WhatDoWeSee / index.html
StephanMeijer's picture
EfficientNetV2-B0 v0.4.0 as default; v0.4.0-rc.1 out of the menu
803273b verified
Raw History Blame Contribute Delete
2.26 kB
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>WhatDoWeSee</title>
<link rel="stylesheet" href="style.css" />
<script src="https://cdn.jsdelivr.net/npm/onnxruntime-web@1.20.1/dist/ort.min.js"></script>
<script type="module" src="app.js"></script>
</head>
<body>
<main>
<header>
<h1>WhatDoWeSee</h1>
<p class="lede">
Drop an image and a small model tags what is visible in it: people, text, charts, maps, aerial views
and more. It runs <strong>in your browser</strong>: your image is never uploaded.
</p>
<label class="model">
Model
<select id="model"></select>
</label>
</header>
<section class="work">
<div id="drop" class="drop" tabindex="0" role="button" aria-label="Choose or drop an image">
<div id="hint" class="hint">
<strong id="hint-title">Drop an image here</strong>
<span id="hint-sub">or click to choose one, or paste with Ctrl+V</span>
</div>
<img id="preview" alt="The image being tagged" hidden />
<input id="file" type="file" accept="image/*" hidden />
</div>
<div class="results" aria-live="polite">
<p id="status" class="status">Loading the model…</p>
<ul id="present" class="chips"></ul>
<table id="all" hidden>
<thead>
<tr>
<th scope="col">Attribute</th>
<th scope="col">Probability <span class="muted">(│ = threshold)</span></th>
<th scope="col" class="num">%</th>
</tr>
</thead>
<tbody id="rows"></tbody>
</table>
</div>
</section>
<footer>
<p>
Model:
<a id="model-link" href="https://huggingface.co/StephanMeijer/WhatDoWeSee-EfficientNetV2-B0">model card</a>
· Apache-2.0 · runs with <a href="https://onnxruntime.ai">ONNX Runtime Web</a>. The browser resizes the
image itself, so scores can differ slightly from the Python reference.
</p>
</footer>
</main>
</body>
</html>