kaihon/sg-aerial-scene-analyser-lora

import torch
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
from peft import PeftModel
from qwen_vl_utils import process_vision_info

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "Qwen/Qwen2.5-VL-7B-Instruct", torch_dtype=torch.bfloat16, device_map="auto"
)
model = PeftModel.from_pretrained(model, "kaihon/sg-aerial-scene-analyser-lora")
model.eval()

processor = AutoProcessor.from_pretrained(
    "Qwen/Qwen2.5-VL-7B-Instruct", min_pixels=256*28*28, max_pixels=1280*28*28
)

messages = [
    {"role": "system", "content": "You are an aerial scene analyst specialising in Singapore urban landscapes. Given a nadir (top-down) aerial image, return a JSON object with exactly these fields:\n{\n  \"caption\": \"3-5 sentences describing what is VISIBLE in a neutral surveyor tone, using Singapore-specific vocabulary (HDB block, hawker centre, covered walkway, MRT station). Name types not instances (MRT station not Bishan MRT). Only name globally unique landmarks (Marina Bay Sands, Jewel Changi Airport).\",\n  \"scene_type\": \"residential_hdb | commercial | industrial | port_terminal | airport | park_green | construction | mixed_use | transport\",\n  \"objects\": [{\"type\": \"hdb_block | condo | landed_house | shophouse | hawker_centre | mrt_station | bus_interchange | shopping_mall | warehouse | container_crane | cargo_ship | aircraft | construction_crane | sports_facility | place_of_worship | school\", \"count\": N}],\n  \"infrastructure\": [\"expressway | mrt_track | bus_lane | pedestrian_bridge | covered_walkway | park_connector | jetty | runway | taxiway\"],\n  \"terrain\": [\"water | urban | industrial | parkland | reclaimed_land | forest_reserve\"]\n}\nReturn ONLY the JSON object, no markdown fences or commentary."},
    {"role": "user", "content": [
        {"type": "image", "image": "path/to/aerial_image.jpg"},
        {"type": "text", "text": "Analyse this nadir aerial image of Singapore."},
    ]},
]

text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
img_inputs, _ = process_vision_info(messages)
inputs = processor(text=[text], images=img_inputs, padding=True, return_tensors="pt").to(model.device)

with torch.no_grad():
    gen = model.generate(**inputs, max_new_tokens=512, do_sample=False)
gen_trimmed = gen[:, inputs["input_ids"].shape[1]:]
output = processor.batch_decode(gen_trimmed, skip_special_tokens=True)[0]
print(output)