Spaces:

q-future
/

OneAlign

Runtime error

App Files Files Community

teowu commited on Dec 31, 2023

Commit

2d5475b

•

1 Parent(s): 746a281

add examples

Browse files

Files changed (9) hide show

README.md +2 -0
app.py +12 -36
fig/10102107193.mp4 +3 -0
fig/10244479353.mp4 +3 -0
fig/eiffel_a.jpg +3 -0
fig/longgang_nightblur.png +3 -0
fig/none.png +3 -0
fig/onescorer.png +3 -0
fig/singapore_flyer_2.jpg +3 -0

README.md CHANGED Viewed

@@ -10,4 +10,6 @@ pinned: false
 license: mit
 ---
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

 license: mit
 ---
+arxiv.org/abs/2312.17090
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py CHANGED Viewed

@@ -64,39 +64,11 @@ def image_classifier(input_img, input_vid, scorer_type):
 title_markdown = ("""
-<h3 align="center">Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels</h3>
-<h3 align="center"> One Unified Model for Visual scoring. </h3>
-<h5 align="center">
-      <a href="https://teowu.github.io/" target="_blank">Haoning Wu</a><sup>1</sup><sup>*</sup><sup>+</sup>,
-      <a href="https://github.com/zzc-1998" target="_blank">Zicheng Zhang</a><sup>2</sup><sup>*</sup>,
-    <a href="https://sites.google.com/view/r-panda" target="_blank">Weixia Zhang</a><sup>2</sup>,
-    <a href="https://chaofengc.github.io" target="_blank">Chaofeng Chen</a><sup>1</sup>,
-      <a href="https://liaoliang92.github.io" target="_blank">Liang Liao</a><sup>1</sup>,
-      <a href="https://github.com/lcysyzxdxc" target="_blank">Chunyi Li</a><sup>2</sup>,
-</h5>
-<h5 align="center">
-        <a href="https://github.com/YixuanGao98" target="_blank">Yixuan Gao</a><sup>2</sup>,
-      <a href="https://github.com/AnnanWangDaniel" target="_blank">Annan Wang</a><sup>1</sup>,
-      <a href="https://github.com/ZhangErliCarl/" target="_blank">Erli Zhang</a><sup>1</sup>,
-      <a href="https://wenxiusun.com" target="_blank">Wenxiu Sun</a><sup>3</sup>,
-      <a href="https://scholar.google.com/citations?user=uT9CtPYAAAAJ&hl=en" target="_blank">Qiong Yan</a><sup>3</sup>,
-        <a href="https://sites.google.com/site/minxiongkuo/" target="_blank">Xiongkuo Min</a><sup>2</sup>,
-      <a href="https://ee.sjtu.edu.cn/en/FacultyDetail.aspx?id=24&infoid=153&flag=153" target="_blank">Guangtao Zhai</a><sup>2</sup><sup>#</sup>,
-      <a href="https://personal.ntu.edu.sg/wslin/Home.html" target="_blank">Weisi Lin</a><sup>1</sup><sup>#</sup>
-</h5>
-<h5 align="center">
-  <sup>1</sup>Nanyang Technological University, <sup>2</sup>Shanghai Jiao Tong University, <sup>3</sup>Sensetime Research
-</h5>
-<h5 align="center">
-<sup>*</sup>Equal contribution. <sup>+</sup>Project Lead. <sup>#</sup>Corresponding author(s).
-</h5>
-<h4 align="center"> If you like the OneScorer, please give us a star ✨ on <a href='https://github.com/Q-Future/Q-Align'>GitHub</a> for latest update.  </h4>
 <h5 align="center">
     <div style="display:flex; gap: 0.25rem;" align="center">
@@ -111,9 +83,13 @@ title_markdown = ("""
 input_img = gr.Image(type='pil', label="Upload an Image")
-input_vid = gr.Video(label="Upload a Video (will INGORE the image if a video is uploaded)")
 labels = gr.Label(label="Probabilities of rating levels:")
-number = gr.Number(label="Output score:", info="Range in [1,5]. Higher is better.")
-demo = gr.Interface(fn=image_classifier, inputs=[input_img, input_vid, gr.Radio(["Image Aesthetics (IAA)", "Image Quality (IQA)", "Video Quality (VQA)"], label="Task", info="Which Scorer will you need?"),], outputs=[labels, number], title="OneScorer", description=title_markdown)
-demo.launch(share=True)

 title_markdown = ("""
+<div style="width: 100%; text-align: center; margin:auto;">
+      <img style="width: 100%" src="https://raw.githubusercontent.com/Q-Future/Q-Align/main/fig/onescorer.png">
+</div>
+<h4 align="center"> If you like the OneScorer, please give us a star ✨ on <a href='https://github.com/Q-Future/Q-Align'>[GitHub]</a> for latest update.  </h4>
 <h5 align="center">
     <div style="display:flex; gap: 0.25rem;" align="center">
 input_img = gr.Image(type='pil', label="Upload an Image")
+input_vid = gr.Video(label="Upload a Video (will INGORE the image if a video is uploaded)",sources=["upload"])
+radio = gr.Radio(["Image Aesthetics (IAA)", "Image Quality (IQA)", "Video Quality (VQA)"], label="Task", info="Which Scorer will you need?")
+input_img = gr.Image(type='pil', label="Upload an Image")
 labels = gr.Label(label="Probabilities of rating levels:")
+number = gr.Number(label="Output score:", info="Range in [1,5]. Higher is better.", precision=4)
+demo = gr.Interface(fn=image_classifier, inputs=[input_img, input_vid, radio], outputs=[labels, number], description=title_markdown, examples=[["fig/eiffel_a.jpg", None, "Image Aesthetics (IAA)"], ["fig/singapore_flyer_2.jpg", None, "Image Quality (IQA)"], ["fig/none.png", "fig/10244479353.mp4", "Video Quality (VQA)"]], article="This is the Scorer Demo as Proposed by Paper: 'Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels'. The proposed Q-Align achieves state-of-the-art performance on image quality assessment (IQA), image aesthetic assessment (IAA), as well as video quality assessment (VQA) tasks under the original LMM structure. With the syllabus, we further unify the three tasks into one model, termed the **OneAlign**, to which the demo corresponds.")
+demo.launch()