Update app.py

app.py

@@ -26,7 +26,7 @@ def dict2namespace(config):
         setattr(namespace, key, new_value)
     return namespace
 
-def load_img (filename, norm=True,):
+def load_img(filename, norm=True):
     img = np.array(Image.open(filename).convert("RGB"))
     h, w = img.shape[:2]
     
@@ -39,20 +39,19 @@ def load_img (filename, norm=True,):
         img = img.astype(np.float32)
     return img
 
-def process_img (image):
+def process_img(image):
     img = np.array(image)
     img = img / 255.
     img = img.astype(np.float32)
-    y = torch.tensor(img).permute(2,0,1).unsqueeze(0).to(device)
+    y = torch.tensor(img).permute(2, 0, 1).unsqueeze(0).to(device)
     
     with torch.no_grad():
         x_hat = model(y)
 
-    restored_img = x_hat.squeeze().permute(1,2,0).clamp_(0, 1).cpu().detach().numpy()
-    restored_img = np.clip(restored_img, 0. , 1.)
+    restored_img = x_hat.squeeze().permute(1, 2, 0).clamp_(0, 1).cpu().detach().numpy()
+    restored_img = np.clip(restored_img, 0., 1.)
 
     restored_img = (restored_img * 255.0).round().astype(np.uint8)  # float32 to uint8
-    #return Image.fromarray(restored_img) #
     return (image, Image.fromarray(restored_img))
 
 def load_network(net, load_path, strict=True, param_key='params'):
@@ -87,29 +86,25 @@ model = seemore.SeemoRe(scale=cfg.model.scale, in_chans=cfg.model.in_chans,
                         recursive=cfg.model.recursive, lr_space=cfg.model.lr_space, topk=cfg.model.topk)
 
 model = model.to(device)
-print ("IMAGE MODEL CKPT:", MODEL_NAME)
+print("IMAGE MODEL CKPT:", MODEL_NAME)
 load_network(model, MODEL_NAME, strict=True, param_key='params')
 
 
-
-
 title = "See More Details"
 description = ''' ### See More Details: Efficient Image Super-Resolution by Experts Mining - ICML 2024, Vienna, Austria
-#### [Eduard Zamfir<sup>1</sup>](https://eduardzamfir.github.io), [Zongwei Wu<sup>1*</sup>](https://sites.google.com/view/zwwu/accueil), [Nancy Mehta<sup>1</sup>](https://scholar.google.com/citations?user=WwdYdlUAAAAJ&hl=en&oi=ao),  [Yulun Zhang<sup>2,3*</sup>](http://yulunzhang.com/) and [Radu Timofte<sup>1</sup>](https://www.informatik.uni-wuerzburg.de/computervision/)
-#### **<sup>1</sup> University of Würzburg, Germany - <sup>2</sup> Shanghai Jiao Tong University, China - <sup>3</sup> ETH Zürich, Switzerland**
-#### **<sup>*</sup> Corresponding authors**
+#### This work is done by DL Titans
 <details>
 <summary> <b> Abstract</b> (click me to read)</summary>
 <p>
 Reconstructing high-resolution (HR) images from low-resolution (LR) inputs poses a significant challenge in image super-resolution (SR). While recent approaches have demonstrated the efficacy of intricate operations customized for various objectives, the straightforward stacking of these disparate operations can result in a substantial computational burden, hampering their practical utility. In response, we introduce **S**eemo**R**e, an efficient SR model employing expert mining. Our approach strategically incorporates experts at different levels, adopting a collaborative methodology. At the macro scale, our experts address rank-wise and spatial-wise informative features, providing a holistic understanding. Subsequently, the model delves into the subtleties of rank choice by leveraging a mixture of low-rank experts. By tapping into experts specialized in distinct key factors crucial for accurate SR, our model excels in uncovering intricate intra-feature details. This collaborative approach is reminiscent of the concept of **see more**, allowing our model to achieve an optimal performance with minimal computational costs in efficient settings
 </p>
 </details>
-####  Drag the slider on the super-resolution image left and right to see the changes in the image details. SeemoRe performs x4 upscaling on the input image.
+#### Drag the slider on the super-resolution image left and right to see the changes in the image details. SeemoRe performs x4 upscaling on the input image.
 <br>
 <code>
 @inproceedings{zamfir2024details,
   title={See More Details: Efficient Image Super-Resolution by Experts Mining}, 
-  author={Eduard Zamfir and Zongwei Wu and Nancy Mehta and Yulun Zhang and Radu Timofte},
+  author={DL Titans},
   booktitle={International Conference on Machine Learning},
   year={2024},
   organization={PMLR}
@@ -118,9 +113,6 @@ Reconstructing high-resolution (HR) images from low-resolution (LR) inputs poses
 <br>
 '''
 
-
-article = "<p style='text-align: center'><a href='https://eduardzamfir.github.io/seemore' target='_blank'>See More Details: Efficient Image Super-Resolution by Experts Mining</a></p>"
-
 #### Image,Prompts examples
 examples = [
             ['images/0801x4.png'],
@@ -150,14 +142,13 @@ css = """
 
 demo = gr.Interface(
     fn=process_img,
-    inputs=[gr.Image(type="pil", label="Input", value="images/0878x4.png"),],
+    inputs=[gr.Image(type="pil", label="Input", value="images/0878x4.png")],
     outputs=ImageSlider(label="Super-Resolved Image", 
                         type="pil",
                         show_download_button=True,
                         ), #[gr.Image(type="pil", label="Ouput", min_width=500)],
     title=title,
     description=description,
-    article=article,
     examples=examples,
     css=css,
 )