Spaces:
Running
on
T4
Running
on
T4
praeclarumjj3
commited on
Commit
•
378b71d
1
Parent(s):
46dd504
Fix text
Browse files- gradio_app.py +2 -13
gradio_app.py
CHANGED
@@ -185,26 +185,15 @@ def segment(path, task, dataset, backbone):
|
|
185 |
out_map = Image.fromarray(out_map.get_image())
|
186 |
return out, out_map
|
187 |
|
188 |
-
title = "OneFormer: One Transformer to Rule Universal Image Segmentation"
|
189 |
|
190 |
-
description = "<p style='font-size:
|
191 |
+ "<p style='font-size: 16px; margin: 5px; font-weight: w600; text-align: center'> <a href='https://praeclarumjj3.github.io/oneformer/' target='_blank'>Project Page</a> | <a href='https://arxiv.org/abs/2211.06220' target='_blank'>ArXiv Paper</a> | <a href='https://github.com/SHI-Labs/OneFormer' target='_blank'>Github Repo</a></p>" \
|
192 |
+ "<p style='text-align: center; margin: 5px; font-size: 14px; font-weight: w300;'> \
|
193 |
OneFormer is the first multi-task universal image segmentation framework based on transformers. Our single OneFormer model achieves state-of-the-art performance across all three segmentation tasks with a single task-conditioned joint training process. OneFormer uses a task token to condition the model on the task in focus, making our architecture task-guided for training, and task-dynamic for inference, all with a single model. We believe OneFormer is a significant step towards making image segmentation more universal and accessible.\
|
194 |
</p>" \
|
195 |
+ "<p style='text-align: center; font-size: 14px; margin: 5px; font-weight: w300;'> [Note: Inference on CPU may take upto 2 minutes. On a single RTX A6000 GPU, OneFormer is able to inference at more than 15 FPS.]</p>"
|
196 |
|
197 |
-
# description = "<p style='color: #E0B941; font-size: 16px; font-weight: w600; text-align: center'> <a style='color: #E0B941;' href='https://praeclarumjj3.github.io/oneformer/' target='_blank'>Project Page</a> | <a style='color: #E0B941;' href='https://arxiv.org/abs/2211.06220' target='_blank'>OneFormer: One Transformer to Rule Universal Image Segmentation</a> | <a style='color: #E0B941;' href='https://github.com/SHI-Labs/OneFormer' target='_blank'>Github</a></p>" \
|
198 |
-
# + "<p style='color:royalblue; margin: 10px; font-size: 16px; font-weight: w400;'> \
|
199 |
-
# [Note: Inference on CPU may take upto 2 minutes.] This is the official gradio demo for our paper <span style='color:#E0B941;'>OneFormer: One Transformer to Rule Universal Image Segmentation</span> To use <span style='color:#E0B941;'>OneFormer</span>: <br> \
|
200 |
-
# (1) <span style='color:#E0B941;'>Upload an Image</span> or <span style='color:#E0B941;'> select a sample image from the examples</span> <br> \
|
201 |
-
# (2) Select the value of the <span style='color:#E0B941;'>Task Token Input</span>. <br>\
|
202 |
-
# (3) Select the <span style='color:#E0B941;'>Model</span> and <span style='color:#E0B941;'>Backbone</span>. </p>"
|
203 |
-
|
204 |
-
# article =
|
205 |
-
|
206 |
-
# css = ".image-preview {height: 32rem; width: auto;} .output-image {height: 32rem; width: auto;} .panel-buttons { display: flex; flex-direction: row;}"
|
207 |
-
|
208 |
setup_modules()
|
209 |
|
210 |
gradio_inputs = [gr.Image(source="upload", tool=None, label="Input Image",type="filepath"),
|
|
|
185 |
out_map = Image.fromarray(out_map.get_image())
|
186 |
return out, out_map
|
187 |
|
188 |
+
title = "<h1 style='margin-bottom: -10px; text-align: center'>OneFormer: One Transformer to Rule Universal Image Segmentation</h1>"
|
189 |
|
190 |
+
description = "<p style='font-size: 14px; margin: 5px; font-weight: w300; text-align: center'> <a href='https://praeclarumjj3.github.io/' style='text-decoration:none' target='_blank'>Jitesh Jain, </a> <a href='https://chrisjuniorli.github.io/' style='text-decoration:none' target='_blank'>Jiachen Li<sup>*</sup>, </a> <a href='https://www.linkedin.com/in/mtchiu/' style='text-decoration:none' target='_blank'>MangTik Chiu<sup>*</sup>, </a> <a href='https://alihassanijr.com/' style='text-decoration:none' target='_blank'>Ali Hassani, </a> <a href='https://www.linkedin.com/in/nukich74/' style='text-decoration:none' target='_blank'>Nikita Orlov, </a> <a href='https://www.humphreyshi.com/home' style='text-decoration:none' target='_blank'>Humphrey Shi</a></p>" \
|
191 |
+ "<p style='font-size: 16px; margin: 5px; font-weight: w600; text-align: center'> <a href='https://praeclarumjj3.github.io/oneformer/' target='_blank'>Project Page</a> | <a href='https://arxiv.org/abs/2211.06220' target='_blank'>ArXiv Paper</a> | <a href='https://github.com/SHI-Labs/OneFormer' target='_blank'>Github Repo</a></p>" \
|
192 |
+ "<p style='text-align: center; margin: 5px; font-size: 14px; font-weight: w300;'> \
|
193 |
OneFormer is the first multi-task universal image segmentation framework based on transformers. Our single OneFormer model achieves state-of-the-art performance across all three segmentation tasks with a single task-conditioned joint training process. OneFormer uses a task token to condition the model on the task in focus, making our architecture task-guided for training, and task-dynamic for inference, all with a single model. We believe OneFormer is a significant step towards making image segmentation more universal and accessible.\
|
194 |
</p>" \
|
195 |
+ "<p style='text-align: center; font-size: 14px; margin: 5px; font-weight: w300;'> [Note: Inference on CPU may take upto 2 minutes. On a single RTX A6000 GPU, OneFormer is able to inference at more than 15 FPS.]</p>"
|
196 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
197 |
setup_modules()
|
198 |
|
199 |
gradio_inputs = [gr.Image(source="upload", tool=None, label="Input Image",type="filepath"),
|