# Transform for input imagestransform = transforms.Compose([ transforms.Resize((448, 448)), transforms.ToTensor(), transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),]) # Load your Sentinel-1 SAR and Sentinel-2 Optical images (RGB PIL Images)sar_image = Image.open("path_to_sar_image.png").convert("RGB")opt_image = Image.open("path_to_optical_image.png").convert("RGB") t_s1 = transform(sar_image).unsqueeze(0).to(model.device, dtype=vision_dtype)t_s2 = transform(opt_image).unsqueeze(0).to(model.device, dtype=vision_dtype)pixel_values = torch.cat([t_s1, t_s2], dim=0) question = "Is there floodwater or inundation present in this scene?" # Structured multimodal promptprompt = ( f"<MODALITY: Sentinel-1 SAR Radar>\n<image>\n" f"<MODALITY: Sentinel-2 Optical>\n<image>\n" f"Question: {question}\nAnswer:") with torch.no_grad(): response = model.chat( tokenizer=tokenizer, pixel_values=pixel_values, question=prompt, num_patches_list=[1, 1], generation_config=dict(max_new_tokens=64, do_sample=False, temperature=0.0), ) print("SatQuery Answer:", response)