Spaces:
Running
Running
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
import gradio as gr
|
3 |
+
from PIL import Image
|
4 |
+
|
5 |
+
|
6 |
+
os.system(
|
7 |
+
'wget https://github.com/FanChiMao/SUNet/releases/download/0.0/AWGN_denoising_SUNet.pth -P experiments/pretrained_models')
|
8 |
+
|
9 |
+
|
10 |
+
def inference(img):
|
11 |
+
os.system('mkdir test')
|
12 |
+
#basewidth = 512
|
13 |
+
#wpercent = (basewidth / float(img.size[0]))
|
14 |
+
#hsize = int((float(img.size[1]) * float(wpercent)))
|
15 |
+
#img = img.resize((basewidth, hsize), Image.ANTIALIAS)
|
16 |
+
img.save("test/1.png", "PNG")
|
17 |
+
os.system(
|
18 |
+
'python main_test_SUNet.py --input_dir test --weights experiments/pretrained_models/AWGN_denoising_SUNet.pth')
|
19 |
+
return 'result/1.png'
|
20 |
+
|
21 |
+
|
22 |
+
title = "SUNet: Swin Transformer with UNet for Image Denoising"
|
23 |
+
description = "Gradio demo for SUNet. SUNet has competitive performance results in terms of quantitative metrics and visual quality. See the paper and project page for detailed results below. Here, we provide a demo for AWGN image denoising. To use it, simply upload your image, or click one of the examples to load them. Reference from: https://huggingface.co/akhaliq"
|
24 |
+
article = "<p style='text-align: center'><a href='https://' target='_blank'>Selective Residual M-Net</a> | <a href='https://github.com/FanChiMao/SRMNet' target='_blank'>Github Repo</a></p>"
|
25 |
+
|
26 |
+
examples = [['baby.png']]
|
27 |
+
gr.Interface(
|
28 |
+
inference,
|
29 |
+
[gr.inputs.Image(type="pil", label="Input")],
|
30 |
+
gr.outputs.Image(type="file", label="Output"),
|
31 |
+
title=title,
|
32 |
+
description=description,
|
33 |
+
article=article,
|
34 |
+
examples=examples
|
35 |
+
).launch(debug=True)
|