adding app with CLIP image segmentation

app.py

@@ -45,7 +45,7 @@ def detect_using_clip(image,prompts=[],threshould=0.4):
     detection = outputs.logits[0]  # Assuming class index 0
     for i,prompt in enumerate(prompts):
         predicted_image =  torch.sigmoid(preds[i][0]).detach().cpu().numpy()
-        predicted_image = np.where(predicted_image>threshould,255,0)
+        predicted_image = np.where(predicted_image>threshould,np.random.randint(128,255),0)
         # extract countours from the image
         lbl_0 = label(predicted_image)
         props = regionprops(lbl_0)
@@ -69,7 +69,10 @@ def visualize_images(image,detections,predicted_images,prompt):
     return final_image
 
 def shot(image, labels_text,selected_categoty):
-    prompts = labels_text.split(',')
+    if "," in labels_text:
+        prompts = labels_text.split(',')
+    else:
+        prompts = [labels_text]
     prompts = list(map(lambda x: x.strip(),prompts))
     model_detections,predicted_images  = detect_using_clip(image,prompts=prompts)