DanbooruCLIP——二次元数据集微调的 CLIP 模型

介绍

Huggingface 在线体验： https://huggingface.co/OysterQAQ/DanbooruCLIP

github 主仓库地址（ pt 模型文件可以在 release 下载）： https://github.com/OysterQAQ/ACG2vec

使用 danburoo2021 数据集对 clip （ ViT-L/14 ）模型进行微调。

0-3 epoch 学习率为 4e-6 ，权重衰减为 1e-3

4-8 epoch 学习率为 1e-6 ，权重衰减为 1e-3

标签预处理过程：

            for i in range(length):
                # 加载并且缩放图片
                if not is_image(data_from_db.path[i]):
                    continue

                try:
                    img = self.preprocess(
                        Image.open(data_from_db.path[i].replace("./", "/mnt/lvm/danbooru2021/danbooru2021/")))
                except Exception as e:
                    #print(e)
                    continue
                # 处理标签
                tags = json.loads(data_from_db.tags[i])
                # 优先选择人物和作品标签
                category_group = {}
                for tag in tags:
                    category_group.setdefault(tag["category"], []).append(tag)

                # category_group=groupby(tags, key=lambda x: (x["category"]))
                character_list = category_group[4] if 4 in category_group else []
                # 作品需要过滤以 bad 开头的

                work_list = list(filter(
                    lambda e:
                               e["name"] != "original"
                            , category_group[3])) if 3 in category_group else []
                # work_list=  category_group[5] if 5 in category_group else []
                general_list = category_group[0] if 0 in category_group else []
                caption = ""
                caption_2 = None
                for character in character_list:
                    if len(work_list) != 0:
                        # 去除括号内作品内容
                        character["name"] = re.sub(u"\\(.*?\\)", "", character["name"])
                    caption += character["name"].replace("_", " ")
                    caption += ","
                caption = caption[:-1]
                caption += " "
                if len(work_list) != 0:
                    caption += "from "
                for work in work_list:
                    caption += work["name"].replace("_", " ")
                    caption += " "
                # 普通标签
                if len(general_list) != 0:
                    caption += "with "
                if len(general_list) > 20:
                    general_list_1 = general_list[:int(len(general_list) / 2)]
                    general_list_2 = general_list[int(len(general_list) / 2):]
                    caption_2 = caption
                    for general in general_list_1:
                        if general["name"].find("girl") == -1 and general["name"].find("boy") == -1 and len(
                                re.findall(is_contain, general["name"])) != 0:
                            caption_2 += general["name"].replace("_", " ")
                            caption_2 += ","
                    caption_2 = caption_2[:-1]
                    for general in general_list_2:
                        if general["name"].find("girl") == -1 and general["name"].find("boy") == -1 and len(
                                re.findall(is_contain, general["name"])) != 0:
                            caption += general["name"].replace("_", " ")
                            caption += ","
                    caption = caption[:-1]
                else:
                    for general in general_list:
                        # 如果标签数据目大于 20 则拆分成两个 caption
                        if general["name"].find("girl") == -1 and general["name"].find("boy") == -1 and len(
                                re.findall(is_contain, general["name"])) != 0:
                            caption += general["name"].replace("_", " ")
                            caption += ","
                    caption = caption[:-1]

                # 标签汇总成语句
                # tokenize 语句
                # 返回
                # 过长截断 不行的话用 huggingface 的
                text_1 = clip.tokenize(texts=caption, truncate=True)
                text_2= None
                if caption_2 is not None:
                    text_2 = clip.tokenize(texts=caption_2, truncate=True)
                # 处理逻辑

                # print(img)
                yield img, text_1[0]
                if text_2 is not None:
                    yield img, text_2[0]

预览