Create app.py

app.py

@@ -0,0 +1,35 @@
+import os
+import gradio as gr
+from PIL import Image
+import torch
+
+os.system(
+    'wget https://github.com/TentativeGitHub/CMFNet/releases/download/0.0/dehaze_model.pth -P experiments/pretrained_models')
+
+
+def inference(img):
+    os.system('mkdir test')
+    basewidth = 512
+    wpercent = (basewidth / float(img.size[0]))
+    hsize = int((float(img.size[1]) * float(wpercent)))
+    img = img.resize((basewidth, hsize), Image.BILINEAR)
+    img.save("test/1.png", "PNG")
+    os.system(
+        'python main_test_CMFNet.py --input_dir test --weights experiments/pretrained_models/dehaze_model.pth')
+    return 'results/1.png'
+
+
+title = "Compound Multi-branch Feature Fusion (Dehaze)"
+description = "Gradio demo for CMFNet. CMFNet achieves state-of-the-art performance on six tasks: image super-resolution (including classical, lightweight and real-world image super-resolution), image denoising (including grayscale and color image denoising) and JPEG compression artifact reduction. See the paper and project page for detailed results below. Here, we provide a demo for real-world image SR.To use it, simply upload your image, or click one of the examples to load them."
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2108.10257' target='_blank'>SwinIR: Image Restoration Using Swin Transformer</a> | <a href='https://github.com/JingyunLiang/SwinIR' target='_blank'>Github Repo</a></p>"
+
+examples = [['Rain.png']]
+gr.Interface(
+    inference,
+    [gr.inputs.Image(type="pil", label="Input")],
+    gr.outputs.Image(type="file", label="Output"),
+    title=title,
+    description=description,
+    article=article,
+    examples=examples
+).launch(debug=True)