Update app.py

app.py

@@ -2,7 +2,6 @@ import torch
 import torch.nn as nn
 import torch.nn.functional as F
 import gradio as gr
-from gradio_imageslider import ImageSlider
 from PIL import Image
 import torchvision.transforms.functional as TF
 
@@ -63,7 +62,6 @@ def calc_psnr(pred, target):
 def standard_upscale(img):
     if img is None: return None, ""
         
-    # Bumped max input to 2K (2048px) for a 4K output
     max_input_dim = 2048 
     w, h = img.size
     
@@ -98,12 +96,10 @@ def benchmark_upscale(hr_img):
     hr_img = hr_img.convert('RGB')
     w, h = hr_img.size
     
-    # Enforce even dimensions so 2x scaling mathematically matches
     w = w - (w % 2)
     h = h - (h % 2)
     hr_img = hr_img.crop((0, 0, w, h))
     
-    # HR can now be 4K (4096px) because the LR input to the model will be max 2K
     max_hr_dim = 4096 
     if w > max_hr_dim or h > max_hr_dim:
         gr.Warning(f"Ground truth image exceeded the 4K ({max_hr_dim}px) limit. It has been proportionally downscaled.")
@@ -113,22 +109,18 @@ def benchmark_upscale(hr_img):
         h = h - (h % 2)
         hr_img = hr_img.resize((w, h), Image.BICUBIC)
 
-    # Create the simulated Low-Res image
     lr_w, lr_h = w // 2, h // 2
     lr_img = hr_img.resize((lr_w, lr_h), Image.BICUBIC)
     
-    # Run Inference
     lr_tensor = TF.to_tensor(lr_img).unsqueeze(0).to(device)
     hr_tensor = TF.to_tensor(hr_img).unsqueeze(0).to(device)
 
     with torch.no_grad():
         pred_tensor = model(lr_tensor).clamp(0, 1)
 
-    # Calculate PSNR
     psnr = calc_psnr(pred_tensor, hr_tensor)
     pred_img = TF.to_pil_image(pred_tensor.squeeze(0))
     
-    # Resize LR using NEAREST so it looks accurately pixelated in the slider comparison
     lr_slider_img = lr_img.resize((w, h), Image.NEAREST)
     
     details = (
@@ -138,6 +130,7 @@ def benchmark_upscale(hr_img):
         f"**Model Output & Ground Truth:** {w} x {h} ({w * h:,} pixels)"
     )
     
+    # Gradio's native ImageSlider expects a tuple of (image1, image2)
     return details, (lr_slider_img, pred_img), (hr_img, pred_img)
 
 # --- 4. GRADIO UI ---
@@ -173,10 +166,10 @@ with gr.Blocks(theme=gr.themes.Soft()) as app:
                     bm_details = gr.Markdown()
                 with gr.Column():
                     gr.Markdown("### Low-Res vs. Model Prediction")
-                    slider_lr_pred = ImageSlider(label="Left: Pixelated Low-Res | Right: FastEDSR")
+                    slider_lr_pred = gr.ImageSlider(label="Left: Pixelated Low-Res | Right: FastEDSR")
                     
                     gr.Markdown("### Ground Truth vs. Model Prediction")
-                    slider_hr_pred = ImageSlider(label="Left: Original HR | Right: FastEDSR")
+                    slider_hr_pred = gr.ImageSlider(label="Left: Original HR | Right: FastEDSR")
                     
             bm_btn.click(fn=benchmark_upscale, inputs=bm_input, outputs=[bm_details, slider_lr_pred, slider_hr_pred])