- [MINOR] [SOURCE] [UPDATE] 1. update app.py

app.py

@@ -10,6 +10,7 @@ from decord import VideoReader
 import numpy as np
 import yaml
 import matplotlib.pyplot as plt
+import matplotlib.patches as patches
 
 from cover.datasets import UnifiedFrameSampler, spatial_temporal_view_decomposition
 from cover.models import COVER
@@ -60,18 +61,26 @@ def compare_score(score, score_list):
     return f"Better than {percentage:.0f}% videos in YT-UGC" if percentage > 50 else f"Worse than {100-percentage:.0f}% videos in YT-UGC"
 
 def create_bar_chart(scores, comparisons):
-    labels = ['Semantic', 'Technical', 'Aesthetic', 'Overall']
-    colors = ['#d62728', '#1f77b4', '#ff7f0e', '#bcbd22']
+    labels = ['Semantic', 'Aesthetic', 'Technical', 'Overall']
+    base_colors = ['#d62728', '#ff7f0e', '#1f77b4', '#bcbd22']
     
     fig, ax = plt.subplots(figsize=(10, 5))
     
-    for i, (label, score, comparison, color) in enumerate(zip(labels, scores, comparisons, colors)):
-        ax.barh(i, score, color=color, edgecolor='black')
-        ax.text(score, i, f'{score:.1f}', va='center', ha='left')
-        ax.text(5.1, i, comparison, va='center', ha='left')
+    for i, (label, score, comparison, base_color) in enumerate(zip(labels, scores, comparisons, base_colors)):
+        color = plt.cm.ScalarMappable(cmap=plt.cm.RdYlBu).to_rgba((score / 5))
+        gradient = patches.Rectangle((0, i), 5, 1, color=base_color, alpha=0.5)
+        ax.add_patch(gradient)
+        
+        # Add the actual score line
+        ax.plot([score, score], [i, i+0.9], color='black', linewidth=2)
+        
+        ax.text(score + 0.1, i + 0.5, f'{score:.1f}', va='center', ha='left', color=base_color)
+        ax.text(5.1, i + 0.5, comparison, va='center', ha='left', color=base_color)
     
     ax.set_yticks(range(len(labels)))
-    ax.set_yticklabels(labels)
+    ax.set_yticklabels(labels, color=base_colors)
+    ax.set_xticks([0, 1, 2, 3, 4, 5])
+    ax.set_xticklabels([0, 1, 2, 3, 4, 5])
     ax.set_xlim(0, 5)
     ax.set_xlabel('Score')
     
@@ -104,7 +113,6 @@ def inference_one_video(input_video):
                 sopt["clip_len"] = clip_len * 2
             if stype == 'technical':
                 sopt["aligned"] = sopt["clip_len"]
-        print(sopt["clip_len"], sopt["t_frag"])
         temporal_samplers[stype] = UnifiedFrameSampler(
             sopt["clip_len"] // sopt["t_frag"],
             sopt["t_frag"],