Removed cards from webapp
This commit is contained in:
@@ -129,16 +129,6 @@
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div class="card note" id="data-acknowledgement-card">
|
||||
<h2>Data acknowledgement</h2>
|
||||
<p>
|
||||
Board layouts, hold metadata, and route data are derived from Tension Board 2 and Kilter Board datasets.
|
||||
This project is unaffiliated with Tension Climbing or Kilter.
|
||||
The route generator is inspired by Andrej Karpathy's
|
||||
<a href="https://github.com/karpathy/nanoGPT" target="_blank" rel="noreferrer">nanoGPT</a>.
|
||||
</p>
|
||||
</div>
|
||||
|
||||
<div class="card note" id="angle-scope-card">
|
||||
<h2>Angle scope</h2>
|
||||
<p>
|
||||
@@ -148,18 +138,14 @@
|
||||
The restriction avoids asking the models to extrapolate into sparse, noisier high-angle data where grades and route distributions are less reliable.
|
||||
</p>
|
||||
</div>
|
||||
|
||||
<div class="card note" id="edge-grade-caveat-card">
|
||||
<h2>High-grade caveat</h2>
|
||||
|
||||
<div class="card note" id="data-acknowledgement-card">
|
||||
<h2>Data acknowledgement</h2>
|
||||
<p>
|
||||
Generation and prediction are both less reliable at edge-case grades, especially around V10 and above. Those grades are rarer in the data, so the generator has weaker grade control and the predictor has less signal for accurate scoring.
|
||||
</p>
|
||||
</div>
|
||||
|
||||
<div class="card note">
|
||||
<h2>To-do</h2>
|
||||
<p>
|
||||
This demo currently focuses on the full-board layouts: Tension Board 2 Mirror 12x12 and Kilter Board Original 16x12. Other board sizes are future work.
|
||||
Board layouts, hold metadata, and route data are derived from Tension Board 2 and Kilter Board datasets.
|
||||
This project is unaffiliated with Tension Climbing or Kilter.
|
||||
The route generator is inspired by Andrej Karpathy's
|
||||
<a href="https://github.com/karpathy/nanoGPT" target="_blank" rel="noreferrer">nanoGPT</a>.
|
||||
</p>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
Reference in New Issue
Block a user