diff options
| author | Soumith Chintala <soumith@fb.com> | 2016-06-02 00:30:15 +0300 |
|---|---|---|
| committer | Soumith Chintala <soumith@fb.com> | 2016-06-02 00:30:15 +0300 |
| commit | 866c5663b93148152afacab091776004966b7f8f (patch) | |
| tree | d3e6a620f2db219e9c586d0846c8e1830f798a2e | |
| parent | 7ebc02481456fc9b952dc1e30c1afe9cfdf32d1c (diff) | |
stuff
| -rw-r--r-- | blog/_posts/2016-06-01-deep-fun-with-opencv.md | 13 | ||||
| -rw-r--r-- | blog/_posts/images/opencv_age.png | bin | 0 -> 1114008 bytes | |||
| -rw-r--r-- | blog/_posts/images/opencv_face1.png | bin | 0 -> 164278 bytes | |||
| -rw-r--r-- | blog/_posts/images/opencv_face2.png | bin | 0 -> 224443 bytes | |||
| -rw-r--r-- | blog/_posts/images/opencv_face3.png | bin | 0 -> 108844 bytes | |||
| -rw-r--r-- | blog/_posts/images/opencv_face4.png | bin | 0 -> 113286 bytes |
6 files changed, 7 insertions, 6 deletions
diff --git a/blog/_posts/2016-06-01-deep-fun-with-opencv.md b/blog/_posts/2016-06-01-deep-fun-with-opencv.md index cac16bf..fc958a5 100644 --- a/blog/_posts/2016-06-01-deep-fun-with-opencv.md +++ b/blog/_posts/2016-06-01-deep-fun-with-opencv.md @@ -4,6 +4,7 @@ title: Deep Fun with OpenCV and Torch comments: True author: egor-burkov excerpt: In this post, we'll have some fun with OpenCV 3.0 + Torch to build live demos of Age & Gender Classification, NeuralStyle, NeuralTalk and live Image classification. +picture: https://raw.githubusercontent.com/torch/torch.github.io/master/blog/_posts/images/opencv_age.png --- <!---# Deep Fun with OpenCV and Torch--> @@ -111,7 +112,7 @@ Of course, this is quite an inefficient way of face detection provided just to b The entire code is [available on GitHub](https://github.com/szagoruyko/torch-opencv-demos/blob/master/age_gender/demo.lua). Here's a sample from IMAGINE Lab by Sergey Zagoruyko: - + [And here is is a heavy just-for-fun GIF](https://raw.githubusercontent.com/torch/torch.github.io/master/blog/_posts/images/opencv_age.gif). @@ -133,10 +134,10 @@ Here is another code sample demonstrating some of the above features. This is an For speed, the face descriptor we use is the most lightweight (~3.7 millions of parameters) of [OpenFace](http://cmusatyalab.github.io/openface/) models, which are based on the CVPR 2015 paper [FaceNet: A Unified Embedding for Face Recognition](http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/1A_089.pdf). It was pre-trained with a combination of [FaceScrub](http://vintage.winklerbros.net/facescrub.html) and [CASIA-WebFace](http://arxiv.org/abs/1411.7923) face recognition datasets. - - - - + + + + Let us introduce how OpenCV interface for Lua looks like in this case. As usual, there's a single `require` for every separate OpenCV package: @@ -271,4 +272,4 @@ Sergey Zagoruyko for putting up most of the demo code and creating sample screen Soumith Chintala for the support from Torch side. Everyone who contributed and contributes to the project by making PRs and helping catch bugs. -This project was created and is maintained in [VisionLabs](http://visionlabs.ru/) by [Egor Burkov](https://github.com/shrubb).
\ No newline at end of file +This project was created and is maintained in [VisionLabs](http://visionlabs.ru/) by [Egor Burkov](https://github.com/shrubb). diff --git a/blog/_posts/images/opencv_age.png b/blog/_posts/images/opencv_age.png Binary files differnew file mode 100644 index 0000000..59885eb --- /dev/null +++ b/blog/_posts/images/opencv_age.png diff --git a/blog/_posts/images/opencv_face1.png b/blog/_posts/images/opencv_face1.png Binary files differnew file mode 100644 index 0000000..c3ae18f --- /dev/null +++ b/blog/_posts/images/opencv_face1.png diff --git a/blog/_posts/images/opencv_face2.png b/blog/_posts/images/opencv_face2.png Binary files differnew file mode 100644 index 0000000..80426f6 --- /dev/null +++ b/blog/_posts/images/opencv_face2.png diff --git a/blog/_posts/images/opencv_face3.png b/blog/_posts/images/opencv_face3.png Binary files differnew file mode 100644 index 0000000..2d24987 --- /dev/null +++ b/blog/_posts/images/opencv_face3.png diff --git a/blog/_posts/images/opencv_face4.png b/blog/_posts/images/opencv_face4.png Binary files differnew file mode 100644 index 0000000..1c0875c --- /dev/null +++ b/blog/_posts/images/opencv_face4.png |
