,
ignore_border=ignore_border, st=stride)(images)
% (outputshp, numpy_output_val.shape))
maxpool_op = \
DownsampleFactorMax(maxpoolshp,
ignore_border=ignore_border,
st=stride)(images)
f = function([images], maxpool_op)
output_val = f(imval)
utt.assert_allclose(output_val, numpy_output_val)
......@@ -157,16 +161,19 @@ class TestDownsampleFactorMax(utt.InferShapeTester):
def test_DownsampleFactorMaxStrideExtra(self):
rng = numpy.random.RandomState(utt.fetch_seed())
maxpoolshps = ((5, 3), (5, 3), (5, 3), (5, 5), (3, 2), (7, 7), (9, 9))
stridesizes = ((3, 2), (7, 5), (10, 6), (1, 1), (2, 3), (10, 10), (1, 1))
imvsizs = ((16, 16), (16, 16), (16, 16), (8, 5), (8, 5), (8, 5), (8, 5))
outputshps = ((4, 10, 4, 7), (4, 10, 5, 8), (4, 10, 2, 3), (4, 10, 3, 4), \
(4, 10, 2, 3), (4, 10, 2, 3), (4, 10, 4, 1), (4, 10, 4, 1), \
(4, 10, 3, 2), (4, 10, 4, 2), (4, 10, 1, 0), (4, 10, 1, 1), \
stridesizes = ((3, 2), (7, 5), (10, 6), (1, 1),
(2, 3), (10, 10), (1, 1))
imvsizs = ((16, 16), (16, 16), (16, 16), (8, 5),
(8, 5), (8, 5), (8, 5))
outputshps = ((4, 10, 4, 7), (4, 10, 5, 8), (4, 10, 2, 3),
(4, 10, 3, 4), (4, 10, 2, 3), (4, 10, 2, 3),
(4, 10, 4, 1), (4, 10, 4, 1), (4, 10, 3, 2),
(4, 10, 4, 2), (4, 10, 1, 0), (4, 10, 1, 1),
(4, 10, 0, 0), (4, 10, 1, 1))
images = tensor.dtensor4()
for indx in numpy.arange(len(maxpoolshps)):
imvsize = imvsizs[indx]
imval = rng.rand(4, 10 , imvsize[0], imvsize[1])
imval = rng.rand(4, 10, imvsize[0], imvsize[1])
stride = stridesizes[indx]
maxpoolshp = maxpoolshps[indx]
for ignore_border in [True, False]:
......@@ -175,13 +182,16 @@ class TestDownsampleFactorMax(utt.InferShapeTester):
indx_out += 1
outputshp = outputshps[indx_out]
#DownsampleFactorMax op
numpy_output_val = self.numpy_max_pool_2d_stride(imval, maxpoolshp,
numpy_output_val = \
self.numpy_max_pool_2d_stride(imval, maxpoolshp,
ignore_border, stride)
assert numpy_output_val.shape == outputshp, (
"outshape is %s, calculated shape is %s"
%(outputshp, numpy_output_val.shape))
maxpool_op = DownsampleFactorMax(maxpoolshp,
ignore_border=ignore_border, st=stride)(images)
% (outputshp, numpy_output_val.shape))
maxpool_op = \
DownsampleFactorMax(maxpoolshp,
ignore_border=ignore_border,
st=stride)(images)
f = function([images], maxpool_op)
output_val = f(imval)
utt.assert_allclose(output_val, numpy_output_val)
......@@ -198,7 +208,8 @@ class TestDownsampleFactorMax(utt.InferShapeTester):
#print 'ignore_border =', ignore_border
def mp(input):
return DownsampleFactorMax(maxpoolshp,
ignore_border=ignore_border)(input)
ignore_border=
ignore_border)(input)
utt.verify_grad(mp, [imval], rng=rng)
def test_DownsampleFactorMaxGrad_grad(self):
......@@ -257,7 +268,8 @@ class TestDownsampleFactorMax(utt.InferShapeTester):
output_val = function([images], output)(imval)
assert numpy.all(output_val == numpy_output_val), (
"output_val is %s, numpy_output_val is %s"
%(output_val, numpy_output_val))
% (output_val, numpy_output_val))
def mp(input):
return max_pool_2d(input, maxpoolshp, ignore_border)
utt.verify_grad(mp, [imval], rng=rng)
......@@ -278,7 +290,7 @@ class TestDownsampleFactorMax(utt.InferShapeTester):
output_val = function([images], output)(imval)
assert numpy.all(output_val == numpy_output_val), (
"output_val is %s, numpy_output_val is %s"
%(output_val, numpy_output_val))
% (output_val, numpy_output_val))
c = tensor.sum(output)
c_val = function([images], c)(imval)
g = tensor.grad(c, images)
......@@ -344,7 +356,8 @@ class TestDownsampleFactorMax(utt.InferShapeTester):
gz_val = rng.rand(*out_shapes[i][j])
self._compile_and_check([image, maxout, gz],
[DownsampleFactorMaxGrad(maxpoolshp,
ignore_border=ignore_border)(image, maxout, gz)],
ignore_border=ignore_border)
(image, maxout, gz)],
[image_val, maxout_val, gz_val],
DownsampleFactorMaxGrad,
warn=False)
......
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