Skip to content

P
pytensor
提交 beded2b3 authored 作者: Gijs van Tulder's avatar Gijs van Tulder
浏览文件
操作

Check shape of cuDNN convolution result.

上级 65798698
隐藏空白字符变更
内嵌 并排
正在显示 包含 98 行增加 和 38 行删除
theano/gpuarray/dnn.py
浏览文件 @ beded2b3
......@@ -24,7 +24,8 @@ from theano.tensor.nnet.abstract_conv import (AbstractConv2d,
AbstractConv3d,
AbstractConv3d_gradWeights,
AbstractConv3d_gradInputs,
get_conv_output_shape)
get_conv_output_shape,
assert_conv_shape)
from theano.tensor.signal.pool import (
Pool, MaxPoolGrad, AveragePoolGrad)
from . import pygpu
......@@ -978,11 +979,12 @@ def dnn_conv(img, kerns, border_mode='valid', subsample=(1, 1),
# that would be flipped by conv_mode='conv' in GpuDnnConvGradW.
kerns = kerns[:, :, ::-1, ::-1]
kerns = gpu_contiguous(kerns.dimshuffle(1, 0, 2, 3))
shape2 = shape_i(img, 2, fgraph) - shape_i(kerns, 2, fgraph) + 1
shape3 = shape_i(img, 3, fgraph) - shape_i(kerns, 3, fgraph) + 1
out = gpu_alloc_empty(ctx_name, dtype=img.dtype)(
shape_i(kerns, 1, fgraph),
shape_i(img, 1, fgraph), shape2, shape3)
out_shp = (shape_i(kerns, 1, fgraph),
shape_i(img, 1, fgraph),
shape_i(img, 2, fgraph) - shape_i(kerns, 2, fgraph) + 1,
shape_i(img, 3, fgraph) - shape_i(kerns, 3, fgraph) + 1)
out_shp = assert_conv_shape(out_shp)
out = gpu_alloc_empty(ctx_name, dtype=img.dtype)(*out_shp)
desc = GpuDnnConvDesc(border_mode='valid', subsample=(1, 1),
conv_mode='cross', precision=precision)(out.shape)
conv = gpu_dnn_conv_gradW()(img, kerns, out, desc)
......@@ -996,11 +998,12 @@ def dnn_conv(img, kerns, border_mode='valid', subsample=(1, 1),
img = gpu_contiguous(img) # cudnn v2 rc3 need contiguous data
kerns = gpu_contiguous(kerns.dimshuffle(1, 0, 2, 3))
conv_mode = 'cross' if conv_mode == 'conv' else 'conv'
shape2 = shape_i(img, 2, fgraph) + shape_i(kerns, 2, fgraph) - 1
shape3 = shape_i(img, 3, fgraph) + shape_i(kerns, 3, fgraph) - 1
out = gpu_alloc_empty(ctx_name, dtype=img.dtype)(shape_i(img, 0, fgraph),
shape_i(kerns, 1, fgraph),
shape2, shape3)
out_shp = (shape_i(img, 0, fgraph),
shape_i(kerns, 1, fgraph),
shape_i(img, 2, fgraph) + shape_i(kerns, 2, fgraph) - 1,
shape_i(img, 3, fgraph) + shape_i(kerns, 3, fgraph) - 1)
out_shp = assert_conv_shape(out_shp)
out = gpu_alloc_empty(ctx_name, dtype=img.dtype)(*out_shp)
desc = GpuDnnConvDesc(border_mode='valid', subsample=(1, 1),
conv_mode=conv_mode, precision=precision)(kerns.shape)
return gpu_dnn_conv_gradI()(kerns, img, out, desc)
......@@ -1020,6 +1023,7 @@ def dnn_conv(img, kerns, border_mode='valid', subsample=(1, 1),
out_shp = get_conv_output_shape(ishape, kshape,
desc_op.border_mode,
desc_op.subsample)
out_shp = assert_conv_shape(out_shp)
out = gpu_alloc_empty(ctx_name, dtype=img.dtype)(*out_shp)
return gpu_dnn_conv(algo=algo)(img, kerns, out, desc)
......@@ -1092,12 +1096,13 @@ def dnn_conv3d(img, kerns, border_mode='valid', subsample=(1, 1, 1),
# that would be flipped by conv_mode='conv' in GpuDnnConvGradW.
kerns = kerns[:, :, ::-1, ::-1]
kerns = gpu_contiguous(kerns.dimshuffle(1, 0, 2, 3, 4))
shape2 = shape_i(img, 2, fgraph) - shape_i(kerns, 2, fgraph) + 1
shape3 = shape_i(img, 3, fgraph) - shape_i(kerns, 3, fgraph) + 1
shape4 = shape_i(img, 4, fgraph) - shape_i(kerns, 4, fgraph) + 1
out = gpu_alloc_empty(ctx_name, dtype=img.dtype)(
shape_i(kerns, 1, fgraph),
shape_i(img, 1, fgraph), shape2, shape3, shape4)
out_shp = (shape_i(kerns, 1, fgraph),
shape_i(img, 1, fgraph),
shape_i(img, 2, fgraph) - shape_i(kerns, 2, fgraph) + 1,
shape_i(img, 3, fgraph) - shape_i(kerns, 3, fgraph) + 1,
shape_i(img, 4, fgraph) - shape_i(kerns, 4, fgraph) + 1)
out_shp = assert_conv_shape(out_shp)
out = gpu_alloc_empty(ctx_name, dtype=img.dtype)(*out_shp)
desc = GpuDnnConvDesc(border_mode='valid', subsample=(1, 1, 1),
conv_mode='cross', precision=precision)(out.shape)
conv = gpu_dnn_conv_gradW()(img, kerns, out, desc)
......@@ -1111,12 +1116,13 @@ def dnn_conv3d(img, kerns, border_mode='valid', subsample=(1, 1, 1),
img = gpu_contiguous(img) # cudnn v2 rc3 need contiguous data
kerns = gpu_contiguous(kerns.dimshuffle(1, 0, 2, 3, 4))
conv_mode = 'cross' if conv_mode == 'conv' else 'conv'
shape2 = shape_i(img, 2, fgraph) + shape_i(kerns, 2, fgraph) - 1
shape3 = shape_i(img, 3, fgraph) + shape_i(kerns, 3, fgraph) - 1
shape4 = shape_i(img, 4, fgraph) + shape_i(kerns, 4, fgraph) - 1
out = gpu_alloc_empty(ctx_name, dtype=img.dtype)(shape_i(img, 0, fgraph),
shape_i(kerns, 1, fgraph),
shape2, shape3, shape4)
out_shp = (shape_i(img, 0, fgraph),
shape_i(kerns, 1, fgraph),
shape_i(img, 2, fgraph) + shape_i(kerns, 2, fgraph) - 1,
shape_i(img, 3, fgraph) + shape_i(kerns, 3, fgraph) - 1,
shape_i(img, 4, fgraph) + shape_i(kerns, 4, fgraph) - 1)
out_shp = assert_conv_shape(out_shp)
out = gpu_alloc_empty(ctx_name, dtype=img.dtype)(*out_shp)
desc = GpuDnnConvDesc(border_mode='valid', subsample=(1, 1, 1),
conv_mode=conv_mode, precision=precision)(kerns.shape)
return gpu_dnn_conv_gradI()(kerns, img, out, desc)
......@@ -1136,6 +1142,7 @@ def dnn_conv3d(img, kerns, border_mode='valid', subsample=(1, 1, 1),
out_shp = get_conv_output_shape(ishape, kshape,
desc_op.border_mode,
desc_op.subsample)
out_shp = assert_conv_shape(out_shp)
out = gpu_alloc_empty(ctx_name, dtype=img.dtype)(*out_shp)
return gpu_dnn_conv(algo=algo)(img, kerns, out, desc)
......
theano/sandbox/cuda/dnn.py
浏览文件 @ beded2b3
......@@ -14,7 +14,8 @@ from theano.gof.type import CDataType
from theano.compile import optdb
from theano.compile.ops import shape_i
from theano.tensor.nnet import LogSoftmax, SoftmaxGrad
from theano.tensor.nnet.abstract_conv import get_conv_output_shape
from theano.tensor.nnet.abstract_conv import (get_conv_output_shape,
assert_conv_shape)
from theano.tensor.signal.pool import (
Pool, MaxPoolGrad, AveragePoolGrad)
from theano.sandbox.cuda.type import CudaNdarrayType
......@@ -1132,10 +1133,12 @@ def dnn_conv(img, kerns, border_mode='valid', subsample=(1, 1),
# that would be flipped by conv_mode='conv' in GpuDnnConvGradW.
kerns = kerns[:, :, ::-1, ::-1]
kerns = gpu_contiguous(kerns.dimshuffle(1, 0, 2, 3))
shape2 = shape_i(img, 2, fgraph) - shape_i(kerns, 2, fgraph) + 1
shape3 = shape_i(img, 3, fgraph) - shape_i(kerns, 3, fgraph) + 1
out = gpu_alloc_empty(shape_i(kerns, 1, fgraph),
shape_i(img, 1, fgraph), shape2, shape3)
out_shp = (shape_i(kerns, 1, fgraph),
shape_i(img, 1, fgraph),
shape_i(img, 2, fgraph) - shape_i(kerns, 2, fgraph) + 1,
shape_i(img, 3, fgraph) - shape_i(kerns, 3, fgraph) + 1)
out_shp = assert_conv_shape(out_shp)
out = gpu_alloc_empty(*out_shp)
desc = GpuDnnConvDesc(border_mode='valid', subsample=(1, 1),
conv_mode='cross', precision=precision)(img.shape,
out.shape)
......@@ -1149,10 +1152,12 @@ def dnn_conv(img, kerns, border_mode='valid', subsample=(1, 1),
img = gpu_contiguous(img)
kerns = gpu_contiguous(kerns.dimshuffle(1, 0, 2, 3))
conv_mode = 'cross' if conv_mode == 'conv' else 'conv'
shape2 = shape_i(img, 2, fgraph) + shape_i(kerns, 2, fgraph) - 1
shape3 = shape_i(img, 3, fgraph) + shape_i(kerns, 3, fgraph) - 1
out = gpu_alloc_empty(shape_i(img, 0, fgraph),
shape_i(kerns, 1, fgraph), shape2, shape3)
out_shp = (shape_i(img, 0, fgraph),
shape_i(kerns, 1, fgraph),
shape_i(img, 2, fgraph) + shape_i(kerns, 2, fgraph) - 1,
shape_i(img, 3, fgraph) + shape_i(kerns, 3, fgraph) - 1)
out_shp = assert_conv_shape(out_shp)
out = gpu_alloc_empty(*out_shp)
desc = GpuDnnConvDesc(border_mode='valid', subsample=(1, 1),
conv_mode=conv_mode, precision=precision)(out.shape,
kerns.shape)
......@@ -1170,6 +1175,7 @@ def dnn_conv(img, kerns, border_mode='valid', subsample=(1, 1),
out_shp = GpuDnnConv.get_out_shape(img.shape, kerns.shape,
desc_op.border_mode,
desc_op.subsample)
out_shp = assert_conv_shape(out_shp)
out = gpu_alloc_empty(*out_shp)
return GpuDnnConv(algo=algo)(img, kerns, out, desc)
......@@ -1248,11 +1254,13 @@ def dnn_conv3d(img, kerns, border_mode='valid', subsample=(1, 1, 1),
# that would be flipped by conv_mode='conv' in GpuDnnConvGradW.
kerns = kerns[:, :, ::-1, ::-1, ::-1]
kerns = gpu_contiguous(kerns.dimshuffle(1, 0, 2, 3, 4))
shape2 = shape_i(img, 2, fgraph) - shape_i(kerns, 2, fgraph) + 1
shape3 = shape_i(img, 3, fgraph) - shape_i(kerns, 3, fgraph) + 1
shape4 = shape_i(img, 4, fgraph) - shape_i(kerns, 4, fgraph) + 1
out = gpu_alloc_empty(shape_i(kerns, 1, fgraph),
shape_i(img, 1, fgraph), shape2, shape3, shape4)
out_shp = (shape_i(kerns, 1, fgraph),
shape_i(img, 1, fgraph),
shape_i(img, 2, fgraph) - shape_i(kerns, 2, fgraph) + 1,
shape_i(img, 3, fgraph) - shape_i(kerns, 3, fgraph) + 1,
shape_i(img, 4, fgraph) - shape_i(kerns, 4, fgraph) + 1)
out_shp = assert_conv_shape(out_shp)
out = gpu_alloc_empty(*out_shp)
desc = GpuDnnConvDesc(border_mode='valid', subsample=(1, 1, 1),
conv_mode='cross', precision=precision)(img.shape,
out.shape)
......@@ -1271,6 +1279,7 @@ def dnn_conv3d(img, kerns, border_mode='valid', subsample=(1, 1, 1),
out_shp = GpuDnnConv3d.get_out_shape(img.shape, kerns.shape,
desc_op.border_mode,
desc_op.subsample)
out_shp = assert_conv_shape(out_shp)
out = gpu_alloc_empty(*out_shp)
return GpuDnnConv3d(algo=algo)(img, kerns, out, desc)
......
theano/tensor/nnet/abstract_conv.py
浏览文件 @ beded2b3
......@@ -11,6 +11,7 @@ import theano
from theano.tensor import as_tensor_variable, patternbroadcast
from theano.tensor import get_scalar_constant_value, NotScalarConstantError
from theano.tensor.opt import Assert
from theano.gof import Apply, Op
from six.moves import xrange
......@@ -428,6 +429,34 @@ def check_conv_gradinputs_shape(image_shape, kernel_shape, output_shape,
for (given, computed) in zip(output_shape, computed_output_shape))
def assert_conv_shape(shape):
"""This function adds Assert nodes that check if shape is a valid convolution shape.
Parameters
----------
shape: tuple of int (symbolic or numeric) corresponding to the input, output or
kernel shape of a convolution. For input and output, the first elements should
should be the batch size and number of channels. For kernels, the first and
second elements should contain the number of input and output channels.
The remaining dimensions are the convolution dimensions.
Returns
-------
Returns a tuple similar to the given `shape`, but with each element wrapped in
an `Assert` op that checks that dimension. The first two dimensions should be
larger than or equal to zero. The convolution dimensions should be larger than zero.
"""
out_shape = []
for i, n in enumerate(shape):
if i < 2:
assert_shp = Assert('The convolution would produce an invalid shape (dim[%d] < 0).' % i)
out_shape.append(assert_shp(n, theano.tensor.ge(n, 0)))
else:
assert_shp = Assert('The convolution would produce an invalid shape (dim[%d] <= 0).' % i)
out_shape.append(assert_shp(n, theano.tensor.gt(n, 0)))
return tuple(out_shape)
def conv2d(input,
filters,
input_shape=None,
......
theano/tensor/nnet/tests/test_abstract_conv.py
浏览文件 @ beded2b3
......@@ -13,7 +13,8 @@ from theano.tensor.nnet import corr, corr3d, abstract_conv as conv
from theano.tensor.nnet.abstract_conv import (get_conv_output_shape,
get_conv_gradweights_shape,
get_conv_gradinputs_shape,
check_conv_gradinputs_shape)
check_conv_gradinputs_shape,
assert_conv_shape)
from theano.tensor.nnet.abstract_conv import AbstractConv2d
from theano.tensor.nnet.abstract_conv import AbstractConv2d_gradInputs
from theano.tensor.nnet.abstract_conv import AbstractConv2d_gradWeights
......@@ -211,6 +212,20 @@ class TestConvGradInputsShape(unittest.TestCase):
self.assertEqual(computed_kernel_shape, kernel_shape_with_None)
class TestAssertConvShape(unittest.TestCase):
def test_basic(self):
shape = tuple(tensor.iscalar() for i in range(4))
f = theano.function(shape, assert_conv_shape(shape))
self.assertEqual([1, 2, 3, 4], f(1, 2, 3, 4))
self.assertEqual([0, 0, 1, 1], f(0, 0, 1, 1))
assert_raises(AssertionError, f, 3, 3, 3, 0)
assert_raises(AssertionError, f, 3, 3, 0, 3)
assert_raises(AssertionError, f, 3, 3, -1, 3)
assert_raises(AssertionError, f, 3, -1, 3, 3)
assert_raises(AssertionError, f, -1, 3, 3, 3)
class BaseTestConv(object):
def get_output_shape(self, inputs_shape, filters_shape,
subsample, border_mode, filter_dilation):
......
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