Skip to content

Commit c880d30

Browse files
add readme
1 parent 2fbd118 commit c880d30

File tree

1 file changed

+49
-0
lines changed

1 file changed

+49
-0
lines changed

Samples/StyleTransfer/README.md

Lines changed: 49 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,49 @@
1+
# Real-Time Style Transfer Sample
2+
3+
This UWP application uses the [Microsoft.AI.MachineLearning](https://www.nuget.org/packages/Microsoft.AI.MachineLearning/) Nuget pacakge to perform style transfer on user-provided input images or web camera streams.
4+
The VideoEffect/StyleTranfserEffectCpp project implements the (IBasicVideoEffect)[https://docs.microsoft.com/en-us/uwp/api/windows.media.effects.ibasicvideoeffect?view=winrt-19041] interface in order to create a video effect that can be plugged in to the media streaming pipeline.
5+
6+
For how-tos, tutorials and additional information, see the [Windows ML documentation](https://docs.microsoft.com/windows/ai/).
7+
To learn more about creating custom video effects, see [this walkthrough](https://docs.microsoft.com/en-us/windows/uwp/audio-video-camera/custom-video-effects).
8+
9+
## Building the Sample
10+
1. If you download the samples ZIP, be sure to unzip the entire archive, not just the folder with
11+
the sample you want to build.
12+
2. Start Microsoft Visual Studio 2017 and select **File** \> **Open** \> **Project/Solution**.
13+
### Build the Video Effect
14+
3. Starting in the folder where you unzipped the samples, go to the Samples subfolder, then the
15+
subfolder for this specific sample (eg. StyleTranfer). Navigate to the VideoEffect/StyleTranferEffectCpp and open the .sln file.
16+
4. Confirm that you are set for the right configuration and platform (eg. Debug, x64).
17+
5. Build the solution (Ctrl+Shift+B).
18+
6. Take note of where the .winmd file is built to (eg. StyleTransferEffectCpp/x64/Debug/StyleTransferEffectCpp.winmd).
19+
### Build the Sample App
20+
7. Open a new Visual Studio window and select **File** \> **Open** \> **Project/Solution**.
21+
8. Starting in the folder where you unzipped the samples, go to the Samples suboflder, then the subfolder for this specific example (eg. StyleTransfer).
22+
Open the Visual Studio (.sln) file.
23+
9. In the Solution Explorer, right-click on the References tab and select "Add Reference..."
24+
10. Click Browse and navigate to the .winmd file you built in the previous section (eg. StyleTransferEffectCpp/x64/Debug/StyleTransferEffectCpp.winmd). Click OK.
25+
11. You should now be able to run the sample app!
26+
27+
## Requirements
28+
29+
- [Visual Studio 2017 - 15.4 or higher](https://developer.microsoft.com/en-us/windows/downloads)
30+
- [Windows 10 - Build 17763 or higher](https://www.microsoft.com/en-us/software-download/windowsinsiderpreviewiso)
31+
- [Windows SDK - Build 17763 or higher](https://www.microsoft.com/en-us/software-download/windowsinsiderpreviewSDK)
32+
- [Microsoft.AI.MachineLearning Nuget package- version 1.4.0 or higher](https://www.nuget.org/packages/Microsoft.AI.MachineLearning/)
33+
34+
## Contributing
35+
36+
We're always looking for your help to fix bugs and improve the samples. Create a pull request, and we'll be happy to take a look.
37+
38+
This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
39+
For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or
40+
contact [[email protected]](mailto:[email protected]) with any additional questions or comments.
41+
42+
## License
43+
44+
MIT. See [LICENSE file](https://github.com/Microsoft/Windows-Machine-Learning/blob/master/LICENSE).
45+
46+
The machine learning models in this sample are used with permission from Justin Johnson.
47+
For additional information on these models, refer to:
48+
- [Fast-neural-style GitHub repo](https://github.com/jcjohnson/fast-neural-style)
49+
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://cs.stanford.edu/people/jcjohns/papers/eccv16/JohnsonECCV16.pdf)

0 commit comments

Comments
 (0)