final

app.py

@@ -256,8 +256,8 @@ def _background_bootstrap():
             import sys
             argv_bak = sys.argv
             try:
-                # Use official splits from nondisjoint/ and disjoint/ folders
-                sys.argv = ["prepare_polyvore.py", "--root", ds_root]
+                # Use official splits from nondisjoint/ and disjoint/ folders with default size limit (2000 samples)
+                sys.argv = ["prepare_polyvore.py", "--root", ds_root, "--max_samples", "2000"]
                 prepare_main()
             finally:
                 sys.argv = argv_bak
@@ -676,7 +676,7 @@ with gr.Blocks(fill_height=True, title="Dressify - Advanced Outfit Recommendatio
     
     with gr.Row():
         gr.Markdown("#### 📊 **Current Behavior**")
-        gr.Markdown("• **Bootstrap**: Downloads full dataset (53K outfits) - this is necessary\n• **Training**: Uses limited samples based on your selection\n• **Apply Button**: Regenerates splits with your selected size limit")
+        gr.Markdown("• **Bootstrap**: Downloads full dataset (53K outfits) + generates splits with **2000 samples by default**\n• **Training**: Uses 2000 samples (ultra-fast testing!)\n• **Apply Button**: Regenerates splits with your selected size limit")
     
     with gr.Row():
         global_dataset_size = gr.Dropdown(
@@ -692,7 +692,7 @@ with gr.Blocks(fill_height=True, title="Dressify - Advanced Outfit Recommendatio
         
         # Current dataset info
         gr.Markdown("#### 📊 **Current Dataset Status**")
-        gr.Markdown("• **Full dataset downloaded**: 53,306 outfits (required for system)\n• **Splits generated**: Full dataset (click Apply to limit)\n• **Training will use**: Limited samples based on your selection")
+        gr.Markdown("• **Full dataset downloaded**: 53,306 outfits (required for system)\n• **Splits generated**: **2000 samples by default** (fast testing!)\n• **Training will use**: 2000 samples (ultra-fast!)\n• **Scale up**: Use Apply button to increase to larger sizes")
         
         def apply_dataset_size(size: str):
             """Apply global dataset size and regenerate splits."""