Tidy Up the mess...

app.py

@@ -89,16 +89,18 @@ def predict(img):
             fig.add_axes(ax)
             ax.imshow(den_map, aspect='auto')
             
-            return pred_cnt, fig
+            return int(np.round(pred_cnt, 0)), fig
 
 
 with gr.Blocks() as demo:
     gr.Markdown("""
     # Crowd Counting based on SASNet
-
+    <p>
     We implemented a image crowd counting model with VGG16 following the paper of Song et. al (2021).
+    </p>
     
-    ## Abstract
+    ## Abstract    
+    <p>
     In this paper, we address the large scale variation problem in crowd counting by taking full advantage of the multi-scale feature representations in a multi-level network. We
     implement such an idea by keeping the counting error of a patch as small as possible with a proper feature level selection strategy, since a specific feature level tends to perform 
     better for a certain range of scales. However, without scale annotations, it is sub-optimal and error-prone to manually assign the predictions for heads of different scales to 
@@ -108,26 +110,38 @@ with gr.Blocks() as demo:
     scale, we conduct the adaptive selection strategy in a patch-wise style. However, pixels within a patch contribute different counting errors due to the various difficulty degrees of 
     learning. Thus, we further propose a Pyramid Region Awareness Loss (PRA Loss) to recursively select the most hard sub-regions within a patch until reaching the pixel level. With 
     awareness of whether the parent patch is over-estimated or under-estimated, the fine-grained optimization with the PRA Loss for these region-aware hard pixels helps to alleviate the 
-    inconsistency problem between training target and evaluation metric. The state-of-the-art results on four datasets demonstrate the superiority of our approach. 
-
-    The code will be available at: https://github.com/TencentYoutuResearch/CrowdCounting-SASNet. 
-
-    ## References
-    Song, Q., Wang, C., Wang, Y., Tai, Y., Wang, C., Li, J., … Ma, J. (2021). To Choose or to Fuse? Scale Selection for Crowd Counting. 
-    The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21).
+    inconsistency problem between training target and evaluation metric. The state-of-the-art results on four datasets demonstrate the superiority of our approach.
+    </p>
+    
+    ## Demo
     """)
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("")
+        with gr.Column():
+            text_output = gr.Label()
     with gr.Row():
         with gr.Column():
             image_input = gr.Image(type="pil")
-            gr.Examples(["IMG_1.jpg", "IMG_2.jpg", "IMG_3.jpg"], image_input)
         with gr.Column():
             image_output = gr.Plot()
+    with gr.Row():
         with gr.Column():
-            text_output = gr.Label()
-            image_button = gr.Button("Count the Crowd!")
-            
+            image_button = gr.Button("Count the Crowd!", variant = "primary")
+        with gr.Column():
+             gr.Markdown("")
+        with gr.Column():
+             gr.Markdown("")
+    
+    gr.Examples(["IMG_1.jpg", "IMG_2.jpg", "IMG_3.jpg"], image_input)
+   
+    gr.Markdown("""
+    ## References
+    The code will be available at: https://github.com/TencentYoutuResearch/CrowdCounting-SASNet.
+    Song, Q., Wang, C., Wang, Y., Tai, Y., Wang, C., Li, J., … Ma, J. (2021). To Choose or to Fuse? Scale Selection for Crowd Counting. The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21).
+    """)
 
     image_button.click(predict, inputs=image_input, outputs=[text_output, image_output])
 
-demo.launch(debug = True)
+demo.launch(debug = True, share=True)