prediction image update

README.md

@@ -1,6 +1,6 @@
 # Tension Board 2: Predicting Climbing Route Difficulty from Board Data
 
-I recently got into *board climbing*, and have been enjoying using the <a href="https://tensionclimbing.com/products/tension-board-2">Tension Board 2</a>. I've been climbing on the 12ftx12ft (mirrored) that is available at my local gym, and I've never felt that the phrase "*it hurts so good*" would be so apt. As such, I decided to do an in depth analysis of available data. See also an <a href="https://github.com/psark007/Kilter-Board-Analysis">analysis of the Kilter Board</a>.
+I recently got into *board climbing*, and have been enjoying using the <a href="https://tensionclimbing.com/products/tension-board-2">Tension Board 2</a>. I've been climbing on the 12ftx12ft (mirrored) that is available at my local gym, and I've never felt that the phrase "*it hurts so good*" would be so apt. As such, I decided to do an in depth analysis of available data. See also an <a href="https://gitlab.com/psark/Kilter-Board-Analysis">analysis of the Kilter Board</a>.
 
 ![Hold Usage Heatmap](images/02_hold_stats/all_holds_all_grades_heatmap.png)
 
@@ -343,7 +343,7 @@ The model can still predict subgrades (e.g., V3 contains 6a and 6a+), but it is
 
 # Future Work
 
-* <a href="https://github.com/psark007/Kilter-Board-Analysis">~~Kilter Board analysis~~</a>
+* <a href="https://gitlab.com/psark/Kilter-Board-Analysis">~~Kilter Board analysis~~</a>
 * A unified approach to grade prediction across boards
 * Test other models
 * Better spatial features