Qwen2.5 VL 3B UI R1 E

🚀 UI-R1-E-3B

このリポジトリには、UI-R1: Enhancing Action Prediction of GUI Agents by Reinforcement Learningで提示された効率的なGUIグラウンディングモデル、UI-R1-E-3Bが含まれています。

プロジェクトページ: https://github.com/lll6gg/UI-R1

旧バージョン: UI-R1-3B

🚀 クイックスタート

このセクションでは、UI-R1-E-3Bモデルの概要と、いくつかのベンチマーク結果を紹介します。

✨ 主な機能

• 効率的なGUIグラウンディングモデルであるUI-R1-E-3Bを提供します。
• 複数のベンチマークでの性能を示しています。

📚 ドキュメント

🔍 ベンチマーク1: ScreenSpotV2

🔍 ベンチマーク2: ScreenSpot-Pro

🔍 リーダーボード: UI-I2E-Bench

💻 使用例

基本的な使用法

UI-R1-E-3Bの生成

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    args.model_path,
    torch_dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
    device_map="cpu",
)
model = model.to(torch.device(rank))
model = model.eval()
processor = AutoProcessor.from_pretrained(ori_processor_path)
question_template = (
    f"In this UI screenshot, I want to perform the command '{task_prompt}'.\n"
    "Please provide the action to perform (enumerate in ['click'])"
    "and the coordinate where the cursor is moved to(integer) if click is performed.\n"
    "Output the final answer in <answer> </answer> tags directly."
    "The output answer format should be as follows:\n"
    "<answer>[{'action': 'click', 'coordinate': [x, y]}]</answer>\n"
    "Please strictly follow the format."
)
query = '<image>\n' + question_template
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": image_path}
        ] + [{"type": "text", "text": query}],
    }
]
text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
generated_ids = model.generate(**inputs, max_new_tokens=1024)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
response = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
response = response[0]
pred_coord, _ = extract_coord(response)

画像のリサイズに応じて予測座標をリスケールする

image = Image.open(image_path)
origin_width, origin_height = image.size
resized_height,resized_width = smart_resize(origin_height,origin_width,max_pixels=12845056)
scale_x = origin_width / resized_width
scale_y = origin_height / resized_height
pred_coord[0] = int(pred_coord[0] * scale_x)
pred_coord[1] = int(pred_coord[1] * scale_y)

smart_resize関数（Qwen2VLから）

import math
def smart_resize(
    height: int, width: int, factor: int = 28, min_pixels: int = 56 * 56, max_pixels: int = 14 * 14 * 4 * 1280
):
    """Rescales the image so that the following conditions are met:

    1. Both dimensions (height and width) are divisible by 'factor'.

    2. The total number of pixels is within the range ['min_pixels', 'max_pixels'].

    3. The aspect ratio of the image is maintained as closely as possible.

    """
    if height < factor or width < factor:
        raise ValueError(f"height:{height} or width:{width} must be larger than factor:{factor}")
    elif max(height, width) / min(height, width) > 200:
        raise ValueError(
            f"absolute aspect ratio must be smaller than 200, got {max(height, width) / min(height, width)}"
        )
    h_bar = round(height / factor) * factor
    w_bar = round(width / factor) * factor
    if h_bar * w_bar > max_pixels:
        beta = math.sqrt((height * width) / max_pixels)
        h_bar = math.floor(height / beta / factor) * factor
        w_bar = math.floor(width / beta / factor) * factor
    elif h_bar * w_bar < min_pixels:
        beta = math.sqrt(min_pixels / (height * width))
        h_bar = math.ceil(height * beta / factor) * factor
        w_bar = math.ceil(width * beta / factor) * factor
    return h_bar, w_bar

📄 ライセンス

このプロジェクトはMITライセンスの下で提供されています。