Skip to content

Commit

Permalink
Merge branch 'gh-pages' of github.com:neuroneural/AML into gh-pages
Browse files Browse the repository at this point in the history
  • Loading branch information
@sergeyplis
sergeyplis committed May 24, 2024
2 parents a29fba1 + 31f7851 commit f47d4b1
Show file tree
Hide file tree
Showing 6 changed files with 24 additions and 13 deletions.
37 changes: 24 additions & 13 deletions cs8850_23_CNN.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -74,7 +74,18 @@ <h3>Outline for the lecture</h3>
<section>
<h2>Convolutions what?</h2>
</section>
<section data-background="figures/convolution.gif" data-background-size="contain">
</section>
<section data-background="figures/convolution_2.gif" data-background-size="contain" data-background-repeat="repeat">
</section>
<section data-background="figures/convolution_3.gif" data-background-size="contain" data-background-repeat="repeat">
</section>
<section data-background="figures/convolution_4.gif" data-background-size="contain" data-background-repeat="repeat">
</section>
<section data-background="figures/convolution_matching.gif" data-background-size="contain" data-background-repeat="repeat">
</section>
</section>


<!-- --------------------------------------------------------------------------->
<section>
Expand Down Expand Up @@ -577,7 +588,7 @@ <h2>Semantic segmentation with twists</h2>
<h2>deep learning standard: U-net</h2>
<img class="stretch" style="border:0; box-shadow: 0px 0px 0px
rgba(150, 150, 255, 0.8);" width="250"
src="figures_ccd/unet_arc.png" alt="david">
src="figures/unet_arc.png" alt="david">
<p>

<div class='slide-footer'>
Expand All @@ -592,7 +603,7 @@ <h2>deep learning standard: U-net</h2>
<h2>deep learning standard: U-net</h2>
<img class="stretch" style="border:0; box-shadow: 0px 0px 0px
rgba(150, 150, 255, 0.8);" width="250"
src="figures_ccd/unet_table.png" alt="david">
src="figures/unet_table.png" alt="david">
<p>
<div class='slide-footer'>
Ronneberger et al. U-net: Convolutional networks for
Expand All @@ -607,7 +618,7 @@ <h2>deep learning standard: U-net</h2>
<h2>comparison on the brain segmentation task</h2>
<img class="stretch" style="border:0; box-shadow: 0px 0px 0px
rgba(150, 150, 255, 0.8);" width="250"
src="figures_ccd/tasks.png" alt="david">
src="figures/tasks.png" alt="david">
</section>

<section>
Expand All @@ -624,10 +635,10 @@ <h2>state of the art: freesurfer</h2>

<section>
<h2>Meshnet</h2>
<img src="figures_ccd/dilation.png" style="border:0; box-shadow: 0px
<img src="figures/dilation.png" style="border:0; box-shadow: 0px
0px 0px rgba(150, 150, 255, 0.8);float: left;"
alt="Websocket" width="40%">
<img src="figures_ccd/mn1.png" style="border:0; box-shadow: 0px
<img src="figures/mn1.png" style="border:0; box-shadow: 0px
0px 0px rgba(150, 150, 255, 0.8);float: right;"
alt="Websocket" width="35%"
>
Expand Down Expand Up @@ -657,7 +668,7 @@ <h2>Meshnet</h2>
<section>
<h2>Meshnet</h2>

<img src="figures_ccd/mntable.png" style="border:0; box-shadow: 0px
<img src="figures/mntable.png" style="border:0; box-shadow: 0px
0px 0px rgba(150, 150, 255, 0.8);float: right;"
alt="Websocket" width="60%"
>
Expand All @@ -678,7 +689,7 @@ <h2>Meshnet</h2>

<section>
<h2>Meshnet</h2>
<img src="figures_ccd/mnpipeline.png" style="border:0; box-shadow: 0px
<img src="figures/mnpipeline.png" style="border:0; box-shadow: 0px
0px 0px rgba(150, 150, 255, 0.8);"
alt="Websocket" class="stretch"
>
Expand All @@ -691,7 +702,7 @@ <h2>Meshnet</h2>

<section>
<h2>Meshnet</h2>
<img src="figures_ccd/mnexample.png" style="border:0; box-shadow: 0px
<img src="figures/mnexample.png" style="border:0; box-shadow: 0px
0px 0px rgba(150, 150, 255, 0.8);"
alt="Websocket" class="stretch"
>
Expand All @@ -706,32 +717,32 @@ <h2>Meshnet</h2>
<h3>(often) better than the teacher</h3>
<img class="stretch" style="border:0; box-shadow: 0px 0px 0px
rgba(150, 150, 255, 0.8);" width="700"
src="figures_ccd/MN_examples.png" alt="loop">
src="figures/MN_examples.png" alt="loop">
</section>

<section>
<h3>multimodal is straightforward</h3>
<img class="stretch" style="border:0; box-shadow: 0px 0px 0px
rgba(150, 150, 255, 0.8);" width="700"
src="figures_ccd/MeshNet_multi.png" alt="loop">
src="figures/MeshNet_multi.png" alt="loop">
</section>

<section>
<h3>better than the human (sometimes)</h3>
<img class="stretch" style="border:0; box-shadow: 0px 0px 0px
rgba(150, 150, 255, 0.8);" width="700"
src="figures_ccd/mnhuman.png" alt="loop">
src="figures/mnhuman.png" alt="loop">
</section>

<section>
<h3>better than U-net</h3>
<img class="stretch" style="border:0; box-shadow: 0px 0px 0px
rgba(150, 150, 255, 0.8);"
src="figures_ccd/mnvsunet.png" alt="loop">
src="figures/mnvsunet.png" alt="loop">
</section>


<section data-background-video="figures_ccd/combined.mp4" data-background-size="contain" data-background-video-loop=true>
<section data-background-video="figures/combined.mp4" data-background-size="contain" data-background-video-loop=true>
</section>
</section>

Expand Down
Binary file added figures/convolution.gif
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added figures/convolution_2.gif
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added figures/convolution_3.gif
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added figures/convolution_4.gif
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added figures/convolution_matching.gif
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

0 comments on commit f47d4b1

Please sign in to comment.