Timeline for Using Mathematica wlnet model in C++
Current License: CC BY-SA 3.0
24 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 22, 2017 at 22:14 | answer | added | tonegas | timeline score: 1 | |
| Oct 11, 2017 at 7:44 | history | edited | partida |
edited tags
|
|
| Oct 11, 2017 at 7:38 | vote | accept | partida | ||
| Oct 11, 2017 at 6:52 | history | edited | partida | CC BY-SA 3.0 |
added 63 characters in body
|
| Oct 11, 2017 at 6:50 | answer | added | partida | timeline score: 5 | |
| Sep 2, 2017 at 10:42 | history | edited | partida | CC BY-SA 3.0 |
added 11 characters in body
|
| Sep 2, 2017 at 10:34 | history | edited | partida | CC BY-SA 3.0 |
added 127 characters in body
|
| Sep 2, 2017 at 9:12 | history | edited | partida | CC BY-SA 3.0 |
deleted 483 characters in body
|
| Aug 16, 2017 at 13:30 | answer | added | Taliesin Beynon | timeline score: 6 | |
| Jul 17, 2017 at 9:02 | history | edited | partida | CC BY-SA 3.0 |
added 46 characters in body; edited tags
|
| Jul 14, 2017 at 3:22 | comment | added | partida | mxnet is so diffcult to install on windows... | |
| Jul 14, 2017 at 1:18 | comment | added | partida | @Szabolcs Thank you.I try | |
| Jul 13, 2017 at 12:43 | comment | added | Szabolcs | There are many that can be used from C++, including MXNet, which Mathematica's neural net framework is based on. It was said that Mathematica would get support for MXNet's format. If your only criterion is really that the framework should have a C++ interface, take a look at MXNet ... | |
| Jul 13, 2017 at 12:38 | comment | added | partida | it seems Caffe supports C++ well.I am now seeking how to use this way now... | |
| Jul 13, 2017 at 12:33 | comment | added | Szabolcs | Then you would probably want to use an existing deep learning framework. You need to choose one first (based on whatever criteria are relevant for your application), and then ask about how to export the network to that one. | |
| Jul 13, 2017 at 12:22 | history | edited | LCarvalho | CC BY-SA 3.0 |
added 93 characters in body
|
| Jul 13, 2017 at 10:34 | comment | added | partida | It means load the net and use it to predict on new data repeatedly.This process will insert in a Visual Studio project. | |
| Jul 13, 2017 at 10:32 | history | edited | partida | CC BY-SA 3.0 |
deleted 45 characters in body; edited tags
|
| Jul 13, 2017 at 9:23 | comment | added | Szabolcs | Can you elaborate on what exactly you mean by "using" the network in C++? | |
| Jul 13, 2017 at 9:10 | history | edited | partida | CC BY-SA 3.0 |
added 58 characters in body; edited tags
|
| Jul 13, 2017 at 8:05 | history | tweeted | twitter.com/StackMma/status/885409902855725057 | ||
| Jul 13, 2017 at 6:55 | comment | added | Sascha |
I'd reckon .wlnet is only intended as a format for use in Mathematica itself. Exporting your net to MXNet (which is what Mathematica's implementation of Neural Nets is based on) is a more feasible approach. There are two questions already about exporting to MXNet but from what I have taken from them currently the exporter is broken.
|
|
| Jul 13, 2017 at 6:02 | history | edited | partida | CC BY-SA 3.0 |
added 3 characters in body
|
| Jul 13, 2017 at 5:34 | history | asked | partida | CC BY-SA 3.0 |