Update links

index.html

@@ -65,9 +65,8 @@
 Models can be fine tuned on Google Colab free T4 GPUs, but larger datasets and longer runs should run on other compute platforms.</p>
 <p dir="auto">Inference and postprocessing both benefit from CUDA GPUs.</p>
 <div class="markdown-heading" dir="auto"><h2 tabindex="-1" class="heading-element" dir="auto"><code>aigis</code> datasets</h2><a id="user-content-aigis-datasets" class="anchor" aria-label="Permalink: aigis datasets" href="#aigis-datasets"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z"></path></svg></a></div>
-<p dir="auto">Explore our two featured example datasets using a <a href="https://felt.com/map/Sydney-Buildings-6drWs3o9ARViitVdt6qp60A?loc=-33.8282,150.8961,10.93z" rel="nofollow">Felt map</a>.</p>
-<p dir="auto"><a target="_blank" rel="noopener noreferrer" href="/aigis/docs/content/Felt_Map.jpeg"><img src="/aigis/docs/content/Felt_Map.jpeg" alt="felt_map" style="max-width: 100%;"></a>
-To load the matching NSW SixMaps aerial photography you have to click 1. background layers, then select 2. NSW SixMaps, as in the image above.</p>
+<p dir="auto">Explore our two featured example datasets using a <a href="https://pmtiles.io/#url=https%3A%2F%2Fhuggingface.co%2Fdatasets%2FSIH%2FGreater-Sydney-Trees-Buildings%2Fresolve%2Fmain%2Fgreater-sydney-trees-buildings.pmtiles&map=13.44/-33.86252/151.20767" rel="nofollow">PMTiles.io map</a> or <a href="https://sydney-informatics-hub.github.io/aigis/map/#15.75/-33.889826/151.185079">overlaid with NSW Sixmap aerial imagery</a>.</p>
+<p dir="auto">The datasets themselves are available on <a href="https://huggingface.co/datasets/SIH/Greater-Sydney-Trees-Buildings">Huggingface Datasets</a></p>  
 <div class="markdown-heading" dir="auto"><h3 tabindex="-1" class="heading-element" dir="auto">Building Segmentation</h3><a id="user-content-building-segmentation" class="anchor" aria-label="Permalink: Building Segmentation" href="#building-segmentation"><svg class="octicon octicon-link" viewBox="0 0 16 16" version="1.1" width="16" height="16" aria-hidden="true"><path d="m7.775 3.275 1.25-1.25a3.5 3.5 0 1 1 4.95 4.95l-2.5 2.5a3.5 3.5 0 0 1-4.95 0 .751.751 0 0 1 .018-1.042.751.751 0 0 1 1.042-.018 1.998 1.998 0 0 0 2.83 0l2.5-2.5a2.002 2.002 0 0 0-2.83-2.83l-1.25 1.25a.751.751 0 0 1-1.042-.018.751.751 0 0 1-.018-1.042Zm-4.69 9.64a1.998 1.998 0 0 0 2.83 0l1.25-1.25a.751.751 0 0 1 1.042.018.751.751 0 0 1 .018 1.042l-1.25 1.25a3.5 3.5 0 1 1-4.95-4.95l2.5-2.5a3.5 3.5 0 0 1 4.95 0 .751.751 0 0 1-.018 1.042.751.751 0 0 1-1.042.018 1.998 1.998 0 0 0-2.83 0l-2.5 2.5a1.998 1.998 0 0 0 0 2.83Z"></path></svg></a></div>
 <p dir="auto">We've used the full <code>aigis</code> toolkit to fine tune segmentation models to detect and segment building outlines in aerial imagery. Our fine tuned model was then run on 37,000 high reslution aerial images across the entire Greater Sydney Urban area in New South Wales, Australia.</p>
 <p dir="auto">Our models's predictions are available as a shapefile in GeoParquet, with almost one million buildings.</p>