-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
940d335
commit 7495ac5
Showing
8 changed files
with
81 additions
and
101 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -44,16 +44,40 @@ | |
<script src="https://unpkg.com/[email protected]/dist/Prando.umd.js"></script> | ||
|
||
<div> | ||
<div style="margin: 10px; border-radius: 10px; box-shadow: 0px 2px 2px rgba(0,0,0,0.20); background: url(/img/warp-sti.jpg); backround-repeat: no-repeat; padding: 20px;"> | ||
<h1><a href="/">warping-machine</a></h1> | ||
<div style="margin: 10px; border-radius: 10px; box-shadow: 0px 2px 2px rgba(0,0,0,0.20); background: rgb(229,119, 1); padding: 20px;"> | ||
<h1><a href="/">questionable-machine</a></h1> | ||
</div> | ||
|
||
<div class="VerticalSection" style="display: flex; flex-direction: row;"> | ||
|
||
<div class="Panel"> | ||
<div class="Panel-content"> | ||
<h2>1. Image model</h2> | ||
<div class="Panel-text">First, load an image model created in <a target="_blank" href="https://teachablemachine.withgoogle.com/train/image">Teachable Machine</a>. This only accepts zip files uploaded locally.</div> | ||
<h2>1. Training dataset</h2> | ||
<div class="Panel-text">First, load the project that you used to create your model in <a target="_blank" href="https://teachablemachine.withgoogle.com/train/image">Teachable Machine</a>.</div> | ||
</div> | ||
<div class="Panel-actions"> | ||
<div class="Status" id="training-status"></div> | ||
<div class="File Button"> | ||
<div class="File-caption"> | ||
<svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg"> | ||
<path fill-rule="evenodd" clip-rule="evenodd" d="M12 6H20C21.1 6 22 6.9 22 8V18C22 19.1 21.1 20 20 20H4C2.9 20 2 19.1 2 18L2.01 6C2.01 4.9 2.9 4 4 4H10L12 6ZM4 8V18H20V8H4Z" fill="#888"></path> | ||
</svg> | ||
Open training project | ||
</div> | ||
<input id="training-zip-input" class="fileList" type="file" accept="application/zip"> | ||
</div> | ||
<a class="ExampleLink" href="/data/training-project.zip"><svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg"> | ||
<path fill-rule="evenodd" clip-rule="evenodd" d="M13 12.17L15.59 9.59L17 11L12 16L7 11L8.41 9.59L11 12.17V4H13V12.17ZM6 15H4V18C4 19.1 4.9 20 6 20H18C19.1 20 20 19.1 20 18V15H18V18H6V15Z" fill="#888"></path> | ||
</svg> | ||
<span>Download example</span> | ||
</a> | ||
</div> | ||
</div> | ||
|
||
<div class="Panel"> | ||
<div class="Panel-content"> | ||
<h2>2. Image model</h2> | ||
<div class="Panel-text">Then, load the image model you created in <a target="_blank" href="https://teachablemachine.withgoogle.com/train/image">Teachable Machine</a>. This only accepts zip files uploaded locally.</div> | ||
</div> | ||
<div class="Panel-actions"> | ||
<div class="Status" id="model-status"></div> | ||
|
@@ -64,9 +88,9 @@ <h2>1. Image model</h2> | |
</svg> | ||
Open model.zip | ||
</div> | ||
<input id="upload-model-zip-input" class="fileList" type="file" accept="application/zip"> | ||
<input id="model-zip-input" class="fileList" type="file" accept="application/zip"> | ||
</div> | ||
<a class="ExampleLink" href="/data/example-model.zip"><svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg"> | ||
<a class="ExampleLink" href="/data/model.zip"><svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg"> | ||
<path fill-rule="evenodd" clip-rule="evenodd" d="M13 12.17L15.59 9.59L17 11L12 16L7 11L8.41 9.59L11 12.17V4H13V12.17ZM6 15H4V18C4 19.1 4.9 20 6 20H18C19.1 20 20 19.1 20 18V15H18V18H6V15Z" fill="#888"></path> | ||
</svg> | ||
<span>Download example</span> | ||
|
@@ -76,21 +100,21 @@ <h2>1. Image model</h2> | |
|
||
<div class="Panel"> | ||
<div class="Panel-content"> | ||
<h2>2. Generalization dataset</h2> | ||
<div class="Panel-text">Next, load a project from <a target="_blank" href="https://teachablemachine.withgoogle.com/train/image">Teachable Machine</a> that contains different images than what the model was trained on, but labeled with the same class names.</div> | ||
<h2>3. Concepts dataset</h2> | ||
<div class="Panel-text">Next, load a project from <a target="_blank" href="https://teachablemachine.withgoogle.com/train/image">Teachable Machine</a> that labels concepts where you want to explore bias in your model.</div> | ||
</div> | ||
<div class="Panel-actions"> | ||
<div class="Status" id="generalization-status"></div> | ||
<div class="Status" id="concepts-status"></div> | ||
<div class="File Button"> | ||
<div class="File-caption"> | ||
<svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg"> | ||
<path fill-rule="evenodd" clip-rule="evenodd" d="M12 6H20C21.1 6 22 6.9 22 8V18C22 19.1 21.1 20 20 20H4C2.9 20 2 19.1 2 18L2.01 6C2.01 4.9 2.9 4 4 4H10L12 6ZM4 8V18H20V8H4Z" fill="#888"></path> | ||
</svg> | ||
Open project.zip | ||
Open concepts project | ||
</div> | ||
<input id="upload-generalization-zip-input" class="fileList" type="file" accept="application/zip"> | ||
<input id="concepts-zip-input" class="fileList" type="file" accept="application/zip"> | ||
</div> | ||
<a class="ExampleLink" href="/data/example-generalization-project.zip"> | ||
<a class="ExampleLink" href="/data/concepts-project.zip"> | ||
<svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg"> | ||
<path fill-rule="evenodd" clip-rule="evenodd" d="M13 12.17L15.59 9.59L17 11L12 16L7 11L8.41 9.59L11 12.17V4H13V12.17ZM6 15H4V18C4 19.1 4.9 20 6 20H18C19.1 20 20 19.1 20 18V15H18V18H6V15Z" fill="#888"></path> | ||
</svg> | ||
|
@@ -101,21 +125,17 @@ <h2>2. Generalization dataset</h2> | |
|
||
<div class="Panel"> | ||
<div class="Panel-content"> | ||
<h2>3. Visualize!</h2> | ||
<div class="Panel-text">Now you can visualize how well the model did on the generalization set.<br/><br/>Scan through individual classification errors, or compare how the images appear in <a href="https://github.com/tensorflow/tfjs-models/tree/master/mobilenet" target="_blank">MobileNet</a> embedding space versus your model's embedding space.</div> | ||
<h2>4. tcav!</h2> | ||
<div class="Panel-text">...</div> | ||
</div> | ||
<div class="Panel-actions ButtonList"> | ||
<button disabled="disabled" id="inspect-button" class="Button">Browse accuracy</button> | ||
<button disabled="disabled"id="embeddings-button" class="Button">Visualize embedding space</button> | ||
<button disabled="disabled" id="embeddings-3d-button" class="Button">Visualize embeddings in 3D</button> | ||
<button disabled="disabled" id="facets-button" class="Button">Explore with Facets Dive</button> | ||
<button disabled="disabled" id="tcav-button" class="Button">go</button> | ||
</div> | ||
</div> | ||
</div> | ||
|
||
<div> | ||
<div class="Workspace" id="workspace"></div> | ||
<div id="generalization-preview"></div> | ||
</div> | ||
|
||
<div id="log"></div> | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters