-

app.py

@@ -129,7 +129,7 @@ def run_inference(url, sampling_interval, search_query, bs=256):
     bs = min(n_frames,bs)
     print(f"extracted {n_frames} frames, now encoding images")
     # encoding images one batch at a time, combine all batch outputs -> image_features, size n_frames x 512
-    image_features = torch.empty(size=(n_frames, 512), dtype=torch.float16).to(device)
+    image_features = torch.empty(size=(n_frames, 512).to(device)
     print(f"batch size :{bs} ; number of batches: {len(range(0, n_frames,bs))}")
     for b in range(0, n_frames,bs):
         images = []
@@ -148,7 +148,7 @@ def run_inference(url, sampling_interval, search_query, bs=256):
     with torch.no_grad():
         text_features = model.encode_text(clip.tokenize(search_query).to(device))
         text_features /= text_features.norm(dim=-1, keepdim=True)
-  
+    print(image_features.dtype, text_features.dtype)
     similarity = (100.0 * image_features @ text_features.T)
     values, indices = similarity.topk(4, dim=0)