Age | Commit message (Collapse) | Author | |
---|---|---|---|
2017-02-07 | Merge pull request #139 from twitter-forks/pcall-graphvizHEADmaster | Soumith Chintala | |
prevent graphiz error for continuous integration | |||
2017-02-07 | prevent graphiz error for continuous integration | Nicholas Leonard | |
2016-10-28 | Merge pull request #132 from BTNC/master | Soumith Chintala | |
fix rockspec for windows | |||
2016-10-28 | fix rockspec for windows | Rui Guo | |
2016-09-13 | Merge pull request #130 from abursuc/patch-1 | Soumith Chintala | |
Typo in example code in README | |||
2016-09-13 | Typo in example code in README | Andrei Bursuc | |
2016-08-04 | overload operator __unm and __sub to support module chaining (#113) | WenLi Zhuang | |
* add operator support * Update README.md | |||
2016-07-27 | Merge pull request #126 from torch/typefix | Soumith Chintala | |
fix for :type() to typecast the children as well | |||
2016-07-27 | fix for :type() to typecast the children as welltypefix | soumith | |
2016-07-27 | add one more assertion in test | Soumith Chintala | |
2016-07-27 | type fix for forwardnodes | Soumith Chintala | |
2016-06-07 | Quick fix for type. (#118) | Jonathan Tompson | |
2016-05-19 | README tweak. (#115) | Jonathan Tompson | |
2016-04-28 | Fix to make compatible with MarginRankingCriterion (#108) | Abhi Agg | |
* Fix to make compatible with MarginRankingCriterion | |||
2016-04-28 | Add :replace() for gModule | Adam Paszke | |
2016-04-28 | fixes for lua 5.2 | Soumith Chintala | |
2016-04-26 | Merge pull request #112 from rohanpadhye/module-type | Soumith Chintala | |
Return type of gModule when no arguments are passed to method: type(). | |||
2016-04-24 | Returning the module's type to conform to torch/nn#691 | Rohan Padhye | |
2016-03-09 | Merge pull request #106 from barwimbe/patch-1 | Soumith Chintala | |
Improved error message (expecting table of inputs) | |||
2016-03-09 | Improved error message (expecting table of inputs) | Marek | |
I think a better error message. Currently if I pass in 2 comma separated inputs the error is: "Error, expecting 2 inputs". After this change it will be "Error, expecting table of 2 inputs.". | |||
2016-03-08 | Merge pull request #103 from fbesse/gradoutput_zero_optim | Soumith Chintala | |
Added optimisation to bypass the buffer allocation when all but one g… | |||
2016-03-04 | Merge pull request #104 from apaszke/master | Soumith Chintala | |
Clear tensors in a whole graph on :clearState() | |||
2016-03-03 | Clear tensors in a whole graph on :clearState() | Adam Paszke | |
2016-03-03 | Merge pull request #105 from malcolmreynolds/remove_local_istensor | Soumith Chintala | |
Remove the istensor local in nesting.lua. | |||
2016-03-03 | Remove the istensor local in nesting.lua. | Malcolm Reynolds | |
This enables support for other Tensor implementations, which may provide a new version of torch.isTensor but only be required after nngraph. | |||
2016-02-16 | Added optimisation to bypass the buffer allocation when all but one ↵ | Frederic Besse | |
gradOutput are zero one-element tensors. | |||
2016-02-13 | Merge pull request #101 from torch/require | Soumith Chintala | |
include and paths.dofile -> require | |||
2016-02-13 | include and paths.dofile -> requirerequire | Soumith Chintala | |
2016-01-29 | Merge pull request #99 from malcolmreynolds/safer_copynested | koray kavukcuoglu | |
Safer copynested | |||
2016-01-29 | avoid string concatenation error when key type is not string or number | Malcolm Reynolds | |
2016-01-29 | Change copyNested to error when there are extra keys in output. | Malcolm Reynolds | |
2016-01-25 | Merge pull request #98 from malcolmreynolds/remove_zeroing_optimisation | koray kavukcuoglu | |
Don't bother filling a Tensor with zero right before we copy into it | |||
2016-01-25 | Merge pull request #97 from malcolmreynolds/detect_dangling_connections | koray kavukcuoglu | |
Store a reverse mapping when wiring together graph, detect unused nodes. | |||
2016-01-25 | Don't bother filling a Tensor with zero right before we copy into it | Malcolm Reynolds | |
2016-01-20 | Store a reverse mapping when wiring together graph, detect unused nodes. | Malcolm Reynolds | |
The connectivity checking code was previously unable to detect the following error case: local input = nn.Identity()() local usedOutput = nn.Linear(20, 10)(input) local unusedOutput = nn.Linear(20, 10)(input) local gmod = nn.gModule({input}, {usedOutput}) With this fix, when gModule is called it will throw an error, because of unusedOutput. This is a backwards incompatible change, but I feel that the current flexibility is error prone, and I can't see any advantage to it. We have flushed out a couple of bugs in internal code with this change. | |||
2015-12-19 | Merge pull request #96 from fidlej/topic_split_one | Soumith Chintala | |
Allow to do node:split(1). | |||
2015-12-18 | Allow to do node:split(1). | Ivo Danihelka | |
2015-11-24 | Merge pull request #94 from LeeTaewoo/patch-1 | koray kavukcuoglu | |
Minor typo | |||
2015-11-24 | Minor typo | Taewoo Lee | |
2015-11-22 | Merge pull request #93 from malcolmreynolds/improve_error_messages | koray kavukcuoglu | |
Make error messages clearer, disallow empty table in inputs. | |||
2015-11-20 | Fix for Lua 5.2+ which removed table.maxn | Malcolm Reynolds | |
2015-11-19 | Make error messages clearer, disallow empty table in inputs. | Malcolm Reynolds | |
This is intended to address the common class of errors I see where people make a mistake connecting up their modules, but the error message is either unclear, or doesn't point towards where the mistake actually is. The 'what is this in the input' is now explicit about what the problem is, and if people pass in a nn.Module (meaning they probably forgot a set of parentheses) instead of a nngraph.Node, we say this explicitly. The '1 of split(2) outputs unused' (which previously provided no information about which split was incorrect) now includes file / line number of both the place where the Node was constructed, and the place where :split() was called. Hopefully this should reduce debugging time drastically. Finally, I have disallow passing an empty table as the input connections, ie 'nn.Identity()({})' will error. I cannot see a use case for this (if you have no input connections, just leave the second parens empty). The risk of this is when people do 'nn.Identity()({variableWithTypo})', thinking they have made a connection but actually they haven't. This is likely to cause errors much later on, whereas with this commit it errors straight away. This *could* break existing code, but theres an easy to apply fix that needs to be done at each callsite. Koray has approved this restriction to the API, but I appreciate others may have a view here.. | |||
2015-11-12 | travis fixes | soumith | |
2015-11-12 | adding graphviz LD path to travis | soumith | |
2015-11-10 | fix path in travis | soumith | |
2015-11-10 | contbuild for Lua51, Lua52 | soumith | |
2015-11-10 | install manual version of graphviz in travis | soumith | |
2015-11-10 | adding graphviz to travis | Soumith Chintala | |
2015-11-04 | adding Lua52 compatibility fixes | Soumith Chintala | |
2015-10-26 | kick contbuild | Soumith Chintala | |