benchmarking_clip.py

DEVICE = "cuda" if torch.cuda.is_available() else "cpu"

start_time = time.time()
for _ in range(1000):
    with torch.no_grad():
        model = model.to(DEVICE)
        inputs = processor(text=[semantic_search_phrase], 
                        images=all_images, return_tensors="pt", padding=True)
        inputs = inputs.to(DEVICE)
        outputs = model(**inputs)
end_time = time.time() - start_time
print(f"Total time: {end_time:.3f} seconds.")