CLIP based NSFW Detector下载 - CLIP based NSFW Detector源代码下载

CLIP based NSFW Detector

其他源码

下载

基于 CLIP 的 NSFW 检测器

这个 2 类 NSFW 检测器是一个轻量级 Autokeras 模型，采用 CLIP ViT L/14 嵌入作为输入。它估计 0 到 1 之间的值（1 = NSFW），并且非常适合图像嵌入。

演示-Colab：https://colab.research.google.com/drive/19Acr4grlk5oQws7BHTqNIK-80XGw2u8Z?usp=sharing

训练 CLIP VL/14 嵌入可以在此处下载：https://drive.google.com/file/d/1yenil0R4GqmTOFQ_GVw__x61ofZ-OBcS/view?usp=sharing（未完全手动注释，因此不能用作测试）

（手动注释的）测试集位于 https://github.com/LAION-AI/CLIP-based-NSFW-Detector/blob/main/nsfw_testset.zip

https://github.com/rom1504/embedding-reader/blob/main/examples/inference_example.py laion5B 上的推理

模型使用示例：

 @ lru_cache ( maxsize = None )
def load_safety_model ( clip_model ):
    """load the safety model"""
    import autokeras as ak  # pylint: disable=import-outside-toplevel
    from tensorflow . keras . models import load_model  # pylint: disable=import-outside-toplevel

    cache_folder = get_cache_folder ( clip_model )

    if clip_model == "ViT-L/14" :
        model_dir = cache_folder + "/clip_autokeras_binary_nsfw"
        dim = 768
    elif clip_model == "ViT-B/32" :
        model_dir = cache_folder + "/clip_autokeras_nsfw_b32"
        dim = 512
    else :
        raise ValueError ( "Unknown clip model" )
    if not os . path . exists ( model_dir ):
        os . makedirs ( cache_folder , exist_ok = True )

        from urllib . request import urlretrieve  # pylint: disable=import-outside-toplevel

        path_to_zip_file = cache_folder + "/clip_autokeras_binary_nsfw.zip"
        if clip_model == "ViT-L/14" :
            url_model = "https://raw.githubusercontent.com/LAION-AI/CLIP-based-NSFW-Detector/main/clip_autokeras_binary_nsfw.zip"
        elif clip_model == "ViT-B/32" :
            url_model = (
                "https://raw.githubusercontent.com/LAION-AI/CLIP-based-NSFW-Detector/main/clip_autokeras_nsfw_b32.zip"
            )
        else :
            raise ValueError ( "Unknown model {}" . format ( clip_model ))  # pylint: disable=consider-using-f-string
        urlretrieve ( url_model , path_to_zip_file )
        import zipfile  # pylint: disable=import-outside-toplevel

        with zipfile . ZipFile ( path_to_zip_file , "r" ) as zip_ref :
            zip_ref . extractall ( cache_folder )

    loaded_model = load_model ( model_dir , custom_objects = ak . CUSTOM_OBJECTS )
    loaded_model . predict ( np . random . rand ( 10 ** 3 , dim ). astype ( "float32" ), batch_size = 10 ** 3 )

    return loaded_model
    
    
nsfw_values = safety_model . predict ( embeddings , batch_size = embeddings . shape [ 0 ])