using global counter

run.py

@@ -5,6 +5,8 @@ import torch
 from transformers import SegformerImageProcessor, SegformerForSemanticSegmentation
 # from torchvision import transforms
 
+
+
 class Count:
     def __init__(self):
         self.n = 0
@@ -13,7 +15,8 @@ class Count:
     def step(self):
         self.n += 1
 
-        
+
+cnt = 0        
 weights2load = 'segformer_ep15_loss0.00.pth'
 id2label = {0: 'seal', 255: 'bck'}
 label2id = {'seal': 0, 'bck': 255}
@@ -31,23 +34,15 @@ model.to(device).eval()
 counter = Count()
 
 def flip_periodically(im, interval_s=2):
-    """
-    Flips the image periodically with the given interval.
-
-    Args:
-        im: The input image.
-        interval_ms: The interval in milliseconds between flips.
-
-    Returns:
-        The flipped image.
-    """
-    counter.step()
-    if (counter.imout.sum() == 0) or ((counter.n % 2) == 0):
+    global cnt  # Access the global counter variable
+    cnt += 1
+    # counter.step()
+    if (counter.imout.sum() == 0) or ((cnt % 100) == 0):
         pixel_values = image_processor(im, return_tensors="pt").pixel_values.to(device)
         outputs = model(pixel_values=pixel_values)
         logits = outputs.logits.cpu().detach().numpy() ** 2
         counter.imout = (logits[0, 0] - logits[0, 0].min()) / (logits[0, 0].max() - logits[0, 0].min())
-    return counter.imout, counter.n  #np.flipud(im)
+    return counter.imout, cnt  #np.flipud(im)
 
 with gr.Blocks() as demo:
     inp = gr.Image(sources=["webcam"], streaming=True)