Update app.py

app.py

@@ -16,7 +16,6 @@ from huggingface_hub.keras_mixin import from_pretrained_keras
 from itertools import cycle, islice
 
 
-model = from_pretrained_keras("tareknaous/unet-visual-clustering")
 
 
 #Function that predicts on only 1 sample 
@@ -50,6 +49,7 @@ def create_input_image(data, visualize=False):
 
   return input
 
+model = from_pretrained_keras("tareknaous/unet-visual-clustering")
 
 
 def get_instances(prediction, data, max_filter_size=1):
@@ -124,7 +124,7 @@ def get_instances(prediction, data, max_filter_size=1):
 
 
 
-def visual_clustering(cluster_type, num_clusters, num_samples, random_state, median_kernel_size, max_kernel_size):
+def visual_clustering(cluster_type, num_clusters, num_samples, noise, random_state, median_kernel_size, max_kernel_size):
 
   NUM_CLUSTERS = num_clusters
   CLUSTER_STD = 4 * np.ones(NUM_CLUSTERS)
@@ -143,10 +143,10 @@ def visual_clustering(cluster_type, num_clusters, num_samples, random_state, med
     data = (X_aniso, y)
 
   elif cluster_type == "noisy moons":
-    data = datasets.make_moons(n_samples=num_samples, noise=.05)
+    data = datasets.make_moons(n_samples=num_samples, noise=noise)
 
   elif cluster_type == "noisy circles":
-    data = datasets.make_circles(n_samples=num_samples, factor=.01, noise=.05)
+    data = datasets.make_circles(n_samples=num_samples, factor=.01, noise=noise)
 
   max_x = max(data[0][:, 0])
   min_x = min(data[0][:, 0])
@@ -184,6 +184,8 @@ def visual_clustering(cluster_type, num_clusters, num_samples, random_state, med
 
   return fig1, fig2
   
+title = "Clustering Plotted Data by Image Segmentation"
+description = "Gradio Demo for Visual Clustering on synthetic datasets"
 
 iface = gr.Interface(
     
@@ -193,6 +195,7 @@ iface = gr.Interface(
           gr.inputs.Dropdown(["blobs", "varied blobs",  "aniso", "noisy moons", "noisy circles" ]),
           gr.inputs.Slider(1, 10, step=1, label='Number of Clusters'),
           gr.inputs.Slider(10000, 1000000, step=10000, label='Number of Samples'),
+          gr.inputs.Slider(0.03, 0.1, step=0.01, label='Noise'),
           gr.inputs.Slider(1, 100, step=1, label='Random State'),
           gr.inputs.Slider(1, 100, step=1, label='Denoising Filter Kernel Size'),
           gr.inputs.Slider(1,100, step=1, label='Max Filter Kernel Size')
@@ -201,6 +204,9 @@ iface = gr.Interface(
   outputs=[
            gr.outputs.Image(type='plot', label='Dataset'),
            gr.outputs.Image(type='plot', label='Clustering Result')
-           ]
+           ],
+           
+  title=title,
+  description=description,
            )
 iface.launch(debug=True)