diff --git a/docs/accuracy.md b/docs/accuracy.md index 21367c3..ed4a847 100644 --- a/docs/accuracy.md +++ b/docs/accuracy.md @@ -10,7 +10,7 @@ We obtain a mean accuracy of 0.8483 ± 0.0172 with an AUC of 0.923. For comparison, training with Google-scale data results in an accuracy of .9963 ± 0.009. -![](../images/nn4.v1.lfw.roc.png) +![](https://raw.githubusercontent.com/cmusatyalab/openface/master/images/nn4.v1.lfw.roc.png) This can be generated with the following commands from the root `openface` directory, assuming you have downloaded and placed the raw and diff --git a/docs/css/extra.css b/docs/css/extra.css new file mode 100644 index 0000000..8f6c171 --- /dev/null +++ b/docs/css/extra.css @@ -0,0 +1,21 @@ +div.col-md-9 h1:first-of-type { + text-align: center; + font-size: 60px; + font-weight: 300; +} + +/* div.col-md-9 p:first-of-type { */ + /* text-align: center; */ +/* } */ + +/* div.col-md-9 p.admonition-title:first-of-type { */ +/* text-align: left; */ +/* } */ + +/* div.col-md-9 h1:first-of-type .headerlink { */ +/* display: none; */ +/* } */ + +code.no-highlight { + color: black; +} \ No newline at end of file diff --git a/docs/demo-1-web.md b/docs/demo-1-web.md index 70e0e58..41bdd4c 100644 --- a/docs/demo-1-web.md +++ b/docs/demo-1-web.md @@ -5,7 +5,7 @@ for face recognition. The source is available in [demos/web](https://github.com/cmusatyalab/openface/blob/master/demos/web). - + This demo does the full face recognition pipeline on every frame. In practice, object tracking diff --git a/docs/demo-2-comparison.md b/docs/demo-2-comparison.md index 8bc463f..099f8d4 100644 --- a/docs/demo-2-comparison.md +++ b/docs/demo-2-comparison.md @@ -11,7 +11,7 @@ Eric Clapton were generated with | Lennon 1 | Lennon 2 | Clapton 1 | Clapton 2 | |---|---|---|---| -| | | | | +| | | | | The following table shows that a distance threshold of `0.5` would distinguish these two people. diff --git a/docs/demo-3-classifier.md b/docs/demo-3-classifier.md index 0595a86..fa7986f 100644 --- a/docs/demo-3-classifier.md +++ b/docs/demo-3-classifier.md @@ -41,7 +41,7 @@ Run the classifier on your images with: | Person | Image | Prediction | Confidence | |---|---|---|---| -| Carell | | SteveCarell | 0.78 | -| Adams | | AmyAdams | 0.87 | -| Lennon 1 (Unknown) | | DavidBoreanaz | 0.28 | -| Lennon 2 (Unknown) | | DavidBoreanaz | 0.56 | +| Carell | | SteveCarell | 0.78 | +| Adams | | AmyAdams | 0.87 | +| Lennon 1 (Unknown) | | DavidBoreanaz | 0.28 | +| Lennon 2 (Unknown) | | DavidBoreanaz | 0.56 | diff --git a/docs/index.md b/docs/index.md index 600a2b5..256cce0 100644 --- a/docs/index.md +++ b/docs/index.md @@ -1,6 +1,9 @@ -# OpenFace +# OpenFace - +
+*Free and open source face recognition with +Google's FaceNet deep neural network.* +
--- @@ -82,7 +85,7 @@ image of Sylvestor Stallone from the publicly available See below for our examples for classification and similarity detection, including an online web demo. -![](../images/summary.jpg) +![](https://raw.githubusercontent.com/cmusatyalab/openface/master/images/summary.jpg) # What's in this repository? + [batch-represent](https://github.com/cmusatyalab/openface/tree/master/batch-represent): Generate representations from diff --git a/docs/models.md b/docs/models.md index 1e9ff97..7675078 100644 --- a/docs/models.md +++ b/docs/models.md @@ -34,4 +34,4 @@ Our `nn4.v1` model is from epoch 177. The LFW section above shows that this model obtains a mean accuracy of 0.8483 ± 0.0172 with an AUC of 0.923. -![](../images/nn4.v1.loss.png) +![](https://raw.githubusercontent.com/cmusatyalab/openface/master/images/nn4.v1.loss.png) diff --git a/docs/visualizations.md b/docs/visualizations.md index cdb265f..c7cee09 100644 --- a/docs/visualizations.md +++ b/docs/visualizations.md @@ -7,11 +7,11 @@ in the training and testing dataset with the most images. **Training** -![](../images/train-tsne.png) +![](https://raw.githubusercontent.com/cmusatyalab/openface/master/images/train-tsne.png) **Testing** -![](../images/val-tsne.png) +![](https://raw.githubusercontent.com/cmusatyalab/openface/master/images/val-tsne.png) These can be generated with the following commands from the root `openface` directory. @@ -37,5 +37,5 @@ The following shows the first 39 filters of the first convolutional layer on two images of John Lennon. -![](../images/nn4.v1.conv1.lennon-1.png) -![](../images/nn4.v1.conv1.lennon-2.png) +![](https://raw.githubusercontent.com/cmusatyalab/openface/master/images/nn4.v1.conv1.lennon-1.png) +![](https://raw.githubusercontent.com/cmusatyalab/openface/master/images/nn4.v1.conv1.lennon-2.png) diff --git a/mkdocs.yml b/mkdocs.yml index 7122cc8..40a9c1b 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -1,18 +1,19 @@ site_name: OpenFace -docs_dir: '.' -site_dir: /tmp/openfacesite repo_url: https://github.com/cmusatyalab/openface -theme: readthedocs +#theme: readthedocs copyright: 'Crafted by Brandon Amos at Carnegie Mellon University' +theme: simplex +extra_css: + - css/extra.css pages: -- Home: docs/index.md +- Home: index.md - Demos: - - 1 - Real-time Web: docs/demo-1-web.md - - 2 - Comparison: docs/demo-2-comparison.md - - 3 - Classifier: docs/demo-3-classifier.md -- Accuracy: docs/accuracy.md -- Usage: docs/usage.md -- Models: docs/models.md -- DNN Training: docs/training-new-models.md -- Visualizations: docs/visualizations.md -- Setup: docs/setup.md + - 1 - Real-time Web: demo-1-web.md + - 2 - Comparison: demo-2-comparison.md + - 3 - Classifier: demo-3-classifier.md +- Accuracy: accuracy.md +- Usage: usage.md +- Models: models.md +- DNN Training: training-new-models.md +- Visualizations: visualizations.md +- Setup: setup.md