change input output

app.py

@@ -10,10 +10,9 @@ from PIL import Image
 title = "Super Resolution with CNN"
 description = """
 
-Your low resolution image will be reconstructed to high resolution with a scale of 2 with a convolutional neural network!
-
-CNN output on the left, bicubic interpolation output on the right.
-
+Your low resolution image will be reconstructed to high resolution with a scale of 2 with a convolutional neural network!<br>
+CNN output on the left, bicubic interpolation output on the right.<br>
+Training and dataset can be found on my [github page](https://github.com/susuhu/super-resolution/blob/main/Super_Resolution.ipynb).<br>
 
 """
 
@@ -28,27 +27,27 @@ model.load_state_dict(torch.load('SRCNNmodel_trained.pt',map_location=torch.devi
 model.eval()
 print("SRCNN model loaded!")
 
-def image_grid(imgs, rows, cols):
-    '''
-    imgs:list of PILImage
-    '''
-    assert len(imgs) == rows*cols
+# def image_grid(imgs, rows, cols):
+#     '''
+#     imgs:list of PILImage
+#     '''
+#     assert len(imgs) == rows*cols
 
-    w, h = imgs[0].size
-    grid = Image.new('RGB', size=(cols*w, rows*h))
-    grid_w, grid_h = grid.size
+#     w, h = imgs[0].size
+#     grid = Image.new('RGB', size=(cols*w, rows*h))
+#     grid_w, grid_h = grid.size
     
-    for i, img in enumerate(imgs):
-        grid.paste(img, box=(i%cols*w, i//cols*h))
-    return grid
+#     for i, img in enumerate(imgs):
+#         grid.paste(img, box=(i%cols*w, i//cols*h))
+#     return grid
 
-def sepia(image_path):
+def sepia(image):
     # gradio open image as np array
-    image = Image.fromarray(image_path,mode='RGB')
+    image = Image.fromarray(image,mode='RGB')
     out_final,image_bicubic,image = pred_SRCNN(model=model,image=image,device=device)
-    grid = image_grid([out_final,image_bicubic],1,2)
-    return grid
+    # grid = image_grid([out_final,image_bicubic],1,2)
+    return out_final,image_bicubic
 
-demo = gr.Interface(fn = sepia, inputs=gr.Image(shape=(200, 200)), outputs="image",title=title,description = description,article = article,examples=['LR_image.png','barbara.png'])
+demo = gr.Interface(fn = sepia, inputs=gr.inputs.Image(label="Upload image"), [gr.outputs.Image(label="Conv net"), gr.outputs.Image(label="Bicubic interpoloation")],title=title,description = description,article = article,examples=[['LR_image.png'],['barbara.png']])
 
 demo.launch()