Skip to content

P
pytensor
提交 420a9b83 authored 作者: Pascal Lamblin's avatar Pascal Lamblin 提交者： GitHub
浏览文件
操作

Merge pull request #4376 from adbrebs/fix_stack_check_nnet

[WIP] Use check_stack_trace helper function in tensor/nnet/tests/
上级 b3f54e3a 8be3b304
全部展开 隐藏空白字符变更
内嵌 并排
正在显示 包含 53 行增加 和 28 行删除
theano/tensor/nnet/nnet.py
浏览文件 @ 420a9b83
......@@ -905,9 +905,11 @@ def softmax_simplifier(numerators, denominators):
matching_denom = denominator
break
if matching_denom:
softmax = softmax_op(x)
copy_stack_trace(numerator, softmax)
numerators.remove(numerator)
denominators.remove(matching_denom)
numerators.append(softmax_op(x))
numerators.append(softmax)
return numerators, denominators
opt.local_mul_canonizer.add_simplifier(softmax_simplifier, 'softmax_simplifier')
......
theano/tensor/nnet/sigm.py
浏览文件 @ 420a9b83
......@@ -612,6 +612,7 @@ def local_exp_over_1_plus_exp(node):
else:
# case: 1/(1+exp(x))
sigmoids.append(sigmoid(-t))
copy_stack_trace(node.outputs[0], sigmoids[-1])
if not sigmoids: # we didn't find any. abort
return
......@@ -625,12 +626,17 @@ def local_exp_over_1_plus_exp(node):
if num_neg ^ denom_neg:
new_num = -new_num
copy_stack_trace(num, new_num)
if len(denom_rest) == 0:
return [new_num]
elif len(denom_rest) == 1:
return [new_num / denom_rest[0]]
out = new_num / denom_rest[0]
else:
return [new_num / tensor.mul(*denom_rest)]
out = new_num / tensor.mul(*denom_rest)
copy_stack_trace(node.outputs[0], out)
return [out]
def parse_mul_tree(root):
......@@ -923,6 +929,7 @@ def local_sigm_times_exp(node):
exp(x) * sigm(-x) -> sigm(x)
exp(-x) * sigm(x) -> sigm(-x)
todo: add stack traces to the intermediate variables
"""
# Bail early if it is not a multiplication.
if node.op != tensor.mul:
......
theano/tensor/nnet/tests/test_abstract_conv.py
浏览文件 @ 420a9b83
......@@ -7,6 +7,7 @@ from nose.tools import assert_raises
import theano
from theano import tensor
from theano.gof.opt import check_stack_trace
from theano.tests import unittest_tools as utt
from theano.tensor.nnet import corr, abstract_conv as conv
from theano.tensor.nnet.abstract_conv import get_conv_output_shape
......@@ -98,7 +99,7 @@ class BaseTestConv2d(unittest.TestCase):
def run_fwd(self, inputs_shape, filters_shape, ref=conv_corr,
subsample=(1, 1), verify_grad=True, mode=None,
border_mode='valid', filter_flip=True, provide_shape=False,
target_op=None):
target_op=None, check_trace=False):
inputs_val = numpy.random.random(inputs_shape).astype('float32')
filters_val = numpy.random.random(filters_shape).astype('float32')
......@@ -133,8 +134,9 @@ class BaseTestConv2d(unittest.TestCase):
if target_op is not None:
assert any([isinstance(n.op, target_op) for n
in f.maker.fgraph.toposort()])
if check_trace:
self.assertTrue(check_stack_trace(f, ops_to_check=target_op))
self.assertTrue(hasattr(f.maker.fgraph.outputs[0].tag, 'trace'))
res_ref = numpy.array(f_ref())
res = numpy.array(f())
utt.assert_allclose(res_ref, res)
......@@ -148,7 +150,7 @@ class BaseTestConv2d(unittest.TestCase):
def run_gradweight(self, inputs_shape, filters_shape, output_shape,
ref=conv_corr_gw, subsample=(1, 1), filter_flip=True,
verify_grad=True, mode=None, border_mode='valid',
provide_shape=False, target_op=None):
provide_shape=False, target_op=None, check_trace=False):
inputs_val = numpy.random.random(inputs_shape).astype('float32')
output_val = numpy.random.random(output_shape).astype('float32')
......@@ -177,12 +179,13 @@ class BaseTestConv2d(unittest.TestCase):
subsample=subsample,
conv_mode=conv_mode)
f = theano.function([], c, mode=mode)
self.assertTrue(hasattr(f.maker.fgraph.outputs[0].tag, 'trace'))
f_ref = theano.function([], c_ref, mode='FAST_RUN')
if target_op is not None:
assert any([isinstance(n.op, target_op) for n
in f.maker.fgraph.toposort()])
if check_trace:
self.assertTrue(check_stack_trace(f, ops_to_check=target_op))
res_ref = numpy.array(f_ref())
res = numpy.array(f())
......@@ -201,7 +204,7 @@ class BaseTestConv2d(unittest.TestCase):
def run_gradinput(self, inputs_shape, filters_shape, output_shape,
ref=conv_corr_gi, subsample=(1, 1), filter_flip=True,
verify_grad=True, mode=None, border_mode='valid',
provide_shape=False, target_op=None):
provide_shape=False, target_op=None, check_trace=False):
output_val = numpy.random.random(output_shape).astype('float32')
filters_val = numpy.random.random(filters_shape).astype('float32')
......@@ -227,12 +230,13 @@ class BaseTestConv2d(unittest.TestCase):
border_mode=border_mode, subsample=subsample,
conv_mode=conv_mode)
f = theano.function([], c, mode=mode)
self.assertTrue(hasattr(f.maker.fgraph.outputs[0].tag, 'trace'))
f_ref = theano.function([], c_ref, mode='FAST_RUN')
if target_op is not None:
assert any([isinstance(n.op, target_op) for n
in f.maker.fgraph.toposort()])
if check_trace:
self.assertTrue(check_stack_trace(f, ops_to_check=target_op))
res_ref = numpy.array(f_ref())
res = numpy.array(f())
......@@ -291,15 +295,18 @@ class TestCorrConv2d(BaseTestConv2d):
raise SkipTest("Need blas to test conv2d")
self.run_fwd(inputs_shape=i, filters_shape=f, subsample=s,
verify_grad=True, provide_shape=provide_shape,
border_mode=b, filter_flip=flip, target_op=CorrMM)
border_mode=b, filter_flip=flip, target_op=CorrMM,
check_trace=True)
self.run_gradweight(inputs_shape=i, filters_shape=f,
output_shape=o, subsample=s, verify_grad=True,
provide_shape=provide_shape, border_mode=b,
filter_flip=flip, target_op=CorrMM_gradWeights)
filter_flip=flip, target_op=CorrMM_gradWeights,
check_trace=True)
self.run_gradinput(inputs_shape=i, filters_shape=f,
output_shape=o, subsample=s, verify_grad=True,
provide_shape=provide_shape, border_mode=b,
filter_flip=flip, target_op=CorrMM_gradInputs)
filter_flip=flip, target_op=CorrMM_gradInputs,
check_trace=True)
class TestCpuConv2d(BaseTestConv2d):
......@@ -343,7 +350,8 @@ class TestCpuConv2d(BaseTestConv2d):
self.run_fwd(inputs_shape=i, filters_shape=f, subsample=s,
verify_grad=(gradweight_OK and gradinput_OK),
mode=mode, provide_shape=provide_shape,
border_mode=b, filter_flip=flip, target_op=ConvOp)
border_mode=b, filter_flip=flip, target_op=ConvOp,
check_trace=True)
else:
self.assertRaises(AssertionError,
self.run_fwd,
......@@ -354,7 +362,8 @@ class TestCpuConv2d(BaseTestConv2d):
mode=mode,
provide_shape=provide_shape,
border_mode=b,
filter_flip=flip)
filter_flip=flip,
check_trace=True)
if gradweight_OK:
if not theano.config.blas.ldflags:
......@@ -364,7 +373,8 @@ class TestCpuConv2d(BaseTestConv2d):
verify_grad=False, mode=mode,
provide_shape=provide_shape, border_mode=b,
filter_flip=flip,
target_op=(ConvOp, ConvGrad3D))
target_op=(ConvOp, ConvGrad3D),
check_trace=True)
else:
self.assertRaises(AssertionError,
self.run_gradweight,
......@@ -376,7 +386,8 @@ class TestCpuConv2d(BaseTestConv2d):
mode=mode,
provide_shape=provide_shape,
border_mode=b,
filter_flip=flip)
filter_flip=flip,
check_trace=True)
if gradinput_OK:
if not theano.config.blas.ldflags:
......@@ -386,7 +397,8 @@ class TestCpuConv2d(BaseTestConv2d):
verify_grad=False, mode=mode,
provide_shape=provide_shape, border_mode=b,
filter_flip=flip,
target_op=(ConvOp, ConvTransp3D))
target_op=(ConvOp, ConvTransp3D),
check_trace=True)
else:
self.assertRaises(AssertionError,
self.run_gradinput,
......@@ -398,7 +410,8 @@ class TestCpuConv2d(BaseTestConv2d):
mode=mode,
provide_shape=provide_shape,
border_mode=b,
filter_flip=flip)
filter_flip=flip,
check_trace=True)
def test_constant_shapes():
......
theano/tensor/nnet/tests/test_conv3d2d.py
浏览文件 @ 420a9b83
......@@ -10,6 +10,7 @@ except ImportError:
from six.moves import xrange
import theano
from theano.gof.opt import check_stack_trace
from theano.tensor.nnet.conv3d2d import *
import theano.tests.unittest_tools as utt
......@@ -73,10 +74,11 @@ def pyconv3d(signals, filters):
r_i += o_i[Tf2:o_i_sh0-Tf2, Hf2:-Hf2, Wf2:-Wf2]
return rval
def check_diagonal_subtensor_view_traces(fn):
for apply_node in fn.maker.fgraph.apply_nodes:
if isinstance(apply_node.op, (DiagonalSubtensor, IncDiagonalSubtensor)):
assert hasattr(apply_node.outputs[0].tag, 'trace')
assert check_stack_trace(
fn, ops_to_check=(DiagonalSubtensor, IncDiagonalSubtensor))
def test_conv3d(mode=mode_without_gpu, shared=theano.tensor._shared):
if ndimage is None:
......@@ -150,7 +152,6 @@ def test_conv3d(mode=mode_without_gpu, shared=theano.tensor._shared):
newconv3d = theano.function([], [],
updates={s_output: out},
mode=mode)
check_diagonal_subtensor_view_traces(newconv3d)
t0 = time.time()
newconv3d()
......@@ -162,7 +163,6 @@ def test_conv3d(mode=mode_without_gpu, shared=theano.tensor._shared):
(s_signals, gsignals)],
mode=mode,
name='grad')
check_diagonal_subtensor_view_traces(gnewconv3d)
t0 = time.time()
gnewconv3d()
......
theano/tensor/nnet/tests/test_opt.py
浏览文件 @ 420a9b83
from __future__ import absolute_import, print_function, division
import theano
from theano import tensor
from theano.tensor.nnet.blocksparse import sparse_block_dot
from theano.gof.opt import check_stack_trace
from theano.tensor.nnet.blocksparse import (
sparse_block_dot, sparse_block_gemv_inplace, sparse_block_outer_inplace,
sparse_block_gemv, sparse_block_outer)
def test_blocksparse_inplace_gemv_opt():
......@@ -14,12 +17,13 @@ def test_blocksparse_inplace_gemv_opt():
o = sparse_block_dot(W, h, iIdx, b, oIdx)
f = theano.function([W, h, iIdx, b, oIdx], o)
assert hasattr(f.maker.fgraph.outputs[0].tag, 'trace')
if theano.config.mode == "FAST_COMPILE":
assert not f.maker.fgraph.toposort()[-1].op.inplace
assert check_stack_trace(f, ops_to_check=[sparse_block_gemv])
else:
assert f.maker.fgraph.toposort()[-1].op.inplace
assert check_stack_trace(f, ops_to_check=[sparse_block_gemv_inplace])
def test_blocksparse_inplace_outer_opt():
......@@ -31,13 +35,12 @@ def test_blocksparse_inplace_outer_opt():
o = sparse_block_dot(W, h, iIdx, b, oIdx)
theano.printing.debugprint(tensor.grad(o.sum(), wrt=W))
f = theano.function([W, h, iIdx, b, oIdx],
[o, tensor.grad(o.sum(), wrt=W)])
assert hasattr(f.maker.fgraph.outputs[0].tag, 'trace')
if theano.config.mode == "FAST_COMPILE":
assert not f.maker.fgraph.toposort()[-1].op.inplace
assert check_stack_trace(f, ops_to_check=sparse_block_outer)
else:
assert f.maker.fgraph.toposort()[-1].op.inplace
assert check_stack_trace(f, ops_to_check=sparse_block_outer_inplace)
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