adding app with CLIP image segmentation

app.py

@@ -1,5 +1,4 @@
 from turtle import title
-import os 
 import gradio as gr
 from transformers import pipeline
 import numpy as np
@@ -7,7 +6,6 @@ from PIL import Image
 import torch 
 import cv2 
 from transformers import CLIPSegProcessor, CLIPSegForImageSegmentation,AutoProcessor,AutoConfig
-from skimage.measure import label, regionprops
 
 processor = CLIPSegProcessor.from_pretrained("CIDAS/clipseg-rd64-refined")
 model = CLIPSegForImageSegmentation.from_pretrained("CIDAS/clipseg-rd64-refined")
@@ -21,7 +19,6 @@ def create_rgb_mask(mask):
 
 
 def detect_using_clip(image,prompts=[],threshould=0.4):
-    h,w  = image.shape[:2]
     predicted_masks = list()
     inputs = processor(
         text=prompts,
@@ -36,14 +33,13 @@ def detect_using_clip(image,prompts=[],threshould=0.4):
     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_masks.append(create_rgb_mask(predicted_image))
+
     return predicted_masks
 
 def visualize_images(image,predicted_images):
     alpha = 0.7
     # H,W = image.shape[:2]
-    prompt = prompt.lower()
     image_resize = cv2.resize(image,(352,352))
     resize_image_copy = image_resize.copy()
 
@@ -59,7 +55,6 @@ def shot(image, labels_text):
     else:
         prompts = [labels_text]
     prompts = list(map(lambda x: x.strip(),prompts))
-    
     predicted_images  = detect_using_clip(image,prompts=prompts)
 
     category_image = visualize_images(image=image,predicted_images=predicted_images)