testing

app.py

@@ -127,6 +127,7 @@ def captioned_strip(images, caption=None, times=None, rows=1):
 def run_inference(url, sampling_interval, search_query):
     original_images, images = vid2frames(url,sampling_interval)
     image_input = torch.tensor(np.stack(images)).to(device)
+    print("testing.. created image_input")
     with torch.no_grad():
         image_features = model.encode_image(image_input)
         text_features = model.encode_text(clip.tokenize(search_query).to(device))
@@ -136,11 +137,13 @@ def run_inference(url, sampling_interval, search_query):
   
     similarity = (100.0 * image_features @ text_features.T)
     values, indices = similarity.topk(4, dim=0)
-  
+    print("testing.. selected best frames")
     best_frames = [original_images[ind] for ind in indices]
     times = [f'{datetime.timedelta(seconds = ind[0].item() * sampling_interval)}' for ind in indices]
+    print("testing... before captioned_strip func")
     image_output = captioned_strip(best_frames,search_query, times,2)
     title = search_query
+    print("testing... after captioned_strip func")
     return(title, image_output)
 
 inputs = [gr.inputs.Textbox(label="Give us the link to your youtube video!"),