Spaces:
Running on CPU Upgrade

osv5m commited on
Commit
7ae36e7
·
verified ·
1 Parent(s): 98bd186

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +6 -4
app.py CHANGED
@@ -38,19 +38,19 @@ IMAGE_FOLDER = './images'
38
  CSV_FILE = './select.csv'
39
  BASE_LOCATION = [0, 23]
40
  RULES = """<h1>OSV-5M (plonk)</h1>
41
- <center><img width="256" alt="Rotating globe" src="https://upload.wikimedia.org/wikipedia/commons/6/6b/Rotating_globe.gif" style="margin-bottom: 0.5em; margin-bottom: 0.5em"></center>
42
  <h2> Instructions </h2>
43
  <h3> Click on the map 🗺️ (left) to the location at which you think the image 🖼️ (right) was captured!</h3>
44
- <h3> Click "Select" to finalize your selection and then "Next" to move to the next image.</h3>
45
 
46
  <h2> AI Competitors </h2>
47
  <h3> You will compete against two AIs: <b>Plonk-AI</b> (our best model) and Baseline-AI (a simpler approach).</h3>
48
  <h3> These AIs have not been trained on any of the images you will see; in fact, they haven't seen anything within a <b>1km radius</b> of them.</h3>
49
- <h3> Like you, the AIs will need to pick up on geographic clues to pinpoint the locations of the images.</h3>
50
 
51
  <h2> Geoscore </h2>
52
  <h3> The geoscore is calculated based on how close each guess is to the true location as in Geoguessr, with a maximum of <b>5000 points</b>. </h3>
53
- <h3> We use the formula \\(g(d) = 5000 \\exp(\\frac{-d}{1492.7})\\) </h3>
54
  """
55
  css = """
56
  @font-face {
@@ -62,6 +62,7 @@ h1 {
62
  text-align: center;
63
  display:block;
64
  font-family: custom;
 
65
  }
66
  img {
67
  text-align: center;
@@ -71,6 +72,7 @@ h2 {
71
  text-align: center;
72
  display:block;
73
  font-family: custom;
 
74
  }
75
  h3 {
76
  text-align: center;
 
38
  CSV_FILE = './select.csv'
39
  BASE_LOCATION = [0, 23]
40
  RULES = """<h1>OSV-5M (plonk)</h1>
41
+ <center style="margin-bottom: 0.5em; margin-top: 0.5em"><img width="256" alt="Rotating globe" src="https://upload.wikimedia.org/wikipedia/commons/6/6b/Rotating_globe.gif"></center>
42
  <h2> Instructions </h2>
43
  <h3> Click on the map 🗺️ (left) to the location at which you think the image 🖼️ (right) was captured!</h3>
44
+ <h3 style="margin-bottom: 0.5em"> Click "Select" to finalize your selection and then "Next" to move to the next image.</h3>
45
 
46
  <h2> AI Competitors </h2>
47
  <h3> You will compete against two AIs: <b>Plonk-AI</b> (our best model) and Baseline-AI (a simpler approach).</h3>
48
  <h3> These AIs have not been trained on any of the images you will see; in fact, they haven't seen anything within a <b>1km radius</b> of them.</h3>
49
+ <h3 style="margin-bottom: 0.5em"> Like you, the AIs will need to pick up on geographic clues to pinpoint the locations of the images.</h3>
50
 
51
  <h2> Geoscore </h2>
52
  <h3> The geoscore is calculated based on how close each guess is to the true location as in Geoguessr, with a maximum of <b>5000 points</b>. </h3>
53
+ <h3> We use the formula $(g(d) = 5000 \\exp(\\frac{-d}{1492.7})$ </h3>
54
  """
55
  css = """
56
  @font-face {
 
62
  text-align: center;
63
  display:block;
64
  font-family: custom;
65
+ font-size: 2.5em;
66
  }
67
  img {
68
  text-align: center;
 
72
  text-align: center;
73
  display:block;
74
  font-family: custom;
75
+ font-size: 2em;
76
  }
77
  h3 {
78
  text-align: center;