init change to zero

README.md

@@ -1,10 +1,11 @@
 ---
-title: SeemoRe
-emoji: 💻
+title: See More Details - Zero
+short_description: Efficient Image Super-Resolution
+emoji: 😊
 colorFrom: purple
 colorTo: blue
 sdk: gradio
-sdk_version: 4.31.5
+sdk_version: 4.21.0
 app_file: app.py
 pinned: false
 license: mit

app.py

@@ -4,6 +4,7 @@ import torch
 import argparse
 import numpy as np
 import gradio as gr
+import spaces
 
 from PIL import Image
 from copy import deepcopy
@@ -39,6 +40,7 @@ def load_img (filename, norm=True,):
         img = img.astype(np.float32)
     return img
 
+@spaces.GPU(enable_queue=True)
 def process_img (image):
     img = np.array(image)
     img = img / 255.
@@ -93,43 +95,22 @@ 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
+title = "See More Details - Efficient Image Super-Resolution"
+description = '''  
 
-#### [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**
+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.
 
-<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.
-
-<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},
-  booktitle={International Conference on Machine Learning},
-  year={2024},
-  organization={PMLR}
-}
-</code>
 <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>"
+article = ""
 
 #### Image,Prompts examples
 examples = [
+          
             ['images/0801x4.png'],
             ['images/0840x4.png'],
             ['images/0841x4.png'],
@@ -156,8 +137,9 @@ css = """
 """
 
 demo = gr.Interface(
+    theme='gradio/soft',
     fn=process_img,
-    inputs=[gr.Image(type="pil", label="Input", value="images/0878x4.png"),],
+    inputs=[gr.Image(type="pil", label="Input", value="images/img002x4.png"),],
     outputs=ImageSlider(label="Super-Resolved Image", 
                         type="pil",
                         show_download_button=True,
@@ -170,4 +152,4 @@ demo = gr.Interface(
 )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(show_api=False)