Skip to content

P
pytensor
提交 84c51913 authored 作者: Sina Honari's avatar Sina Honari
浏览文件
操作

resolving the conflict for git rebase

上级 1d2eec53
隐藏空白字符变更
内嵌 并排
正在显示 包含 104 行增加 和 54 行删除
theano/tensor/signal/downsample.py
浏览文件 @ 84c51913
......@@ -236,7 +236,8 @@ class DownsampleFactorMax(Op):
gz, = grads
maxout = self(x)
return [DownsampleFactorMaxGrad(self.ds,
ignore_border=self.ignore_border)(
ignore_border=self.ignore_border,
st=self.st)(
x, maxout, gz)]
def c_code_tmp(self, node, name, inp, out, sub):
......@@ -317,21 +318,26 @@ class DownsampleFactorMax(Op):
class DownsampleFactorMaxGrad(Op):
def __init__(self, ds, ignore_border):
def __init__(self, ds, ignore_border, st=None):
self.ds = tuple(ds)
self.ignore_border = ignore_border
if st is None:
st = ds
self.st = tuple(st)
def __eq__(self, other):
return (type(self) == type(other) and
self.ds == other.ds and
self.st == other.st and
self.ignore_border == other.ignore_border)
def __hash__(self):
return hash(type(self)) ^ hash(self.ds) ^ 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}' % (self.__class__.__name__,
self.ds, self.ignore_border)
return '%s{%s,%s,%s}' % (self.__class__.__name__,
self.ds, self.st, self.ignore_border)
def make_node(self, x, maxout, gz):
# make_node should only be called by the grad function of
......@@ -347,22 +353,27 @@ class DownsampleFactorMaxGrad(Op):
gx_stg, = out
gx = numpy.zeros_like(x)
#number of pooling output rows
pr = maxout.shape[-2]
#number of pooling output cols
pc = maxout.shape[-1]
ds0, ds1 = self.ds
shape2 = (x.shape[2] // ds0 * ds0)
if not self.ignore_border:
shape2 = x.shape[2]
shape3 = (x.shape[3] // ds1 * ds1)
if not self.ignore_border:
shape3 = x.shape[3]
st0, st1 = self.st
img_rows = x.shape[-2]
img_cols = x.shape[-1]
for n in xrange(x.shape[0]):
for k in xrange(x.shape[1]):
for i in xrange(shape2):
zi = i // ds0
for j in xrange(shape3):
zj = j // ds1
if (maxout[n, k, zi, zj] == x[n, k, i, j]):
gx[n, k, i, j] = gz[n, k, zi, zj]
# No else clause needed as it is allocated with zeros
for r in xrange(pr):
row_st = r * st0
row_end = __builtin__.min(row_st + ds0, img_rows)
for c in xrange(pc):
col_st = c * st1
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):
if (maxout[n, k, r, c] == x[n, k, row_ind, col_ind]):
gx[n, k, row_ind, col_ind] = gz[n, k, r, c]
gx_stg[0] = gx
def infer_shape(self, node, in_shapes):
......@@ -374,9 +385,9 @@ class DownsampleFactorMaxGrad(Op):
return [theano.tensor.zeros_like(x),
theano.tensor.zeros_like(maxout),
DownsampleFactorMaxGradGrad(
self.ds, ignore_border=self.ignore_border)(x, maxout, ggx)]
self.ds, ignore_border=self.ignore_border, st=self.st)(x, maxout, ggx)]
def c_code(self, node, name, inp, out, sub):
def c_code_tmp(self, node, name, inp, out, sub):
x, z, gz = inp
gx, = out
fail = sub['fail']
......@@ -475,7 +486,7 @@ class DownsampleFactorMaxGrad(Op):
class DownsampleFactorMaxGradGrad(Op):
@staticmethod
def out_shape(imgshape, ds, ignore_border=False):
def out_shape(imgshape, ds, ignore_border=False, st=None):
"""Return the shape of the output from this op, for input of given
shape and flags.
......@@ -485,11 +496,15 @@ class DownsampleFactorMaxGradGrad(Op):
scalar Theano variable.
:param ds: downsample factor over rows and columns
this parameter indicates the size of the pooling region
:type ds: list or tuple of two ints
:param ignore_border: if ds doesn't divide imgshape, do we include
an extra row/col of partial downsampling (False) or ignore
it (True).
:param st: the stride size. This is the distance between the pooling
regions. If it's set to None, in which case it equlas ds.
:type st: list or tuple of two ints
:param ignore_border: if ds doesn't divide imgshape, do we include an
extra row/col of partial downsampling (False) or ignore it (True).
:type ignore_border: bool
:rtype: list
......@@ -500,35 +515,66 @@ class DownsampleFactorMaxGradGrad(Op):
if len(imgshape) < 2:
raise TypeError('imgshape must have at least two elements '
'(rows, cols)')
if st is None:
st = ds
r, c = imgshape[-2:]
rval = list(imgshape[:-2]) + [r // ds[0], c // ds[1]]
if not ignore_border:
if ignore_border:
out_r = (r - ds[0]) // st[0] + 1
out_c = (c - ds[1]) // st[1] + 1
if isinstance(r, theano.Variable):
rval[-2] = tensor.switch(r % ds[0], rval[-2] + 1, rval[-2])
elif r % ds[0]:
rval[-2] += 1
nr = tensor.maximum(out_r, 0)
else:
nr = numpy.maximum(out_r, 0)
if isinstance(c, theano.Variable):
rval[-1] = tensor.switch(c % ds[1], rval[-1] + 1, rval[-1])
elif c % ds[1]:
rval[-1] += 1
nc = tensor.maximum(out_c, 0)
else:
nc = numpy.maximum(out_c, 0)
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)
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)
elif st[1] >= ds[1]:
nc = (c - 1) // st[1] + 1
else:
nc = max(0, (c - 1 - ds[1]) // st[1] + 1) + 1
rval = list(imgshape[:-2]) + [nr, nc]
return rval
def __init__(self, ds, ignore_border):
def __init__(self, ds, ignore_border, st=None):
self.ds = tuple(ds)
self.ignore_border = ignore_border
if st is None:
st = ds
self.st = tuple(st)
def __eq__(self, other):
return (type(self) == type(other)
and self.ds == other.ds
and self.st == other.st
and self.ignore_border == other.ignore_border)
def __hash__(self):
return hash(type(self)) ^ hash(self.ds) ^ 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}' % (self.__class__.__name__, self.ds,
self.ignore_border)
return '%s{%s,%s,%s}' % (self.__class__.__name__,
self.ds, self.st, self.ignore_border)
def make_node(self, x, maxout, gz):
# make_node should only be called by the grad function of
......@@ -540,38 +586,42 @@ class DownsampleFactorMaxGradGrad(Op):
return Apply(self, [x, maxout, gz], [x.type()])
def perform(self, node, inp, out):
x, maxout, ggx = inp
z, = out
if len(x.shape) != 4:
raise NotImplementedError(
'DownsampleFactorMaxGradGrad requires 4D input for now')
z_shape = self.out_shape(x.shape, self.ds, self.ignore_border)
z_shape = self.out_shape(x.shape, self.ds, self.ignore_border, self.st)
if (z[0] is None) or (z[0].shape != z_shape):
z[0] = numpy.zeros(
self.out_shape(x.shape, self.ds, self.ignore_border))
z[0] = numpy.zeros(self.out_shape(x.shape, self.ds,
self.ignore_border, self.st))
z[0] = theano._asarray(z[0], dtype=x.dtype)
ggz = z[0]
## zz needs to be initialized with -inf for the following to work
ggz -= numpy.inf
#number of pooling output rows
pr = ggz.shape[-2]
#number of pooling output cols
pc = ggz.shape[-1]
ds0, ds1 = self.ds
if self.ignore_border:
x_usable2 = (x.shape[2] // ds0 * ds0)
else:
x_usable2 = x.shape[2]
if self.ignore_border:
x_usable3 = (x.shape[3] // ds1 * ds1)
else:
x_usable3 = x.shape[3]
st0, st1 = self.st
img_rows = x.shape[-2]
img_cols = x.shape[-1]
for n in xrange(x.shape[0]):
for k in xrange(x.shape[1]):
for i in xrange(x_usable2):
zi = i // ds0
for j in xrange(x_usable3):
zj = j // ds1
if (maxout[n, k, zi, zj] == x[n, k, i, j]):
ggz[n, k, zi, zj] = ggx[n, k, i, j]
for r in xrange(pr):
row_st = r * st0
row_end = __builtin__.min(row_st + ds0, img_rows)
for c in xrange(pc):
col_st = c * st1
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):
if (maxout[n, k, r, c] == x[n, k, row_ind, col_ind]):
ggz[n, k, r, c] = ggx[n, k, row_ind, col_ind]
def infer_shape(self, node, in_shapes):
return [in_shapes[0]]
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