139ef0d61d
fix glog macro to assert
2014-11-08 22:16:32 -05:00
90ec6b1452
reverted extra spaces which were added in last commit
2014-11-07 12:11:08 +01:00
bd3f9db7df
inlined a fully specialized function template defined in a .hpp
2014-11-07 11:37:27 +01:00
e0c4d84dd7
Fixed some tests/warnings in quaternion mode
2014-11-03 00:59:19 +01:00
11416cac65
Merge branch 'feature/BAD' into feature/BAD_generic_value_traits
...
Conflicts:
gtsam_unstable/nonlinear/tests/testAdaptAutoDiff.cpp
gtsam_unstable/nonlinear/tests/testExpressionFactor.cpp
2014-11-02 19:00:30 +01:00
17d352bab4
Slight re-factor
2014-11-02 14:42:59 +01:00
d2f56b13ed
Non-trivial noise models now correctly handled (at a small performance penalty, due to malloc of Vector b).
2014-11-02 14:37:52 +01:00
90a0fa6e45
Check if active
2014-11-02 13:53:22 +01:00
a8ab910c32
Merged twio changes in: the is_constrained() flag that does away with the dynamic cast, and the changes duy made in commit a61b49d to remove the constrained noise model hack. At the same time, both linearize methods (in expressionFactor and NonlinearFactor) now make use of is_constrained().
2014-11-02 13:45:54 +01:00
b9e3c3b116
Made unsafe constructor private, but made ExpressionFactor<T> a friend.
2014-11-02 12:01:52 +01:00
cb69f2cb82
Fastest linearize so far. Putting 'unsafe' constructor in JacobianFactor itself makes a *huge* difference.
2014-11-02 11:40:48 +01:00
7aaf4dae8c
Merge remote-tracking branch 'origin/feature/BAD_VerticalBlockMatrix' into feature/BAD_WriteableJacobianFactor
...
Conflicts:
gtsam_unstable/nonlinear/ExpressionFactor.h
2014-11-01 17:45:23 +01:00
7debde7518
Moved to ExpressionFactor that now uses it - timing seems worse ?
2014-11-01 15:12:06 +01:00
12e38a44e4
WriteableJacobianFactor will allow ExpressionFactor to write into the factor directly, (hopefull) eliminating huge overhead.
2014-11-01 14:13:08 +01:00
a4fa61a7a4
Removed JacobianMap tests
2014-11-01 11:56:38 +01:00
f38b0b0eed
Fixed unwhitenedError
2014-11-01 11:50:28 +01:00
7b539fbb5c
Make JacobianMap a wrapper around a VerticalBlockMatrix, which avoids us having to make a vector of references into it
2014-11-01 11:35:49 +01:00
593edd1e5c
Fixed asserts
2014-10-31 16:29:15 +01:00
d0c3bc0c8e
Fixed tests
2014-10-31 16:27:54 +01:00
768a4abc05
Does not need lambda
2014-10-31 16:27:46 +01:00
a5b8d0fd35
Modified finding method
2014-10-31 11:06:26 -04:00
6a20d35a60
Modified pointer expression
2014-10-31 07:28:07 -04:00
133fcf20e2
Cleaned up some commented codes
2014-10-31 07:22:19 -04:00
97d4120858
Changed the type of JacobianMap as std::vector
2014-10-31 07:10:53 -04:00
80187362b8
attemping to expose ChartValue for expressions with non DefaultCharts, but needs testing
2014-10-28 11:20:02 +01:00
bc094951ed
all values in Values container are now a ChartValue<ValueType, Chart=DefaultChart<ValueType> >
...
ChartValues are GenericValues and a Chart, which defaults to DefaultChart
had to make charts functional (ie no storage of the chart origin) so that they could be zero sized base class
otherwise there would have been a double of the memory for values (ones for the value, and once for the chart origin, which default to the same)
most tests work, execept for serialization based stuff, and const filtering of values.
2014-10-28 00:57:44 +01:00
4a3dc51f85
more tests work, except for serialization based tests
2014-10-24 23:47:02 +02:00
e7ec6b3fa5
Fixed size
2014-10-23 12:04:16 +02:00
49ff33602d
Undid change
2014-10-23 01:44:04 +02:00
0501750c7c
Fixed accuracy and size issues in Quaternion mode
2014-10-22 22:54:25 +02:00
48a6777935
Some refactoring
2014-10-22 16:26:40 +02:00
0f53c8d5ec
Timing of Ceres AutoDiff adaptor
2014-10-22 12:49:18 +02:00
f44e6f0187
Moved AdaptAutoDiff template in its own header file
2014-10-22 11:41:04 +02:00
516bb4b0b1
Isolated Snavely example
2014-10-22 11:23:35 +02:00
439f51ec7f
test out invoke
2014-10-22 10:10:58 +02:00
1eb5e185e5
New numericalDerivatives with traits an Charts - still some segfaults, *and* there should be no need for (a) multiple prototypes to match against c++ pointers, (b) the use of explicit template arguments. A task for someone...
2014-10-21 18:50:52 +02:00
224b71d696
Created testManifold
2014-10-21 12:54:28 +02:00
0acffe5ae9
Fixed bug in DefaultChart: keeping a reference s never a good idea.
2014-10-21 11:13:14 +02:00
25ad9ade05
Moved AdaptAutoDiff into its own test
2014-10-21 10:42:30 +02:00
bf16446f92
Deal with traits changes
2014-10-21 01:26:17 +02:00
e0841fb3e6
No more Ceres dependecy, copied relevant Ceres files here (for now)
2014-10-20 23:53:56 +02:00
bce84ca4db
Successfully created Expression from AutoDiff function!
2014-10-20 15:38:27 +02:00
bf5580d518
AdaptAutoDiff now works with RowMajor Eigen matrices
2014-10-20 14:39:28 +02:00
df5e584412
Compiles, but Jacobains not correct yet
2014-10-20 14:32:20 +02:00
a423f284e9
Canonical coordinates prototype, works for Snavely
2014-10-20 14:23:08 +02:00
821f776118
Wrapper works to some extent
2014-10-20 09:43:32 +02:00
7ebc8e969f
Charts with default constructors
2014-10-20 09:29:45 +02:00
63ae33088e
Some success on the way to autodiff
2014-10-19 23:47:59 +02:00
8ee16c9018
Comments for Paul
2014-10-19 11:19:09 +02:00
eac76cd0f0
Some progress on defining interface
2014-10-19 11:18:36 +02:00
6e142184cc
Implemented is_manifold and dimension for all types in testExpressionFactor
2014-10-19 00:35:25 +02:00
c32d2bb3b2
Fixed comments
2014-10-18 23:48:51 +02:00
d436d99146
Moved stuff to Manifold.h
2014-10-18 23:25:25 +02:00
fcda501ee2
double as manifold. No more LieScalar !
2014-10-18 18:13:33 +02:00
ed6a2b6eff
Charts !!!!
2014-10-18 17:11:28 +02:00
9c97b1d8a0
Some more refactoring
2014-10-18 16:45:04 +02:00
66b3081603
localCoordinates and retract
2014-10-18 15:02:22 +02:00
10cfd47404
TangentVector meta-function
2014-10-18 14:29:40 +02:00
ec69949f43
Point2 specialized
2014-10-18 14:22:01 +02:00
f08dc6c031
More boost-style traits
2014-10-18 14:16:24 +02:00
4c33444415
Snavely tested
2014-10-18 13:16:44 +02:00
bdf12b14b9
Add Snavely cost function
2014-10-18 12:35:02 +02:00
7018afdd58
Slight refactor of numerical derivatives
2014-10-18 12:34:05 +02:00
2972671064
Use boost::bind to avoid code duplication
2014-10-18 12:29:14 +02:00
db037c96c5
Implemented manifold_traits to allow numerical derivatives wrpt Matrix arguments
2014-10-18 12:12:25 +02:00
2cbba15573
ceres style functor
2014-10-18 00:29:18 +02:00
02d25f6658
New tests on traceSize
2014-10-16 15:07:05 +02:00
0bcca2c386
Drastic reduction in allocations at ExpressionFactor construction by having dims constructed imperatively, and using it for both keys_ and dimensions_
2014-10-16 14:16:58 +02:00
944422e295
Only ExpressionFactor needs dimensions! Also, add dimensions at construction -> speeds up linearize.
2014-10-16 11:15:47 +02:00
3413b98331
New storage sizes
2014-10-15 14:30:36 +02:00
79ff0c54f9
createUnknowns
2014-10-15 10:38:54 +02:00
649478f186
Should work but seg-faults
2014-10-15 01:19:14 +02:00
9b1c9bbf37
Allocate temporary matrix on the stack rather tahn on heap, and give VerticalBlockMatrix a view on it.
2014-10-15 00:56:06 +02:00
c88b2a5902
Fixed bizarre link erro as well as off-by-1 bug
2014-10-15 00:34:28 +02:00
0f055f7910
Pass matrix to VerticalBlockMatrix constructor
2014-10-15 00:28:53 +02:00
625b939b66
Another very significant speed-up of reverseAD pipeline, by template specialization of the leaf case for fixed matrices. Unfortunately, while this sped up reverse AD for our SFM kernel by 300%, reverseAD was only 6%, and is now 2% of total time. So, time to look elsewhere.
...
Oh, and, it is clear that the Identity matrix for Leaf only expressions is completely known at compile time: Eigen::Matrix<double, T::dimension, T::dimension>::Identity(). That should nicely speed up many a PriorFactor (replacement).
2014-10-14 23:40:21 +02:00
baaeaacabe
Made dimensions constant property. Now performance is ***blazing***, way past custom factors.
2014-10-14 17:46:57 +02:00
c971207abf
Switched to vector for dimensions
2014-10-14 17:16:31 +02:00
1c3f328fb2
Successful switch to Blocks !
2014-10-14 15:43:41 +02:00
f3e1561105
Prepare VerticalBlockMatrix for filling
2014-10-14 11:13:49 +02:00
4c76f39009
Now uses dimensions
2014-10-14 09:55:34 +02:00
d8d94d0c34
dimensions implemented and tested
2014-10-14 09:53:47 +02:00
781cc6daa9
keys now from expression_
2014-10-14 08:59:01 +02:00
0a41b0a027
Moved meta-programming tests to testExpressionMeta.cpp
2014-10-14 08:53:16 +02:00
ef5bf03c81
Clean up
2014-10-13 23:04:30 +02:00
70f0caf0e3
Experimenting w Fusion
2014-10-13 22:50:47 +02:00
dda91df6e1
On the way to full fusion: Optional meta-function now separate from Jacobian.
2014-10-13 18:32:58 +02:00
ba0b68110f
Boost Fusion needed to access values :-(
2014-10-13 13:56:51 +02:00
a52ff52941
Try some meta-transforms
2014-10-13 13:34:00 +02:00
1c1695353e
Now we can apply ExecutionTrace and Expression as meta-functions
2014-10-13 13:04:37 +02:00
c11d7885e1
Comments
2014-10-13 11:55:16 +02:00
74269902d7
Big collapse now realized all the way through
2014-10-13 11:37:47 +02:00
da0e5fe52f
The great collapse: instead of two recursively defined classes, there is now only one. The Record class is now a (recursive) inner class.
2014-10-13 10:50:05 +02:00
bc9e11f43c
Pre-big collapse: prototype recursively defined inner Record2 type
2014-10-13 10:10:46 +02:00
7fde47c48b
No more JacobianTA typedefs -> all use Jacobian<T,A> now.
2014-10-13 09:25:06 +02:00
7848d74928
Detailed explanation of recursive class composition pattern.
...
Jacobian type now defined in argument.
2014-10-13 08:49:12 +02:00
7f621af54a
Fixed bug
2014-10-13 00:57:11 +02:00
2e8d868cd2
keys have been implemented
2014-10-13 00:37:46 +02:00
a9d9fcd241
FunctionalNode inherited for all three functional ExpressionNode sub-classes
2014-10-13 00:31:03 +02:00
8100d89094
So much better as methods
2014-10-12 23:57:08 +02:00
55cc4ba56c
Switched names of fold result and meta-function that is folded over
2014-10-12 23:31:58 +02:00
ef21a4ba4a
Major re-org in preparation of recursive Functional nodes
2014-10-12 23:03:33 +02:00
408be628d2
Small change in meta-programming, big improvement in clarity
2014-10-12 22:17:21 +02:00
107bcd8bb4
Going forwards, we default to reverse :-)
2014-10-12 22:04:40 +02:00
4d1eb05c7d
Passing JacobianMap as an argument now..
2014-10-12 20:16:08 +02:00
dc541f1051
made traceSize an instance variable
2014-10-12 18:52:12 +02:00
7a5f48f6dd
Fixed typo in assert
2014-10-12 12:20:12 +02:00
fea2eb0b5f
Inlined VerticalBlockMatrix construction
2014-10-12 11:05:43 +02:00
ed62271f81
Dealing with constrained noise model
2014-10-12 10:52:07 +02:00
86d3e559e6
Merge branch 'feature/BAD' into feature/BAD_linearize
2014-10-11 23:07:40 +02:00
c9f80536c0
Added a constraint model
2014-10-11 23:07:23 +02:00
3c6f7a42e6
Merge branch 'feature/BAD' into feature/BAD_linearize: easier trace/dTdA access
2014-10-11 22:31:43 +02:00
c776e87f78
Refactoring for readability/sanity
2014-10-11 21:33:07 +02:00
0c7ea68f2f
Now overwriting linearize as preparation for direct VericalBlockMatrix
2014-10-11 17:05:53 +02:00
1bac83381f
Merge remote-tracking branch 'origin/feature/BAD_meta' into feature/BAD: Now the Record structures are recursively generated using template meta-programming, basically mpl::fold
...
Conflicts:
gtsam_unstable/nonlinear/Expression-inl.h
2014-10-11 15:20:12 +02:00
88f9a423c5
Numbered types avoid ambiguity
2014-10-11 14:19:39 +02:00
ecf6462a25
Victory!! Unit tests work!
2014-10-11 13:07:58 +02:00
599e232d1d
traceSize, two tests work
2014-10-11 12:11:22 +02:00
9585823d5d
...but works with correct size !
2014-10-11 11:32:52 +02:00
deed7b8018
Unary prints, but still-faults downstream
2014-10-11 11:30:06 +02:00
05f78b6dca
Re-factor, allow traceExecution
2014-10-11 11:29:42 +02:00
1f692638f5
Accessing matrices works
2014-10-11 11:04:39 +02:00
69b69a0bc8
placement new works! And sophisticated Trace::print
2014-10-11 11:03:35 +02:00
eef2d49e8d
First prototype, segfaults
2014-10-11 10:27:30 +02:00
e09e24964a
No need to have all of T as template parameter
2014-10-11 09:00:03 +02:00
820988b04e
Do casting inside Trace
2014-10-11 08:52:24 +02:00
52fc6f2db4
Testing old trace
2014-10-11 08:41:39 +02:00
820e9553ee
TestBinaryExpression friend
2014-10-11 08:17:46 +02:00
a2d2d82e0e
some namespace management
2014-10-11 07:39:13 +02:00
23485a0e71
New and consistent naming: ExecutionTrace = whole tree, CallRecord = local information left by the function.
2014-10-10 17:45:39 +02:00
ae93dd9869
Commented out repeated arguments
2014-10-10 13:57:37 +02:00
58bbce482d
Ternary works, same caveat
2014-10-10 13:33:13 +02:00
406467e341
Binary works, but it's ugly and does not work for repeated types
2014-10-10 13:29:56 +02:00
24714e48c5
Works for Unary !
2014-10-10 12:38:26 +02:00
f8468bd596
Recursion done
2014-10-10 12:31:40 +02:00
40fc6f5c03
Working prototype
2014-10-10 12:29:01 +02:00
dd1b931802
Successfully defined Jacobian
2014-10-10 12:03:13 +02:00
732ff54b83
More experiments
2014-10-10 11:41:01 +02:00
8e264f4289
Attempt at defining Trace recursively
2014-10-09 14:38:16 +02:00
5e5457b390
Renamed entry point to startReverseAD to emphasize it is only called once
2014-10-09 13:42:43 +02:00
563c4d214c
Renamed BADFactor -> ExpressionFactor
2014-10-09 13:00:56 +02:00
7e069191e5
Slight refactor
2014-10-09 10:58:46 +02:00
a38a0ae9e1
Some comments
2014-10-09 00:21:10 +02:00
9ebe1e6d10
Super-speedup by specializing to 2-dimensional output (for now). Using some template magic.
2014-10-08 23:50:17 +02:00
abb92632b8
Empty derived destructors are not needed
2014-10-08 17:32:46 +02:00
6a1bc6e242
Documentation
2014-10-08 17:28:33 +02:00
ce2dcaeb3b
Tagged union, lightweight
2014-10-08 15:39:59 +02:00
390842e1f7
Put Trace in front
2014-10-08 13:58:15 +02:00
ba9faa68b6
New Leaf/noise tests
2014-10-08 13:56:54 +02:00
c4a92acde1
Avoid argument temporaries
2014-10-07 19:35:44 +02:00
Jing Dong
Renaud Dube
dellaert
Mike Bosse
Sungtae An