From 25a9268c3f83f8187dd2856d1e0dac1e510905d6 Mon Sep 17 00:00:00 2001
From: jm12138 <2286040843@qq.com>
Date: Mon, 16 Nov 2020 11:42:40 +0800
Subject: [PATCH] Add the AnimeGAN modules

---
 .../animegan_v1_hayao_60/README.md            | 127 +++++++++++++++++
 .../animegan_v1_hayao_60/model.py             |  67 +++++++++
 .../animegan_v1_hayao_60/module.py            |  72 ++++++++++
 .../animegan_v1_hayao_60/processor.py         | 133 ++++++++++++++++++
 .../animegan_v2_hayao_64/README.md            | 127 +++++++++++++++++
 .../animegan_v2_hayao_64/model.py             |  67 +++++++++
 .../animegan_v2_hayao_64/module.py            |  72 ++++++++++
 .../animegan_v2_hayao_64/processor.py         | 133 ++++++++++++++++++
 .../animegan_v2_hayao_99/README.md            | 127 +++++++++++++++++
 .../animegan_v2_hayao_99/model.py             |  67 +++++++++
 .../animegan_v2_hayao_99/module.py            |  72 ++++++++++
 .../animegan_v2_hayao_99/processor.py         | 133 ++++++++++++++++++
 .../animegan_v2_paprika_54/README.md          | 127 +++++++++++++++++
 .../animegan_v2_paprika_54/model.py           |  67 +++++++++
 .../animegan_v2_paprika_54/module.py          |  72 ++++++++++
 .../animegan_v2_paprika_54/processor.py       | 133 ++++++++++++++++++
 .../animegan_v2_paprika_74/README.md          | 127 +++++++++++++++++
 .../animegan_v2_paprika_74/model.py           |  67 +++++++++
 .../animegan_v2_paprika_74/module.py          |  72 ++++++++++
 .../animegan_v2_paprika_74/processor.py       | 133 ++++++++++++++++++
 .../animegan_v2_paprika_97/README.md          | 127 +++++++++++++++++
 .../animegan_v2_paprika_97/model.py           |  67 +++++++++
 .../animegan_v2_paprika_97/module.py          |  72 ++++++++++
 .../animegan_v2_paprika_97/processor.py       | 133 ++++++++++++++++++
 .../animegan_v2_paprika_98/README.md          | 127 +++++++++++++++++
 .../animegan_v2_paprika_98/model.py           |  67 +++++++++
 .../animegan_v2_paprika_98/module.py          |  72 ++++++++++
 .../animegan_v2_paprika_98/processor.py       | 133 ++++++++++++++++++
 .../animegan_v2_shinkai_33/README.md          | 127 +++++++++++++++++
 .../animegan_v2_shinkai_33/model.py           |  67 +++++++++
 .../animegan_v2_shinkai_33/module.py          |  72 ++++++++++
 .../animegan_v2_shinkai_33/processor.py       | 133 ++++++++++++++++++
 .../animegan_v2_shinkai_53/README.md          | 127 +++++++++++++++++
 .../animegan_v2_shinkai_53/model.py           |  67 +++++++++
 .../animegan_v2_shinkai_53/module.py          |  72 ++++++++++
 .../animegan_v2_shinkai_53/processor.py       | 133 ++++++++++++++++++
 36 files changed, 3591 insertions(+)
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v1_hayao_60/README.md
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v1_hayao_60/model.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v1_hayao_60/module.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v1_hayao_60/processor.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_hayao_64/README.md
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_hayao_64/model.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_hayao_64/module.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_hayao_64/processor.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_hayao_99/README.md
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_hayao_99/model.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_hayao_99/module.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_hayao_99/processor.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_paprika_54/README.md
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_paprika_54/model.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_paprika_54/module.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_paprika_54/processor.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_paprika_74/README.md
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_paprika_74/model.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_paprika_74/module.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_paprika_74/processor.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_paprika_97/README.md
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_paprika_97/model.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_paprika_97/module.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_paprika_97/processor.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_paprika_98/README.md
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_paprika_98/model.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_paprika_98/module.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_paprika_98/processor.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_shinkai_33/README.md
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_shinkai_33/model.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_shinkai_33/module.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_shinkai_33/processor.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_shinkai_53/README.md
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_shinkai_53/model.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_shinkai_53/module.py
 create mode 100644 hub_module/modules/image/style_transfer/animegan_v2_shinkai_53/processor.py

diff --git a/hub_module/modules/image/style_transfer/animegan_v1_hayao_60/README.md b/hub_module/modules/image/style_transfer/animegan_v1_hayao_60/README.md
new file mode 100644
index 00000000..587f4ba9
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v1_hayao_60/README.md
@@ -0,0 +1,127 @@
+## 模型概述
+AnimeGAN V1 图像风格转换模型
+
+模型可将输入的图像转换成Hayao风格
+
+模型权重转换自AnimeGAN V1官方开源项目
+
+模型所使用的权重为Hayao-60.ckpt
+
+模型详情请参考[AnimeGAN V1 开源项目](https://github.com/TachibanaYoshino/AnimeGAN)
+
+## 模型安装
+
+```shell
+$hub install animegan_v1_hayao_60
+```
+
+
+## API 说明
+
+```python
+def style_transfer(
+    self,
+    images=None,
+    paths=None,
+    batch_size=1,
+    output_dir='output',
+    visualization=False,
+    min_size=32,
+    max_size=1024
+)
+```
+
+风格转换API，将输入的图片转换为漫画风格。
+
+转换效果图如下：
+
+![输入图像](https://ai-studio-static-online.cdn.bcebos.com/bd002c4bb6a7427daf26988770bb18648b7d8d2bfd6746bfb9a429db4867727f)
+![输出图像](https://ai-studio-static-online.cdn.bcebos.com/10175bb964e94ce18608a84b0ab6ebfe154b523df42f44a3a851b2d91dd17a63)
+
+
+**参数**
+
+* images (list\[numpy.ndarray\]): 图片数据，ndarray.shape 为 \[H, W, C\]，默认为 None；
+* paths (list\[str\]): 图片的路径，默认为 None；
+* batch\_size (int): batch 的大小，默认设为 1；
+* visualization (bool): 是否将识别结果保存为图片文件，默认设为 False；
+* output\_dir (str): 图片的保存路径，默认设为 output；
+* min\_size (int): 输入图片的短边最小尺寸，默认设为 32；
+* max\_size (int): 输入图片的短边最大尺寸，默认设为 1024。
+
+
+**返回**
+
+* res (list\[numpy.ndarray\]): 输出图像数据，ndarray.shape 为 \[H, W, C\]。
+
+
+## 预测代码示例
+
+```python
+import cv2
+import paddlehub as hub
+
+# 模型加载
+# use_gpu：是否使用GPU进行预测
+model = hub.Module('animegan_v1_hayao_60', use_gpu=False)
+
+# 模型预测
+result = model.style_transfer(images=[cv2.imread('/PATH/TO/IMAGE')])
+
+# or
+# result = model.style_transfer(paths=['/PATH/TO/IMAGE'])
+```
+
+## 服务部署
+
+PaddleHub Serving可以部署一个在线图像风格转换服务。
+
+## 第一步：启动PaddleHub Serving
+
+运行启动命令：
+```shell
+$ hub serving start -m animegan_v1_hayao_60
+```
+
+这样就完成了一个图像风格转换的在线服务API的部署，默认端口号为8866。
+
+**NOTE:** 如使用GPU预测，则需要在启动服务之前，请设置CUDA\_VISIBLE\_DEVICES环境变量，否则不用设置。
+
+## 第二步：发送预测请求
+
+配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果
+
+```python
+import requests
+import json
+import cv2
+import base64
+
+
+def cv2_to_base64(image):
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+
+# 发送HTTP请求
+data = {'images':[cv2_to_base64(cv2.imread("/PATH/TO/IMAGE"))]}
+headers = {"Content-type": "application/json"}
+url = "http://127.0.0.1:8866/predict/animegan_v1_hayao_60"
+r = requests.post(url=url, headers=headers, data=json.dumps(data))
+
+# 打印预测结果
+print(r.json()["results"])
+```
+
+
+## 模型相关信息
+
+### 模型代码
+
+https://github.com/TachibanaYoshino/AnimeGAN
+
+### 依赖
+
+paddlepaddle >= 1.8.0
+
+paddlehub >= 1.8.0
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v1_hayao_60/model.py b/hub_module/modules/image/style_transfer/animegan_v1_hayao_60/model.py
new file mode 100644
index 00000000..a72cf8a3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v1_hayao_60/model.py
@@ -0,0 +1,67 @@
+import os
+import numpy as np
+
+from paddle.fluid.core import AnalysisConfig, create_paddle_predictor
+
+__all__ = ['Model']
+
+class Model():
+    # 初始化函数
+    def __init__(self, modelpath, use_gpu):
+        # 加载模型预测器
+        self.predictor = self.load_model(modelpath, use_gpu)
+
+        # 获取模型的输入输出
+        self.input_names = self.predictor.get_input_names()
+        self.output_names = self.predictor.get_output_names()
+        self.input_tensor = self.predictor.get_input_tensor(self.input_names[0])
+        self.output_tensor = self.predictor.get_output_tensor(self.output_names[0])
+
+    # 模型加载函数
+    def load_model(self, modelpath, use_gpu):
+        # 对运行位置进行配置
+        if use_gpu:
+            try:
+                places = os.environ["CUDA_VISIBLE_DEVICES"]
+                places = int(places[0])
+            except Exception as e:
+                print('Error: %s. Please set the environment variables "CUDA_VISIBLE_DEVICES".' % e)
+                use_gpu = False
+
+        # 加载模型参数
+        config = AnalysisConfig(modelpath)
+
+        # 设置参数
+        if use_gpu:   
+            config.enable_use_gpu(100, places)
+        else:
+            config.disable_gpu()
+            config.enable_mkldnn()
+        config.disable_glog_info()
+        config.switch_ir_optim(True)
+        config.enable_memory_optim()
+        config.switch_use_feed_fetch_ops(False)
+        config.switch_specify_input_names(True)
+        
+        # 通过参数加载模型预测器
+        predictor = create_paddle_predictor(config)
+        
+        # 返回预测器
+        return predictor
+
+    # 模型预测函数
+    def predict(self, input_datas):
+        outputs = []
+
+        # 遍历输入数据进行预测
+        for input_data in input_datas:
+            self.input_tensor.copy_from_cpu(input_data)
+            self.predictor.zero_copy_run()
+            output = self.output_tensor.copy_to_cpu()
+            outputs.append(output)
+        
+        # 预测结果合并
+        outputs = np.concatenate(outputs, 0)
+
+        # 返回预测结果
+        return outputs
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v1_hayao_60/module.py b/hub_module/modules/image/style_transfer/animegan_v1_hayao_60/module.py
new file mode 100644
index 00000000..8b77d894
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v1_hayao_60/module.py
@@ -0,0 +1,72 @@
+import os
+
+from paddlehub import Module
+from paddlehub.module.module import moduleinfo, serving
+
+from animegan_v1_hayao_60.model import Model
+from animegan_v1_hayao_60.processor import base64_to_cv2, cv2_to_base64, Processor
+
+@moduleinfo(
+    name="animegan_v1_hayao_60", # 模型名称
+    type="CV/style_transfer", # 模型类型
+    author="jm12138", # 作者名称
+    author_email="jm12138@qq.com", # 作者邮箱
+    summary="animegan_v1_hayao_60", # 模型介绍
+    version="1.0.0" # 版本号
+)
+class Animegan_V1_Hayao_60(Module):
+    # 初始化函数
+    def _initialize(self, use_gpu=False):
+        # 设置模型路径
+        self.model_path = os.path.join(self.directory, "animegan_v1_hayao_60")
+
+        # 加载模型
+        self.model = Model(self.model_path, use_gpu)     
+    
+    # 关键点检测函数
+    def style_transfer(
+        self,
+        images=None,
+        paths=None,
+        batch_size=1,
+        output_dir='output',
+        visualization=False,
+        min_size=32,
+        max_size=1024
+    ):
+        # 加载数据处理器
+        processor = Processor(
+            images, 
+            paths, 
+            batch_size, 
+            output_dir, 
+            min_size, 
+            max_size
+        )
+
+        # 模型预测
+        outputs = self.model.predict(processor.input_datas)
+
+        # 结果后处理
+        results = processor.postprocess(outputs, visualization)
+
+        # 返回结果
+        return results
+
+    # Hub Serving
+    @serving
+    def serving_method(self, images, **kwargs):
+        # 获取输入数据
+        images_decode = [base64_to_cv2(image) for image in images]
+
+        # 图片风格转换
+        results = self.style_transfer(images_decode, **kwargs)
+
+        # 对输出图片进行编码
+        encodes = []
+        for result in results:
+            encode = cv2_to_base64(result)
+            encodes.append(encode)
+            
+        # 返回结果
+        return encodes
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v1_hayao_60/processor.py b/hub_module/modules/image/style_transfer/animegan_v1_hayao_60/processor.py
new file mode 100644
index 00000000..777487d3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v1_hayao_60/processor.py
@@ -0,0 +1,133 @@
+import os
+import cv2 
+import time
+import base64
+import numpy as np
+
+__all__ = ['base64_to_cv2', 'cv2_to_base64', 'Processor']
+
+def check_dir(dir_path):
+    # 目录检查函数
+    if not os.path.exists(dir_path):
+        os.makedirs(dir_path)
+    elif os.path.isfile(dir_path):
+        os.remove(dir_path)
+        os.makedirs(dir_path)
+
+def base64_to_cv2(b64str):
+    # base64转cv2函数
+    data = base64.b64decode(b64str.encode('utf8'))
+    data = np.frombuffer(data, np.uint8)
+    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
+    return data
+
+def cv2_to_base64(image):
+    # cv2转base64函数
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+class Processor():
+    # 初始化函数
+    def __init__(
+        self, 
+        images=None, 
+        paths=None, 
+        batch_size=1, 
+        output_dir='output',
+        min_size=32,
+        max_size=1024
+    ):
+        # 变量设置
+        self.min_size = min_size
+        self.max_size = max_size
+
+        self.images = images
+        self.paths = paths
+        self.batch_size = batch_size
+        self.output_dir = output_dir
+
+        # 获取原始输入数据
+        self.datas = self.load_datas()
+
+        # 对原始输入数据进行预处理
+        self.input_datas = self.preprocess()
+
+    # 读取数据函数
+    def load_datas(self):
+        datas = []
+
+        # 读取数据列表
+        if self.paths is not None:
+            for im_path in self.paths:
+                assert os.path.isfile(im_path), "The {} isn't a valid file path.".format(im_path)
+                im = cv2.imread(im_path)
+                datas.append(im)
+
+        if self.images is not None:
+            datas = self.images
+        
+        # 返回数据列表
+        return datas
+
+    # 数据预处理函数
+    def preprocess(self):
+        input_datas = []
+
+        # 数据预处理
+        for i, img in enumerate(self.datas):
+            # 格式转换
+            img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+            
+            # 缩放图片
+            h, w = img.shape[:2]
+            if max(h,w)>self.max_size:
+                img = cv2.resize(img, (self.max_size, int(h/w*self.max_size))) if h<w else cv2.resize(img, (int(w/h*self.max_size), self.max_size))
+            elif min(h,w)<self.min_size:
+                img = cv2.resize(img, (self.min_size, int(h/w*self.min_size))) if h>w else cv2.resize(img, (int(w/h*self.min_size), self.min_size))
+
+            # 裁剪图片
+            h, w = img.shape[:2]
+            img = img[:h-(h%32), :w-(w%32), :]
+
+            # 归一化
+            img = img/127.5 - 1.0
+
+            # 新建维度
+            img = np.expand_dims(img, axis=0).astype('float32')
+
+            # 加入输入数据列表
+            input_datas.append(img)
+
+        # 数据按batch_size切分
+        input_datas = np.concatenate(input_datas, 0)
+        split_num = len(self.datas)//self.batch_size+1 if len(self.datas)%self.batch_size!=0 else len(self.datas)//self.batch_size
+        input_datas = np.array_split(input_datas, split_num)   
+
+        # 返回预处理完成的数据
+        return input_datas
+
+    def postprocess(self, outputs, visualization):
+        results = []
+
+        for im_id, output in enumerate(outputs):
+            # 反归一化
+            image = (output.squeeze() + 1.) / 2 * 255
+
+            # 限幅
+            image = np.clip(image, 0, 255).astype(np.uint8)
+
+            # 格式转换
+            image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+
+            # 可视化
+            if visualization:
+                # 检查输出目录
+                check_dir(self.output_dir)
+
+                # 写入输出图片
+                cv2.imwrite(os.path.join(self.output_dir, '%d_%d.jpg' % (im_id, time.time())), image)
+
+            results.append(image)
+
+        # 返回结果
+        return results
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_hayao_64/README.md b/hub_module/modules/image/style_transfer/animegan_v2_hayao_64/README.md
new file mode 100644
index 00000000..20c8ef9d
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_hayao_64/README.md
@@ -0,0 +1,127 @@
+## 模型概述
+AnimeGAN V2 图像风格转换模型
+
+模型可将输入的图像转换成Hayao风格
+
+模型权重转换自AnimeGAN V2官方开源项目
+
+模型所使用的权重为Hayao-64.ckpt
+
+模型详情请参考[AnimeGAN V2 开源项目](https://github.com/TachibanaYoshino/AnimeGANv2)
+
+## 模型安装
+
+```shell
+$hub install animegan_v2_hayao_64
+```
+
+
+## API 说明
+
+```python
+def style_transfer(
+    self,
+    images=None,
+    paths=None,
+    batch_size=1,
+    output_dir='output',
+    visualization=False,
+    min_size=32,
+    max_size=1024
+)
+```
+
+风格转换API，将输入的图片转换为漫画风格。
+
+转换效果图如下：
+
+![输入图像](https://ai-studio-static-online.cdn.bcebos.com/bd002c4bb6a7427daf26988770bb18648b7d8d2bfd6746bfb9a429db4867727f)
+![输出图像](https://ai-studio-static-online.cdn.bcebos.com/49620341f1fe4f00af4d93c22694897a1ae578a235844a1db1bbb4bd37bf750b)
+
+
+**参数**
+
+* images (list\[numpy.ndarray\]): 图片数据，ndarray.shape 为 \[H, W, C\]，默认为 None；
+* paths (list\[str\]): 图片的路径，默认为 None；
+* batch\_size (int): batch 的大小，默认设为 1；
+* visualization (bool): 是否将识别结果保存为图片文件，默认设为 False；
+* output\_dir (str): 图片的保存路径，默认设为 output；
+* min\_size (int): 输入图片的短边最小尺寸，默认设为 32；
+* max\_size (int): 输入图片的短边最大尺寸，默认设为 1024。
+
+
+**返回**
+
+* res (list\[numpy.ndarray\]): 输出图像数据，ndarray.shape 为 \[H, W, C\]。
+
+
+## 预测代码示例
+
+```python
+import cv2
+import paddlehub as hub
+
+# 模型加载
+# use_gpu：是否使用GPU进行预测
+model = hub.Module('animegan_v2_hayao_64', use_gpu=False)
+
+# 模型预测
+result = model.style_transfer(images=[cv2.imread('/PATH/TO/IMAGE')])
+
+# or
+# result = model.style_transfer(paths=['/PATH/TO/IMAGE'])
+```
+
+## 服务部署
+
+PaddleHub Serving可以部署一个在线图像风格转换服务。
+
+## 第一步：启动PaddleHub Serving
+
+运行启动命令：
+```shell
+$ hub serving start -m animegan_v2_hayao_64
+```
+
+这样就完成了一个图像风格转换的在线服务API的部署，默认端口号为8866。
+
+**NOTE:** 如使用GPU预测，则需要在启动服务之前，请设置CUDA\_VISIBLE\_DEVICES环境变量，否则不用设置。
+
+## 第二步：发送预测请求
+
+配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果
+
+```python
+import requests
+import json
+import cv2
+import base64
+
+
+def cv2_to_base64(image):
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+
+# 发送HTTP请求
+data = {'images':[cv2_to_base64(cv2.imread("/PATH/TO/IMAGE"))]}
+headers = {"Content-type": "application/json"}
+url = "http://127.0.0.1:8866/predict/animegan_v2_hayao_64"
+r = requests.post(url=url, headers=headers, data=json.dumps(data))
+
+# 打印预测结果
+print(r.json()["results"])
+```
+
+
+## 模型相关信息
+
+### 模型代码
+
+https://github.com/TachibanaYoshino/AnimeGANv2
+
+### 依赖
+
+paddlepaddle >= 1.8.0
+
+paddlehub >= 1.8.0
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_hayao_64/model.py b/hub_module/modules/image/style_transfer/animegan_v2_hayao_64/model.py
new file mode 100644
index 00000000..a72cf8a3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_hayao_64/model.py
@@ -0,0 +1,67 @@
+import os
+import numpy as np
+
+from paddle.fluid.core import AnalysisConfig, create_paddle_predictor
+
+__all__ = ['Model']
+
+class Model():
+    # 初始化函数
+    def __init__(self, modelpath, use_gpu):
+        # 加载模型预测器
+        self.predictor = self.load_model(modelpath, use_gpu)
+
+        # 获取模型的输入输出
+        self.input_names = self.predictor.get_input_names()
+        self.output_names = self.predictor.get_output_names()
+        self.input_tensor = self.predictor.get_input_tensor(self.input_names[0])
+        self.output_tensor = self.predictor.get_output_tensor(self.output_names[0])
+
+    # 模型加载函数
+    def load_model(self, modelpath, use_gpu):
+        # 对运行位置进行配置
+        if use_gpu:
+            try:
+                places = os.environ["CUDA_VISIBLE_DEVICES"]
+                places = int(places[0])
+            except Exception as e:
+                print('Error: %s. Please set the environment variables "CUDA_VISIBLE_DEVICES".' % e)
+                use_gpu = False
+
+        # 加载模型参数
+        config = AnalysisConfig(modelpath)
+
+        # 设置参数
+        if use_gpu:   
+            config.enable_use_gpu(100, places)
+        else:
+            config.disable_gpu()
+            config.enable_mkldnn()
+        config.disable_glog_info()
+        config.switch_ir_optim(True)
+        config.enable_memory_optim()
+        config.switch_use_feed_fetch_ops(False)
+        config.switch_specify_input_names(True)
+        
+        # 通过参数加载模型预测器
+        predictor = create_paddle_predictor(config)
+        
+        # 返回预测器
+        return predictor
+
+    # 模型预测函数
+    def predict(self, input_datas):
+        outputs = []
+
+        # 遍历输入数据进行预测
+        for input_data in input_datas:
+            self.input_tensor.copy_from_cpu(input_data)
+            self.predictor.zero_copy_run()
+            output = self.output_tensor.copy_to_cpu()
+            outputs.append(output)
+        
+        # 预测结果合并
+        outputs = np.concatenate(outputs, 0)
+
+        # 返回预测结果
+        return outputs
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_hayao_64/module.py b/hub_module/modules/image/style_transfer/animegan_v2_hayao_64/module.py
new file mode 100644
index 00000000..cdb31f67
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_hayao_64/module.py
@@ -0,0 +1,72 @@
+import os
+
+from paddlehub import Module
+from paddlehub.module.module import moduleinfo, serving
+
+from animegan_v2_hayao_64.model import Model
+from animegan_v2_hayao_64.processor import base64_to_cv2, cv2_to_base64, Processor
+
+@moduleinfo(
+    name="animegan_v2_hayao_64", # 模型名称
+    type="CV/style_transfer", # 模型类型
+    author="jm12138", # 作者名称
+    author_email="jm12138@qq.com", # 作者邮箱
+    summary="animegan_v2_hayao_64", # 模型介绍
+    version="1.0.0" # 版本号
+)
+class Animegan_V2_Hayao_64(Module):
+    # 初始化函数
+    def _initialize(self, use_gpu=False):
+        # 设置模型路径
+        self.model_path = os.path.join(self.directory, "animegan_v2_hayao_64")
+
+        # 加载模型
+        self.model = Model(self.model_path, use_gpu)     
+    
+    # 关键点检测函数
+    def style_transfer(
+        self,
+        images=None,
+        paths=None,
+        batch_size=1,
+        output_dir='output',
+        visualization=False,
+        min_size=32,
+        max_size=1024
+    ):
+        # 加载数据处理器
+        processor = Processor(
+            images, 
+            paths, 
+            batch_size, 
+            output_dir, 
+            min_size, 
+            max_size
+        )
+
+        # 模型预测
+        outputs = self.model.predict(processor.input_datas)
+
+        # 结果后处理
+        results = processor.postprocess(outputs, visualization)
+
+        # 返回结果
+        return results
+
+    # Hub Serving
+    @serving
+    def serving_method(self, images, **kwargs):
+        # 获取输入数据
+        images_decode = [base64_to_cv2(image) for image in images]
+
+        # 图片风格转换
+        results = self.style_transfer(images_decode, **kwargs)
+
+        # 对输出图片进行编码
+        encodes = []
+        for result in results:
+            encode = cv2_to_base64(result)
+            encodes.append(encode)
+            
+        # 返回结果
+        return encodes
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_hayao_64/processor.py b/hub_module/modules/image/style_transfer/animegan_v2_hayao_64/processor.py
new file mode 100644
index 00000000..777487d3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_hayao_64/processor.py
@@ -0,0 +1,133 @@
+import os
+import cv2 
+import time
+import base64
+import numpy as np
+
+__all__ = ['base64_to_cv2', 'cv2_to_base64', 'Processor']
+
+def check_dir(dir_path):
+    # 目录检查函数
+    if not os.path.exists(dir_path):
+        os.makedirs(dir_path)
+    elif os.path.isfile(dir_path):
+        os.remove(dir_path)
+        os.makedirs(dir_path)
+
+def base64_to_cv2(b64str):
+    # base64转cv2函数
+    data = base64.b64decode(b64str.encode('utf8'))
+    data = np.frombuffer(data, np.uint8)
+    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
+    return data
+
+def cv2_to_base64(image):
+    # cv2转base64函数
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+class Processor():
+    # 初始化函数
+    def __init__(
+        self, 
+        images=None, 
+        paths=None, 
+        batch_size=1, 
+        output_dir='output',
+        min_size=32,
+        max_size=1024
+    ):
+        # 变量设置
+        self.min_size = min_size
+        self.max_size = max_size
+
+        self.images = images
+        self.paths = paths
+        self.batch_size = batch_size
+        self.output_dir = output_dir
+
+        # 获取原始输入数据
+        self.datas = self.load_datas()
+
+        # 对原始输入数据进行预处理
+        self.input_datas = self.preprocess()
+
+    # 读取数据函数
+    def load_datas(self):
+        datas = []
+
+        # 读取数据列表
+        if self.paths is not None:
+            for im_path in self.paths:
+                assert os.path.isfile(im_path), "The {} isn't a valid file path.".format(im_path)
+                im = cv2.imread(im_path)
+                datas.append(im)
+
+        if self.images is not None:
+            datas = self.images
+        
+        # 返回数据列表
+        return datas
+
+    # 数据预处理函数
+    def preprocess(self):
+        input_datas = []
+
+        # 数据预处理
+        for i, img in enumerate(self.datas):
+            # 格式转换
+            img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+            
+            # 缩放图片
+            h, w = img.shape[:2]
+            if max(h,w)>self.max_size:
+                img = cv2.resize(img, (self.max_size, int(h/w*self.max_size))) if h<w else cv2.resize(img, (int(w/h*self.max_size), self.max_size))
+            elif min(h,w)<self.min_size:
+                img = cv2.resize(img, (self.min_size, int(h/w*self.min_size))) if h>w else cv2.resize(img, (int(w/h*self.min_size), self.min_size))
+
+            # 裁剪图片
+            h, w = img.shape[:2]
+            img = img[:h-(h%32), :w-(w%32), :]
+
+            # 归一化
+            img = img/127.5 - 1.0
+
+            # 新建维度
+            img = np.expand_dims(img, axis=0).astype('float32')
+
+            # 加入输入数据列表
+            input_datas.append(img)
+
+        # 数据按batch_size切分
+        input_datas = np.concatenate(input_datas, 0)
+        split_num = len(self.datas)//self.batch_size+1 if len(self.datas)%self.batch_size!=0 else len(self.datas)//self.batch_size
+        input_datas = np.array_split(input_datas, split_num)   
+
+        # 返回预处理完成的数据
+        return input_datas
+
+    def postprocess(self, outputs, visualization):
+        results = []
+
+        for im_id, output in enumerate(outputs):
+            # 反归一化
+            image = (output.squeeze() + 1.) / 2 * 255
+
+            # 限幅
+            image = np.clip(image, 0, 255).astype(np.uint8)
+
+            # 格式转换
+            image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+
+            # 可视化
+            if visualization:
+                # 检查输出目录
+                check_dir(self.output_dir)
+
+                # 写入输出图片
+                cv2.imwrite(os.path.join(self.output_dir, '%d_%d.jpg' % (im_id, time.time())), image)
+
+            results.append(image)
+
+        # 返回结果
+        return results
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_hayao_99/README.md b/hub_module/modules/image/style_transfer/animegan_v2_hayao_99/README.md
new file mode 100644
index 00000000..94b23a6e
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_hayao_99/README.md
@@ -0,0 +1,127 @@
+## 模型概述
+AnimeGAN V2 图像风格转换模型
+
+模型可将输入的图像转换成Hayao风格
+
+模型权重转换自AnimeGAN V2官方开源项目
+
+模型所使用的权重为Hayao-99.ckpt
+
+模型详情请参考[AnimeGAN V2 开源项目](https://github.com/TachibanaYoshino/AnimeGANv2)
+
+## 模型安装
+
+```shell
+$hub install animegan_v2_hayao_99
+```
+
+
+## API 说明
+
+```python
+def style_transfer(
+    self,
+    images=None,
+    paths=None,
+    batch_size=1,
+    output_dir='output',
+    visualization=False,
+    min_size=32,
+    max_size=1024
+)
+```
+
+风格转换API，将输入的图片转换为漫画风格。
+
+转换效果图如下：
+
+![输入图像](https://ai-studio-static-online.cdn.bcebos.com/bd002c4bb6a7427daf26988770bb18648b7d8d2bfd6746bfb9a429db4867727f)
+![输出图像](https://ai-studio-static-online.cdn.bcebos.com/16195e03d7e0412d990349587c587a26d9ae9e2ed1ec4fa1b4dc994e948d1f7d)
+
+
+**参数**
+
+* images (list\[numpy.ndarray\]): 图片数据，ndarray.shape 为 \[H, W, C\]，默认为 None；
+* paths (list\[str\]): 图片的路径，默认为 None；
+* batch\_size (int): batch 的大小，默认设为 1；
+* visualization (bool): 是否将识别结果保存为图片文件，默认设为 False；
+* output\_dir (str): 图片的保存路径，默认设为 output；
+* min\_size (int): 输入图片的短边最小尺寸，默认设为 32；
+* max\_size (int): 输入图片的短边最大尺寸，默认设为 1024。
+
+
+**返回**
+
+* res (list\[numpy.ndarray\]): 输出图像数据，ndarray.shape 为 \[H, W, C\]。
+
+
+## 预测代码示例
+
+```python
+import cv2
+import paddlehub as hub
+
+# 模型加载
+# use_gpu：是否使用GPU进行预测
+model = hub.Module('animegan_v2_hayao_99', use_gpu=False)
+
+# 模型预测
+result = model.style_transfer(images=[cv2.imread('/PATH/TO/IMAGE')])
+
+# or
+# result = model.style_transfer(paths=['/PATH/TO/IMAGE'])
+```
+
+## 服务部署
+
+PaddleHub Serving可以部署一个在线图像风格转换服务。
+
+## 第一步：启动PaddleHub Serving
+
+运行启动命令：
+```shell
+$ hub serving start -m animegan_v2_hayao_99
+```
+
+这样就完成了一个图像风格转换的在线服务API的部署，默认端口号为8866。
+
+**NOTE:** 如使用GPU预测，则需要在启动服务之前，请设置CUDA\_VISIBLE\_DEVICES环境变量，否则不用设置。
+
+## 第二步：发送预测请求
+
+配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果
+
+```python
+import requests
+import json
+import cv2
+import base64
+
+
+def cv2_to_base64(image):
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+
+# 发送HTTP请求
+data = {'images':[cv2_to_base64(cv2.imread("/PATH/TO/IMAGE"))]}
+headers = {"Content-type": "application/json"}
+url = "http://127.0.0.1:8866/predict/animegan_v2_hayao_99"
+r = requests.post(url=url, headers=headers, data=json.dumps(data))
+
+# 打印预测结果
+print(r.json()["results"])
+```
+
+
+## 模型相关信息
+
+### 模型代码
+
+https://github.com/TachibanaYoshino/AnimeGANv2
+
+### 依赖
+
+paddlepaddle >= 1.8.0
+
+paddlehub >= 1.8.0
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_hayao_99/model.py b/hub_module/modules/image/style_transfer/animegan_v2_hayao_99/model.py
new file mode 100644
index 00000000..a72cf8a3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_hayao_99/model.py
@@ -0,0 +1,67 @@
+import os
+import numpy as np
+
+from paddle.fluid.core import AnalysisConfig, create_paddle_predictor
+
+__all__ = ['Model']
+
+class Model():
+    # 初始化函数
+    def __init__(self, modelpath, use_gpu):
+        # 加载模型预测器
+        self.predictor = self.load_model(modelpath, use_gpu)
+
+        # 获取模型的输入输出
+        self.input_names = self.predictor.get_input_names()
+        self.output_names = self.predictor.get_output_names()
+        self.input_tensor = self.predictor.get_input_tensor(self.input_names[0])
+        self.output_tensor = self.predictor.get_output_tensor(self.output_names[0])
+
+    # 模型加载函数
+    def load_model(self, modelpath, use_gpu):
+        # 对运行位置进行配置
+        if use_gpu:
+            try:
+                places = os.environ["CUDA_VISIBLE_DEVICES"]
+                places = int(places[0])
+            except Exception as e:
+                print('Error: %s. Please set the environment variables "CUDA_VISIBLE_DEVICES".' % e)
+                use_gpu = False
+
+        # 加载模型参数
+        config = AnalysisConfig(modelpath)
+
+        # 设置参数
+        if use_gpu:   
+            config.enable_use_gpu(100, places)
+        else:
+            config.disable_gpu()
+            config.enable_mkldnn()
+        config.disable_glog_info()
+        config.switch_ir_optim(True)
+        config.enable_memory_optim()
+        config.switch_use_feed_fetch_ops(False)
+        config.switch_specify_input_names(True)
+        
+        # 通过参数加载模型预测器
+        predictor = create_paddle_predictor(config)
+        
+        # 返回预测器
+        return predictor
+
+    # 模型预测函数
+    def predict(self, input_datas):
+        outputs = []
+
+        # 遍历输入数据进行预测
+        for input_data in input_datas:
+            self.input_tensor.copy_from_cpu(input_data)
+            self.predictor.zero_copy_run()
+            output = self.output_tensor.copy_to_cpu()
+            outputs.append(output)
+        
+        # 预测结果合并
+        outputs = np.concatenate(outputs, 0)
+
+        # 返回预测结果
+        return outputs
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_hayao_99/module.py b/hub_module/modules/image/style_transfer/animegan_v2_hayao_99/module.py
new file mode 100644
index 00000000..ebb1640e
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_hayao_99/module.py
@@ -0,0 +1,72 @@
+import os
+
+from paddlehub import Module
+from paddlehub.module.module import moduleinfo, serving
+
+from animegan_v2_hayao_99.model import Model
+from animegan_v2_hayao_99.processor import base64_to_cv2, cv2_to_base64, Processor
+
+@moduleinfo(
+    name="animegan_v2_hayao_99", # 模型名称
+    type="CV/style_transfer", # 模型类型
+    author="jm12138", # 作者名称
+    author_email="jm12138@qq.com", # 作者邮箱
+    summary="animegan_v2_hayao_99", # 模型介绍
+    version="1.0.0" # 版本号
+)
+class Animegan_V2_Hayao_99(Module):
+    # 初始化函数
+    def _initialize(self, use_gpu=False):
+        # 设置模型路径
+        self.model_path = os.path.join(self.directory, "animegan_v2_hayao_99")
+
+        # 加载模型
+        self.model = Model(self.model_path, use_gpu)     
+    
+    # 关键点检测函数
+    def style_transfer(
+        self,
+        images=None,
+        paths=None,
+        batch_size=1,
+        output_dir='output',
+        visualization=False,
+        min_size=32,
+        max_size=1024
+    ):
+        # 加载数据处理器
+        processor = Processor(
+            images, 
+            paths, 
+            batch_size, 
+            output_dir, 
+            min_size, 
+            max_size
+        )
+
+        # 模型预测
+        outputs = self.model.predict(processor.input_datas)
+
+        # 结果后处理
+        results = processor.postprocess(outputs, visualization)
+
+        # 返回结果
+        return results
+
+    # Hub Serving
+    @serving
+    def serving_method(self, images, **kwargs):
+        # 获取输入数据
+        images_decode = [base64_to_cv2(image) for image in images]
+
+        # 图片风格转换
+        results = self.style_transfer(images_decode, **kwargs)
+
+        # 对输出图片进行编码
+        encodes = []
+        for result in results:
+            encode = cv2_to_base64(result)
+            encodes.append(encode)
+            
+        # 返回结果
+        return encodes
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_hayao_99/processor.py b/hub_module/modules/image/style_transfer/animegan_v2_hayao_99/processor.py
new file mode 100644
index 00000000..777487d3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_hayao_99/processor.py
@@ -0,0 +1,133 @@
+import os
+import cv2 
+import time
+import base64
+import numpy as np
+
+__all__ = ['base64_to_cv2', 'cv2_to_base64', 'Processor']
+
+def check_dir(dir_path):
+    # 目录检查函数
+    if not os.path.exists(dir_path):
+        os.makedirs(dir_path)
+    elif os.path.isfile(dir_path):
+        os.remove(dir_path)
+        os.makedirs(dir_path)
+
+def base64_to_cv2(b64str):
+    # base64转cv2函数
+    data = base64.b64decode(b64str.encode('utf8'))
+    data = np.frombuffer(data, np.uint8)
+    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
+    return data
+
+def cv2_to_base64(image):
+    # cv2转base64函数
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+class Processor():
+    # 初始化函数
+    def __init__(
+        self, 
+        images=None, 
+        paths=None, 
+        batch_size=1, 
+        output_dir='output',
+        min_size=32,
+        max_size=1024
+    ):
+        # 变量设置
+        self.min_size = min_size
+        self.max_size = max_size
+
+        self.images = images
+        self.paths = paths
+        self.batch_size = batch_size
+        self.output_dir = output_dir
+
+        # 获取原始输入数据
+        self.datas = self.load_datas()
+
+        # 对原始输入数据进行预处理
+        self.input_datas = self.preprocess()
+
+    # 读取数据函数
+    def load_datas(self):
+        datas = []
+
+        # 读取数据列表
+        if self.paths is not None:
+            for im_path in self.paths:
+                assert os.path.isfile(im_path), "The {} isn't a valid file path.".format(im_path)
+                im = cv2.imread(im_path)
+                datas.append(im)
+
+        if self.images is not None:
+            datas = self.images
+        
+        # 返回数据列表
+        return datas
+
+    # 数据预处理函数
+    def preprocess(self):
+        input_datas = []
+
+        # 数据预处理
+        for i, img in enumerate(self.datas):
+            # 格式转换
+            img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+            
+            # 缩放图片
+            h, w = img.shape[:2]
+            if max(h,w)>self.max_size:
+                img = cv2.resize(img, (self.max_size, int(h/w*self.max_size))) if h<w else cv2.resize(img, (int(w/h*self.max_size), self.max_size))
+            elif min(h,w)<self.min_size:
+                img = cv2.resize(img, (self.min_size, int(h/w*self.min_size))) if h>w else cv2.resize(img, (int(w/h*self.min_size), self.min_size))
+
+            # 裁剪图片
+            h, w = img.shape[:2]
+            img = img[:h-(h%32), :w-(w%32), :]
+
+            # 归一化
+            img = img/127.5 - 1.0
+
+            # 新建维度
+            img = np.expand_dims(img, axis=0).astype('float32')
+
+            # 加入输入数据列表
+            input_datas.append(img)
+
+        # 数据按batch_size切分
+        input_datas = np.concatenate(input_datas, 0)
+        split_num = len(self.datas)//self.batch_size+1 if len(self.datas)%self.batch_size!=0 else len(self.datas)//self.batch_size
+        input_datas = np.array_split(input_datas, split_num)   
+
+        # 返回预处理完成的数据
+        return input_datas
+
+    def postprocess(self, outputs, visualization):
+        results = []
+
+        for im_id, output in enumerate(outputs):
+            # 反归一化
+            image = (output.squeeze() + 1.) / 2 * 255
+
+            # 限幅
+            image = np.clip(image, 0, 255).astype(np.uint8)
+
+            # 格式转换
+            image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+
+            # 可视化
+            if visualization:
+                # 检查输出目录
+                check_dir(self.output_dir)
+
+                # 写入输出图片
+                cv2.imwrite(os.path.join(self.output_dir, '%d_%d.jpg' % (im_id, time.time())), image)
+
+            results.append(image)
+
+        # 返回结果
+        return results
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_paprika_54/README.md b/hub_module/modules/image/style_transfer/animegan_v2_paprika_54/README.md
new file mode 100644
index 00000000..01eabc69
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_paprika_54/README.md
@@ -0,0 +1,127 @@
+## 模型概述
+AnimeGAN V2 图像风格转换模型
+
+模型可将输入的图像转换成Paprika风格
+
+模型权重转换自AnimeGAN V2官方开源项目
+
+模型所使用的权重为Paprika-54.ckpt
+
+模型详情请参考[AnimeGAN V2 开源项目](https://github.com/TachibanaYoshino/AnimeGANv2)
+
+## 模型安装
+
+```shell
+$hub install animegan_v2_paprika_54
+```
+
+
+## API 说明
+
+```python
+def style_transfer(
+    self,
+    images=None,
+    paths=None,
+    batch_size=1,
+    output_dir='output',
+    visualization=False,
+    min_size=32,
+    max_size=1024
+)
+```
+
+风格转换API，将输入的图片转换为漫画风格。
+
+转换效果图如下：
+
+![输入图像](https://ai-studio-static-online.cdn.bcebos.com/bd002c4bb6a7427daf26988770bb18648b7d8d2bfd6746bfb9a429db4867727f)
+![输出图像](https://ai-studio-static-online.cdn.bcebos.com/08ee95c94e0b4d4e8b2855a6ed40af5853b40c0047b3421aaa2f7c877fac5130)
+
+
+**参数**
+
+* images (list\[numpy.ndarray\]): 图片数据，ndarray.shape 为 \[H, W, C\]，默认为 None；
+* paths (list\[str\]): 图片的路径，默认为 None；
+* batch\_size (int): batch 的大小，默认设为 1；
+* visualization (bool): 是否将识别结果保存为图片文件，默认设为 False；
+* output\_dir (str): 图片的保存路径，默认设为 output；
+* min\_size (int): 输入图片的短边最小尺寸，默认设为 32；
+* max\_size (int): 输入图片的短边最大尺寸，默认设为 1024。
+
+
+**返回**
+
+* res (list\[numpy.ndarray\]): 输出图像数据，ndarray.shape 为 \[H, W, C\]。
+
+
+## 预测代码示例
+
+```python
+import cv2
+import paddlehub as hub
+
+# 模型加载
+# use_gpu：是否使用GPU进行预测
+model = hub.Module('animegan_v2_paprika_54', use_gpu=False)
+
+# 模型预测
+result = model.style_transfer(images=[cv2.imread('/PATH/TO/IMAGE')])
+
+# or
+# result = model.style_transfer(paths=['/PATH/TO/IMAGE'])
+```
+
+## 服务部署
+
+PaddleHub Serving可以部署一个在线图像风格转换服务。
+
+## 第一步：启动PaddleHub Serving
+
+运行启动命令：
+```shell
+$ hub serving start -m animegan_v2_paprika_54
+```
+
+这样就完成了一个图像风格转换的在线服务API的部署，默认端口号为8866。
+
+**NOTE:** 如使用GPU预测，则需要在启动服务之前，请设置CUDA\_VISIBLE\_DEVICES环境变量，否则不用设置。
+
+## 第二步：发送预测请求
+
+配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果
+
+```python
+import requests
+import json
+import cv2
+import base64
+
+
+def cv2_to_base64(image):
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+
+# 发送HTTP请求
+data = {'images':[cv2_to_base64(cv2.imread("/PATH/TO/IMAGE"))]}
+headers = {"Content-type": "application/json"}
+url = "http://127.0.0.1:8866/predict/animegan_v2_paprika_54"
+r = requests.post(url=url, headers=headers, data=json.dumps(data))
+
+# 打印预测结果
+print(r.json()["results"])
+```
+
+
+## 模型相关信息
+
+### 模型代码
+
+https://github.com/TachibanaYoshino/AnimeGANv2
+
+### 依赖
+
+paddlepaddle >= 1.8.0
+
+paddlehub >= 1.8.0
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_paprika_54/model.py b/hub_module/modules/image/style_transfer/animegan_v2_paprika_54/model.py
new file mode 100644
index 00000000..a72cf8a3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_paprika_54/model.py
@@ -0,0 +1,67 @@
+import os
+import numpy as np
+
+from paddle.fluid.core import AnalysisConfig, create_paddle_predictor
+
+__all__ = ['Model']
+
+class Model():
+    # 初始化函数
+    def __init__(self, modelpath, use_gpu):
+        # 加载模型预测器
+        self.predictor = self.load_model(modelpath, use_gpu)
+
+        # 获取模型的输入输出
+        self.input_names = self.predictor.get_input_names()
+        self.output_names = self.predictor.get_output_names()
+        self.input_tensor = self.predictor.get_input_tensor(self.input_names[0])
+        self.output_tensor = self.predictor.get_output_tensor(self.output_names[0])
+
+    # 模型加载函数
+    def load_model(self, modelpath, use_gpu):
+        # 对运行位置进行配置
+        if use_gpu:
+            try:
+                places = os.environ["CUDA_VISIBLE_DEVICES"]
+                places = int(places[0])
+            except Exception as e:
+                print('Error: %s. Please set the environment variables "CUDA_VISIBLE_DEVICES".' % e)
+                use_gpu = False
+
+        # 加载模型参数
+        config = AnalysisConfig(modelpath)
+
+        # 设置参数
+        if use_gpu:   
+            config.enable_use_gpu(100, places)
+        else:
+            config.disable_gpu()
+            config.enable_mkldnn()
+        config.disable_glog_info()
+        config.switch_ir_optim(True)
+        config.enable_memory_optim()
+        config.switch_use_feed_fetch_ops(False)
+        config.switch_specify_input_names(True)
+        
+        # 通过参数加载模型预测器
+        predictor = create_paddle_predictor(config)
+        
+        # 返回预测器
+        return predictor
+
+    # 模型预测函数
+    def predict(self, input_datas):
+        outputs = []
+
+        # 遍历输入数据进行预测
+        for input_data in input_datas:
+            self.input_tensor.copy_from_cpu(input_data)
+            self.predictor.zero_copy_run()
+            output = self.output_tensor.copy_to_cpu()
+            outputs.append(output)
+        
+        # 预测结果合并
+        outputs = np.concatenate(outputs, 0)
+
+        # 返回预测结果
+        return outputs
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_paprika_54/module.py b/hub_module/modules/image/style_transfer/animegan_v2_paprika_54/module.py
new file mode 100644
index 00000000..4631c281
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_paprika_54/module.py
@@ -0,0 +1,72 @@
+import os
+
+from paddlehub import Module
+from paddlehub.module.module import moduleinfo, serving
+
+from animegan_v2_paprika_54.model import Model
+from animegan_v2_paprika_54.processor import base64_to_cv2, cv2_to_base64, Processor
+
+@moduleinfo(
+    name="animegan_v2_paprika_54", # 模型名称
+    type="CV/style_transfer", # 模型类型
+    author="jm12138", # 作者名称
+    author_email="jm12138@qq.com", # 作者邮箱
+    summary="animegan_v2_paprika_54", # 模型介绍
+    version="1.0.0" # 版本号
+)
+class Animegan_V2_Paprika_54(Module):
+    # 初始化函数
+    def _initialize(self, use_gpu=False):
+        # 设置模型路径
+        self.model_path = os.path.join(self.directory, "animegan_v2_paprika_54")
+
+        # 加载模型
+        self.model = Model(self.model_path, use_gpu)     
+    
+    # 关键点检测函数
+    def style_transfer(
+        self,
+        images=None,
+        paths=None,
+        batch_size=1,
+        output_dir='output',
+        visualization=False,
+        min_size=32,
+        max_size=1024
+    ):
+        # 加载数据处理器
+        processor = Processor(
+            images, 
+            paths, 
+            batch_size, 
+            output_dir, 
+            min_size, 
+            max_size
+        )
+
+        # 模型预测
+        outputs = self.model.predict(processor.input_datas)
+
+        # 结果后处理
+        results = processor.postprocess(outputs, visualization)
+
+        # 返回结果
+        return results
+
+    # Hub Serving
+    @serving
+    def serving_method(self, images, **kwargs):
+        # 获取输入数据
+        images_decode = [base64_to_cv2(image) for image in images]
+
+        # 图片风格转换
+        results = self.style_transfer(images_decode, **kwargs)
+
+        # 对输出图片进行编码
+        encodes = []
+        for result in results:
+            encode = cv2_to_base64(result)
+            encodes.append(encode)
+            
+        # 返回结果
+        return encodes
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_paprika_54/processor.py b/hub_module/modules/image/style_transfer/animegan_v2_paprika_54/processor.py
new file mode 100644
index 00000000..777487d3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_paprika_54/processor.py
@@ -0,0 +1,133 @@
+import os
+import cv2 
+import time
+import base64
+import numpy as np
+
+__all__ = ['base64_to_cv2', 'cv2_to_base64', 'Processor']
+
+def check_dir(dir_path):
+    # 目录检查函数
+    if not os.path.exists(dir_path):
+        os.makedirs(dir_path)
+    elif os.path.isfile(dir_path):
+        os.remove(dir_path)
+        os.makedirs(dir_path)
+
+def base64_to_cv2(b64str):
+    # base64转cv2函数
+    data = base64.b64decode(b64str.encode('utf8'))
+    data = np.frombuffer(data, np.uint8)
+    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
+    return data
+
+def cv2_to_base64(image):
+    # cv2转base64函数
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+class Processor():
+    # 初始化函数
+    def __init__(
+        self, 
+        images=None, 
+        paths=None, 
+        batch_size=1, 
+        output_dir='output',
+        min_size=32,
+        max_size=1024
+    ):
+        # 变量设置
+        self.min_size = min_size
+        self.max_size = max_size
+
+        self.images = images
+        self.paths = paths
+        self.batch_size = batch_size
+        self.output_dir = output_dir
+
+        # 获取原始输入数据
+        self.datas = self.load_datas()
+
+        # 对原始输入数据进行预处理
+        self.input_datas = self.preprocess()
+
+    # 读取数据函数
+    def load_datas(self):
+        datas = []
+
+        # 读取数据列表
+        if self.paths is not None:
+            for im_path in self.paths:
+                assert os.path.isfile(im_path), "The {} isn't a valid file path.".format(im_path)
+                im = cv2.imread(im_path)
+                datas.append(im)
+
+        if self.images is not None:
+            datas = self.images
+        
+        # 返回数据列表
+        return datas
+
+    # 数据预处理函数
+    def preprocess(self):
+        input_datas = []
+
+        # 数据预处理
+        for i, img in enumerate(self.datas):
+            # 格式转换
+            img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+            
+            # 缩放图片
+            h, w = img.shape[:2]
+            if max(h,w)>self.max_size:
+                img = cv2.resize(img, (self.max_size, int(h/w*self.max_size))) if h<w else cv2.resize(img, (int(w/h*self.max_size), self.max_size))
+            elif min(h,w)<self.min_size:
+                img = cv2.resize(img, (self.min_size, int(h/w*self.min_size))) if h>w else cv2.resize(img, (int(w/h*self.min_size), self.min_size))
+
+            # 裁剪图片
+            h, w = img.shape[:2]
+            img = img[:h-(h%32), :w-(w%32), :]
+
+            # 归一化
+            img = img/127.5 - 1.0
+
+            # 新建维度
+            img = np.expand_dims(img, axis=0).astype('float32')
+
+            # 加入输入数据列表
+            input_datas.append(img)
+
+        # 数据按batch_size切分
+        input_datas = np.concatenate(input_datas, 0)
+        split_num = len(self.datas)//self.batch_size+1 if len(self.datas)%self.batch_size!=0 else len(self.datas)//self.batch_size
+        input_datas = np.array_split(input_datas, split_num)   
+
+        # 返回预处理完成的数据
+        return input_datas
+
+    def postprocess(self, outputs, visualization):
+        results = []
+
+        for im_id, output in enumerate(outputs):
+            # 反归一化
+            image = (output.squeeze() + 1.) / 2 * 255
+
+            # 限幅
+            image = np.clip(image, 0, 255).astype(np.uint8)
+
+            # 格式转换
+            image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+
+            # 可视化
+            if visualization:
+                # 检查输出目录
+                check_dir(self.output_dir)
+
+                # 写入输出图片
+                cv2.imwrite(os.path.join(self.output_dir, '%d_%d.jpg' % (im_id, time.time())), image)
+
+            results.append(image)
+
+        # 返回结果
+        return results
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_paprika_74/README.md b/hub_module/modules/image/style_transfer/animegan_v2_paprika_74/README.md
new file mode 100644
index 00000000..74f32987
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_paprika_74/README.md
@@ -0,0 +1,127 @@
+## 模型概述
+AnimeGAN V2 图像风格转换模型
+
+模型可将输入的图像转换成Paprika风格
+
+模型权重转换自AnimeGAN V2官方开源项目
+
+模型所使用的权重为Paprika-74.ckpt
+
+模型详情请参考[AnimeGAN V2 开源项目](https://github.com/TachibanaYoshino/AnimeGANv2)
+
+## 模型安装
+
+```shell
+$hub install animegan_v2_paprika_74
+```
+
+
+## API 说明
+
+```python
+def style_transfer(
+    self,
+    images=None,
+    paths=None,
+    batch_size=1,
+    output_dir='output',
+    visualization=False,
+    min_size=32,
+    max_size=1024
+)
+```
+
+风格转换API，将输入的图片转换为漫画风格。
+
+转换效果图如下：
+
+![输入图像](https://ai-studio-static-online.cdn.bcebos.com/bd002c4bb6a7427daf26988770bb18648b7d8d2bfd6746bfb9a429db4867727f)
+![输出图像](https://ai-studio-static-online.cdn.bcebos.com/6574669d87b24bab9627c6e33896528b4a0bf5af1cd84ca29655d68719f2d551)
+
+
+**参数**
+
+* images (list\[numpy.ndarray\]): 图片数据，ndarray.shape 为 \[H, W, C\]，默认为 None；
+* paths (list\[str\]): 图片的路径，默认为 None；
+* batch\_size (int): batch 的大小，默认设为 1；
+* visualization (bool): 是否将识别结果保存为图片文件，默认设为 False；
+* output\_dir (str): 图片的保存路径，默认设为 output；
+* min\_size (int): 输入图片的短边最小尺寸，默认设为 32；
+* max\_size (int): 输入图片的短边最大尺寸，默认设为 1024。
+
+
+**返回**
+
+* res (list\[numpy.ndarray\]): 输出图像数据，ndarray.shape 为 \[H, W, C\]。
+
+
+## 预测代码示例
+
+```python
+import cv2
+import paddlehub as hub
+
+# 模型加载
+# use_gpu：是否使用GPU进行预测
+model = hub.Module('animegan_v2_paprika_74', use_gpu=False)
+
+# 模型预测
+result = model.style_transfer(images=[cv2.imread('/PATH/TO/IMAGE')])
+
+# or
+# result = model.style_transfer(paths=['/PATH/TO/IMAGE'])
+```
+
+## 服务部署
+
+PaddleHub Serving可以部署一个在线图像风格转换服务。
+
+## 第一步：启动PaddleHub Serving
+
+运行启动命令：
+```shell
+$ hub serving start -m animegan_v2_paprika_74
+```
+
+这样就完成了一个图像风格转换的在线服务API的部署，默认端口号为8866。
+
+**NOTE:** 如使用GPU预测，则需要在启动服务之前，请设置CUDA\_VISIBLE\_DEVICES环境变量，否则不用设置。
+
+## 第二步：发送预测请求
+
+配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果
+
+```python
+import requests
+import json
+import cv2
+import base64
+
+
+def cv2_to_base64(image):
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+
+# 发送HTTP请求
+data = {'images':[cv2_to_base64(cv2.imread("/PATH/TO/IMAGE"))]}
+headers = {"Content-type": "application/json"}
+url = "http://127.0.0.1:8866/predict/animegan_v2_paprika_74"
+r = requests.post(url=url, headers=headers, data=json.dumps(data))
+
+# 打印预测结果
+print(r.json()["results"])
+```
+
+
+## 模型相关信息
+
+### 模型代码
+
+https://github.com/TachibanaYoshino/AnimeGANv2
+
+### 依赖
+
+paddlepaddle >= 1.8.0
+
+paddlehub >= 1.8.0
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_paprika_74/model.py b/hub_module/modules/image/style_transfer/animegan_v2_paprika_74/model.py
new file mode 100644
index 00000000..a72cf8a3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_paprika_74/model.py
@@ -0,0 +1,67 @@
+import os
+import numpy as np
+
+from paddle.fluid.core import AnalysisConfig, create_paddle_predictor
+
+__all__ = ['Model']
+
+class Model():
+    # 初始化函数
+    def __init__(self, modelpath, use_gpu):
+        # 加载模型预测器
+        self.predictor = self.load_model(modelpath, use_gpu)
+
+        # 获取模型的输入输出
+        self.input_names = self.predictor.get_input_names()
+        self.output_names = self.predictor.get_output_names()
+        self.input_tensor = self.predictor.get_input_tensor(self.input_names[0])
+        self.output_tensor = self.predictor.get_output_tensor(self.output_names[0])
+
+    # 模型加载函数
+    def load_model(self, modelpath, use_gpu):
+        # 对运行位置进行配置
+        if use_gpu:
+            try:
+                places = os.environ["CUDA_VISIBLE_DEVICES"]
+                places = int(places[0])
+            except Exception as e:
+                print('Error: %s. Please set the environment variables "CUDA_VISIBLE_DEVICES".' % e)
+                use_gpu = False
+
+        # 加载模型参数
+        config = AnalysisConfig(modelpath)
+
+        # 设置参数
+        if use_gpu:   
+            config.enable_use_gpu(100, places)
+        else:
+            config.disable_gpu()
+            config.enable_mkldnn()
+        config.disable_glog_info()
+        config.switch_ir_optim(True)
+        config.enable_memory_optim()
+        config.switch_use_feed_fetch_ops(False)
+        config.switch_specify_input_names(True)
+        
+        # 通过参数加载模型预测器
+        predictor = create_paddle_predictor(config)
+        
+        # 返回预测器
+        return predictor
+
+    # 模型预测函数
+    def predict(self, input_datas):
+        outputs = []
+
+        # 遍历输入数据进行预测
+        for input_data in input_datas:
+            self.input_tensor.copy_from_cpu(input_data)
+            self.predictor.zero_copy_run()
+            output = self.output_tensor.copy_to_cpu()
+            outputs.append(output)
+        
+        # 预测结果合并
+        outputs = np.concatenate(outputs, 0)
+
+        # 返回预测结果
+        return outputs
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_paprika_74/module.py b/hub_module/modules/image/style_transfer/animegan_v2_paprika_74/module.py
new file mode 100644
index 00000000..7d54fafa
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_paprika_74/module.py
@@ -0,0 +1,72 @@
+import os
+
+from paddlehub import Module
+from paddlehub.module.module import moduleinfo, serving
+
+from animegan_v2_paprika_74.model import Model
+from animegan_v2_paprika_74.processor import base64_to_cv2, cv2_to_base64, Processor
+
+@moduleinfo(
+    name="animegan_v2_paprika_74", # 模型名称
+    type="CV/style_transfer", # 模型类型
+    author="jm12138", # 作者名称
+    author_email="jm12138@qq.com", # 作者邮箱
+    summary="animegan_v2_paprika_74", # 模型介绍
+    version="1.0.0" # 版本号
+)
+class Animegan_V2_Paprika_74(Module):
+    # 初始化函数
+    def _initialize(self, use_gpu=False):
+        # 设置模型路径
+        self.model_path = os.path.join(self.directory, "animegan_v2_paprika_74")
+
+        # 加载模型
+        self.model = Model(self.model_path, use_gpu)     
+    
+    # 关键点检测函数
+    def style_transfer(
+        self,
+        images=None,
+        paths=None,
+        batch_size=1,
+        output_dir='output',
+        visualization=False,
+        min_size=32,
+        max_size=1024
+    ):
+        # 加载数据处理器
+        processor = Processor(
+            images, 
+            paths, 
+            batch_size, 
+            output_dir, 
+            min_size, 
+            max_size
+        )
+
+        # 模型预测
+        outputs = self.model.predict(processor.input_datas)
+
+        # 结果后处理
+        results = processor.postprocess(outputs, visualization)
+
+        # 返回结果
+        return results
+
+    # Hub Serving
+    @serving
+    def serving_method(self, images, **kwargs):
+        # 获取输入数据
+        images_decode = [base64_to_cv2(image) for image in images]
+
+        # 图片风格转换
+        results = self.style_transfer(images_decode, **kwargs)
+
+        # 对输出图片进行编码
+        encodes = []
+        for result in results:
+            encode = cv2_to_base64(result)
+            encodes.append(encode)
+            
+        # 返回结果
+        return encodes
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_paprika_74/processor.py b/hub_module/modules/image/style_transfer/animegan_v2_paprika_74/processor.py
new file mode 100644
index 00000000..777487d3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_paprika_74/processor.py
@@ -0,0 +1,133 @@
+import os
+import cv2 
+import time
+import base64
+import numpy as np
+
+__all__ = ['base64_to_cv2', 'cv2_to_base64', 'Processor']
+
+def check_dir(dir_path):
+    # 目录检查函数
+    if not os.path.exists(dir_path):
+        os.makedirs(dir_path)
+    elif os.path.isfile(dir_path):
+        os.remove(dir_path)
+        os.makedirs(dir_path)
+
+def base64_to_cv2(b64str):
+    # base64转cv2函数
+    data = base64.b64decode(b64str.encode('utf8'))
+    data = np.frombuffer(data, np.uint8)
+    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
+    return data
+
+def cv2_to_base64(image):
+    # cv2转base64函数
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+class Processor():
+    # 初始化函数
+    def __init__(
+        self, 
+        images=None, 
+        paths=None, 
+        batch_size=1, 
+        output_dir='output',
+        min_size=32,
+        max_size=1024
+    ):
+        # 变量设置
+        self.min_size = min_size
+        self.max_size = max_size
+
+        self.images = images
+        self.paths = paths
+        self.batch_size = batch_size
+        self.output_dir = output_dir
+
+        # 获取原始输入数据
+        self.datas = self.load_datas()
+
+        # 对原始输入数据进行预处理
+        self.input_datas = self.preprocess()
+
+    # 读取数据函数
+    def load_datas(self):
+        datas = []
+
+        # 读取数据列表
+        if self.paths is not None:
+            for im_path in self.paths:
+                assert os.path.isfile(im_path), "The {} isn't a valid file path.".format(im_path)
+                im = cv2.imread(im_path)
+                datas.append(im)
+
+        if self.images is not None:
+            datas = self.images
+        
+        # 返回数据列表
+        return datas
+
+    # 数据预处理函数
+    def preprocess(self):
+        input_datas = []
+
+        # 数据预处理
+        for i, img in enumerate(self.datas):
+            # 格式转换
+            img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+            
+            # 缩放图片
+            h, w = img.shape[:2]
+            if max(h,w)>self.max_size:
+                img = cv2.resize(img, (self.max_size, int(h/w*self.max_size))) if h<w else cv2.resize(img, (int(w/h*self.max_size), self.max_size))
+            elif min(h,w)<self.min_size:
+                img = cv2.resize(img, (self.min_size, int(h/w*self.min_size))) if h>w else cv2.resize(img, (int(w/h*self.min_size), self.min_size))
+
+            # 裁剪图片
+            h, w = img.shape[:2]
+            img = img[:h-(h%32), :w-(w%32), :]
+
+            # 归一化
+            img = img/127.5 - 1.0
+
+            # 新建维度
+            img = np.expand_dims(img, axis=0).astype('float32')
+
+            # 加入输入数据列表
+            input_datas.append(img)
+
+        # 数据按batch_size切分
+        input_datas = np.concatenate(input_datas, 0)
+        split_num = len(self.datas)//self.batch_size+1 if len(self.datas)%self.batch_size!=0 else len(self.datas)//self.batch_size
+        input_datas = np.array_split(input_datas, split_num)   
+
+        # 返回预处理完成的数据
+        return input_datas
+
+    def postprocess(self, outputs, visualization):
+        results = []
+
+        for im_id, output in enumerate(outputs):
+            # 反归一化
+            image = (output.squeeze() + 1.) / 2 * 255
+
+            # 限幅
+            image = np.clip(image, 0, 255).astype(np.uint8)
+
+            # 格式转换
+            image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+
+            # 可视化
+            if visualization:
+                # 检查输出目录
+                check_dir(self.output_dir)
+
+                # 写入输出图片
+                cv2.imwrite(os.path.join(self.output_dir, '%d_%d.jpg' % (im_id, time.time())), image)
+
+            results.append(image)
+
+        # 返回结果
+        return results
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_paprika_97/README.md b/hub_module/modules/image/style_transfer/animegan_v2_paprika_97/README.md
new file mode 100644
index 00000000..8baa6762
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_paprika_97/README.md
@@ -0,0 +1,127 @@
+## 模型概述
+AnimeGAN V2 图像风格转换模型
+
+模型可将输入的图像转换成Paprika风格
+
+模型权重转换自AnimeGAN V2官方开源项目
+
+模型所使用的权重为Paprika-97.ckpt
+
+模型详情请参考[AnimeGAN V2 开源项目](https://github.com/TachibanaYoshino/AnimeGANv2)
+
+## 模型安装
+
+```shell
+$hub install animegan_v2_paprika_97
+```
+
+
+## API 说明
+
+```python
+def style_transfer(
+    self,
+    images=None,
+    paths=None,
+    batch_size=1,
+    output_dir='output',
+    visualization=False,
+    min_size=32,
+    max_size=1024
+)
+```
+
+风格转换API，将输入的图片转换为漫画风格。
+
+转换效果图如下：
+
+![输入图像](https://ai-studio-static-online.cdn.bcebos.com/bd002c4bb6a7427daf26988770bb18648b7d8d2bfd6746bfb9a429db4867727f)
+![输出图像](https://ai-studio-static-online.cdn.bcebos.com/3b962a18a22e43028cc5530db1c5adb1a42e6aae4bb74b8598ee30ed52b59c8b)
+
+
+**参数**
+
+* images (list\[numpy.ndarray\]): 图片数据，ndarray.shape 为 \[H, W, C\]，默认为 None；
+* paths (list\[str\]): 图片的路径，默认为 None；
+* batch\_size (int): batch 的大小，默认设为 1；
+* visualization (bool): 是否将识别结果保存为图片文件，默认设为 False；
+* output\_dir (str): 图片的保存路径，默认设为 output；
+* min\_size (int): 输入图片的短边最小尺寸，默认设为 32；
+* max\_size (int): 输入图片的短边最大尺寸，默认设为 1024。
+
+
+**返回**
+
+* res (list\[numpy.ndarray\]): 输出图像数据，ndarray.shape 为 \[H, W, C\]。
+
+
+## 预测代码示例
+
+```python
+import cv2
+import paddlehub as hub
+
+# 模型加载
+# use_gpu：是否使用GPU进行预测
+model = hub.Module('animegan_v2_paprika_97', use_gpu=False)
+
+# 模型预测
+result = model.style_transfer(images=[cv2.imread('/PATH/TO/IMAGE')])
+
+# or
+# result = model.style_transfer(paths=['/PATH/TO/IMAGE'])
+```
+
+## 服务部署
+
+PaddleHub Serving可以部署一个在线图像风格转换服务。
+
+## 第一步：启动PaddleHub Serving
+
+运行启动命令：
+```shell
+$ hub serving start -m animegan_v2_paprika_97
+```
+
+这样就完成了一个图像风格转换的在线服务API的部署，默认端口号为8866。
+
+**NOTE:** 如使用GPU预测，则需要在启动服务之前，请设置CUDA\_VISIBLE\_DEVICES环境变量，否则不用设置。
+
+## 第二步：发送预测请求
+
+配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果
+
+```python
+import requests
+import json
+import cv2
+import base64
+
+
+def cv2_to_base64(image):
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+
+# 发送HTTP请求
+data = {'images':[cv2_to_base64(cv2.imread("/PATH/TO/IMAGE"))]}
+headers = {"Content-type": "application/json"}
+url = "http://127.0.0.1:8866/predict/animegan_v2_paprika_97"
+r = requests.post(url=url, headers=headers, data=json.dumps(data))
+
+# 打印预测结果
+print(r.json()["results"])
+```
+
+
+## 模型相关信息
+
+### 模型代码
+
+https://github.com/TachibanaYoshino/AnimeGANv2
+
+### 依赖
+
+paddlepaddle >= 1.8.0
+
+paddlehub >= 1.8.0
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_paprika_97/model.py b/hub_module/modules/image/style_transfer/animegan_v2_paprika_97/model.py
new file mode 100644
index 00000000..a72cf8a3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_paprika_97/model.py
@@ -0,0 +1,67 @@
+import os
+import numpy as np
+
+from paddle.fluid.core import AnalysisConfig, create_paddle_predictor
+
+__all__ = ['Model']
+
+class Model():
+    # 初始化函数
+    def __init__(self, modelpath, use_gpu):
+        # 加载模型预测器
+        self.predictor = self.load_model(modelpath, use_gpu)
+
+        # 获取模型的输入输出
+        self.input_names = self.predictor.get_input_names()
+        self.output_names = self.predictor.get_output_names()
+        self.input_tensor = self.predictor.get_input_tensor(self.input_names[0])
+        self.output_tensor = self.predictor.get_output_tensor(self.output_names[0])
+
+    # 模型加载函数
+    def load_model(self, modelpath, use_gpu):
+        # 对运行位置进行配置
+        if use_gpu:
+            try:
+                places = os.environ["CUDA_VISIBLE_DEVICES"]
+                places = int(places[0])
+            except Exception as e:
+                print('Error: %s. Please set the environment variables "CUDA_VISIBLE_DEVICES".' % e)
+                use_gpu = False
+
+        # 加载模型参数
+        config = AnalysisConfig(modelpath)
+
+        # 设置参数
+        if use_gpu:   
+            config.enable_use_gpu(100, places)
+        else:
+            config.disable_gpu()
+            config.enable_mkldnn()
+        config.disable_glog_info()
+        config.switch_ir_optim(True)
+        config.enable_memory_optim()
+        config.switch_use_feed_fetch_ops(False)
+        config.switch_specify_input_names(True)
+        
+        # 通过参数加载模型预测器
+        predictor = create_paddle_predictor(config)
+        
+        # 返回预测器
+        return predictor
+
+    # 模型预测函数
+    def predict(self, input_datas):
+        outputs = []
+
+        # 遍历输入数据进行预测
+        for input_data in input_datas:
+            self.input_tensor.copy_from_cpu(input_data)
+            self.predictor.zero_copy_run()
+            output = self.output_tensor.copy_to_cpu()
+            outputs.append(output)
+        
+        # 预测结果合并
+        outputs = np.concatenate(outputs, 0)
+
+        # 返回预测结果
+        return outputs
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_paprika_97/module.py b/hub_module/modules/image/style_transfer/animegan_v2_paprika_97/module.py
new file mode 100644
index 00000000..c57d7172
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_paprika_97/module.py
@@ -0,0 +1,72 @@
+import os
+
+from paddlehub import Module
+from paddlehub.module.module import moduleinfo, serving
+
+from animegan_v2_paprika_97.model import Model
+from animegan_v2_paprika_97.processor import base64_to_cv2, cv2_to_base64, Processor
+
+@moduleinfo(
+    name="animegan_v2_paprika_97", # 模型名称
+    type="CV/style_transfer", # 模型类型
+    author="jm12138", # 作者名称
+    author_email="jm12138@qq.com", # 作者邮箱
+    summary="animegan_v2_paprika_97", # 模型介绍
+    version="1.0.0" # 版本号
+)
+class Animegan_V2_Paprika_97(Module):
+    # 初始化函数
+    def _initialize(self, use_gpu=False):
+        # 设置模型路径
+        self.model_path = os.path.join(self.directory, "animegan_v2_paprika_97")
+
+        # 加载模型
+        self.model = Model(self.model_path, use_gpu)     
+    
+    # 关键点检测函数
+    def style_transfer(
+        self,
+        images=None,
+        paths=None,
+        batch_size=1,
+        output_dir='output',
+        visualization=False,
+        min_size=32,
+        max_size=1024
+    ):
+        # 加载数据处理器
+        processor = Processor(
+            images, 
+            paths, 
+            batch_size, 
+            output_dir, 
+            min_size, 
+            max_size
+        )
+
+        # 模型预测
+        outputs = self.model.predict(processor.input_datas)
+
+        # 结果后处理
+        results = processor.postprocess(outputs, visualization)
+
+        # 返回结果
+        return results
+
+    # Hub Serving
+    @serving
+    def serving_method(self, images, **kwargs):
+        # 获取输入数据
+        images_decode = [base64_to_cv2(image) for image in images]
+
+        # 图片风格转换
+        results = self.style_transfer(images_decode, **kwargs)
+
+        # 对输出图片进行编码
+        encodes = []
+        for result in results:
+            encode = cv2_to_base64(result)
+            encodes.append(encode)
+            
+        # 返回结果
+        return encodes
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_paprika_97/processor.py b/hub_module/modules/image/style_transfer/animegan_v2_paprika_97/processor.py
new file mode 100644
index 00000000..777487d3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_paprika_97/processor.py
@@ -0,0 +1,133 @@
+import os
+import cv2 
+import time
+import base64
+import numpy as np
+
+__all__ = ['base64_to_cv2', 'cv2_to_base64', 'Processor']
+
+def check_dir(dir_path):
+    # 目录检查函数
+    if not os.path.exists(dir_path):
+        os.makedirs(dir_path)
+    elif os.path.isfile(dir_path):
+        os.remove(dir_path)
+        os.makedirs(dir_path)
+
+def base64_to_cv2(b64str):
+    # base64转cv2函数
+    data = base64.b64decode(b64str.encode('utf8'))
+    data = np.frombuffer(data, np.uint8)
+    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
+    return data
+
+def cv2_to_base64(image):
+    # cv2转base64函数
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+class Processor():
+    # 初始化函数
+    def __init__(
+        self, 
+        images=None, 
+        paths=None, 
+        batch_size=1, 
+        output_dir='output',
+        min_size=32,
+        max_size=1024
+    ):
+        # 变量设置
+        self.min_size = min_size
+        self.max_size = max_size
+
+        self.images = images
+        self.paths = paths
+        self.batch_size = batch_size
+        self.output_dir = output_dir
+
+        # 获取原始输入数据
+        self.datas = self.load_datas()
+
+        # 对原始输入数据进行预处理
+        self.input_datas = self.preprocess()
+
+    # 读取数据函数
+    def load_datas(self):
+        datas = []
+
+        # 读取数据列表
+        if self.paths is not None:
+            for im_path in self.paths:
+                assert os.path.isfile(im_path), "The {} isn't a valid file path.".format(im_path)
+                im = cv2.imread(im_path)
+                datas.append(im)
+
+        if self.images is not None:
+            datas = self.images
+        
+        # 返回数据列表
+        return datas
+
+    # 数据预处理函数
+    def preprocess(self):
+        input_datas = []
+
+        # 数据预处理
+        for i, img in enumerate(self.datas):
+            # 格式转换
+            img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+            
+            # 缩放图片
+            h, w = img.shape[:2]
+            if max(h,w)>self.max_size:
+                img = cv2.resize(img, (self.max_size, int(h/w*self.max_size))) if h<w else cv2.resize(img, (int(w/h*self.max_size), self.max_size))
+            elif min(h,w)<self.min_size:
+                img = cv2.resize(img, (self.min_size, int(h/w*self.min_size))) if h>w else cv2.resize(img, (int(w/h*self.min_size), self.min_size))
+
+            # 裁剪图片
+            h, w = img.shape[:2]
+            img = img[:h-(h%32), :w-(w%32), :]
+
+            # 归一化
+            img = img/127.5 - 1.0
+
+            # 新建维度
+            img = np.expand_dims(img, axis=0).astype('float32')
+
+            # 加入输入数据列表
+            input_datas.append(img)
+
+        # 数据按batch_size切分
+        input_datas = np.concatenate(input_datas, 0)
+        split_num = len(self.datas)//self.batch_size+1 if len(self.datas)%self.batch_size!=0 else len(self.datas)//self.batch_size
+        input_datas = np.array_split(input_datas, split_num)   
+
+        # 返回预处理完成的数据
+        return input_datas
+
+    def postprocess(self, outputs, visualization):
+        results = []
+
+        for im_id, output in enumerate(outputs):
+            # 反归一化
+            image = (output.squeeze() + 1.) / 2 * 255
+
+            # 限幅
+            image = np.clip(image, 0, 255).astype(np.uint8)
+
+            # 格式转换
+            image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+
+            # 可视化
+            if visualization:
+                # 检查输出目录
+                check_dir(self.output_dir)
+
+                # 写入输出图片
+                cv2.imwrite(os.path.join(self.output_dir, '%d_%d.jpg' % (im_id, time.time())), image)
+
+            results.append(image)
+
+        # 返回结果
+        return results
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_paprika_98/README.md b/hub_module/modules/image/style_transfer/animegan_v2_paprika_98/README.md
new file mode 100644
index 00000000..1f650fd6
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_paprika_98/README.md
@@ -0,0 +1,127 @@
+## 模型概述
+AnimeGAN V2 图像风格转换模型
+
+模型可将输入的图像转换成Paprika风格
+
+模型权重转换自AnimeGAN V2官方开源项目
+
+模型所使用的权重为Paprika-98.ckpt
+
+模型详情请参考[AnimeGAN V2 开源项目](https://github.com/TachibanaYoshino/AnimeGANv2)
+
+## 模型安装
+
+```shell
+$hub install animegan_v2_paprika_98
+```
+
+
+## API 说明
+
+```python
+def style_transfer(
+    self,
+    images=None,
+    paths=None,
+    batch_size=1,
+    output_dir='output',
+    visualization=False,
+    min_size=32,
+    max_size=1024
+)
+```
+
+风格转换API，将输入的图片转换为漫画风格。
+
+转换效果图如下：
+
+![输入图像](https://ai-studio-static-online.cdn.bcebos.com/bd002c4bb6a7427daf26988770bb18648b7d8d2bfd6746bfb9a429db4867727f)
+![输出图像](https://ai-studio-static-online.cdn.bcebos.com/495436a627ef423ab572536c5f2ba6d0eb99b1ce098947a5ac02af36e7eb85f7)
+
+
+**参数**
+
+* images (list\[numpy.ndarray\]): 图片数据，ndarray.shape 为 \[H, W, C\]，默认为 None；
+* paths (list\[str\]): 图片的路径，默认为 None；
+* batch\_size (int): batch 的大小，默认设为 1；
+* visualization (bool): 是否将识别结果保存为图片文件，默认设为 False；
+* output\_dir (str): 图片的保存路径，默认设为 output；
+* min\_size (int): 输入图片的短边最小尺寸，默认设为 32；
+* max\_size (int): 输入图片的短边最大尺寸，默认设为 1024。
+
+
+**返回**
+
+* res (list\[numpy.ndarray\]): 输出图像数据，ndarray.shape 为 \[H, W, C\]。
+
+
+## 预测代码示例
+
+```python
+import cv2
+import paddlehub as hub
+
+# 模型加载
+# use_gpu：是否使用GPU进行预测
+model = hub.Module('animegan_v2_paprika_98', use_gpu=False)
+
+# 模型预测
+result = model.style_transfer(images=[cv2.imread('/PATH/TO/IMAGE')])
+
+# or
+# result = model.style_transfer(paths=['/PATH/TO/IMAGE'])
+```
+
+## 服务部署
+
+PaddleHub Serving可以部署一个在线图像风格转换服务。
+
+## 第一步：启动PaddleHub Serving
+
+运行启动命令：
+```shell
+$ hub serving start -m animegan_v2_paprika_98
+```
+
+这样就完成了一个图像风格转换的在线服务API的部署，默认端口号为8866。
+
+**NOTE:** 如使用GPU预测，则需要在启动服务之前，请设置CUDA\_VISIBLE\_DEVICES环境变量，否则不用设置。
+
+## 第二步：发送预测请求
+
+配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果
+
+```python
+import requests
+import json
+import cv2
+import base64
+
+
+def cv2_to_base64(image):
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+
+# 发送HTTP请求
+data = {'images':[cv2_to_base64(cv2.imread("/PATH/TO/IMAGE"))]}
+headers = {"Content-type": "application/json"}
+url = "http://127.0.0.1:8866/predict/animegan_v2_paprika_98"
+r = requests.post(url=url, headers=headers, data=json.dumps(data))
+
+# 打印预测结果
+print(r.json()["results"])
+```
+
+
+## 模型相关信息
+
+### 模型代码
+
+https://github.com/TachibanaYoshino/AnimeGANv2
+
+### 依赖
+
+paddlepaddle >= 1.8.0
+
+paddlehub >= 1.8.0
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_paprika_98/model.py b/hub_module/modules/image/style_transfer/animegan_v2_paprika_98/model.py
new file mode 100644
index 00000000..a72cf8a3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_paprika_98/model.py
@@ -0,0 +1,67 @@
+import os
+import numpy as np
+
+from paddle.fluid.core import AnalysisConfig, create_paddle_predictor
+
+__all__ = ['Model']
+
+class Model():
+    # 初始化函数
+    def __init__(self, modelpath, use_gpu):
+        # 加载模型预测器
+        self.predictor = self.load_model(modelpath, use_gpu)
+
+        # 获取模型的输入输出
+        self.input_names = self.predictor.get_input_names()
+        self.output_names = self.predictor.get_output_names()
+        self.input_tensor = self.predictor.get_input_tensor(self.input_names[0])
+        self.output_tensor = self.predictor.get_output_tensor(self.output_names[0])
+
+    # 模型加载函数
+    def load_model(self, modelpath, use_gpu):
+        # 对运行位置进行配置
+        if use_gpu:
+            try:
+                places = os.environ["CUDA_VISIBLE_DEVICES"]
+                places = int(places[0])
+            except Exception as e:
+                print('Error: %s. Please set the environment variables "CUDA_VISIBLE_DEVICES".' % e)
+                use_gpu = False
+
+        # 加载模型参数
+        config = AnalysisConfig(modelpath)
+
+        # 设置参数
+        if use_gpu:   
+            config.enable_use_gpu(100, places)
+        else:
+            config.disable_gpu()
+            config.enable_mkldnn()
+        config.disable_glog_info()
+        config.switch_ir_optim(True)
+        config.enable_memory_optim()
+        config.switch_use_feed_fetch_ops(False)
+        config.switch_specify_input_names(True)
+        
+        # 通过参数加载模型预测器
+        predictor = create_paddle_predictor(config)
+        
+        # 返回预测器
+        return predictor
+
+    # 模型预测函数
+    def predict(self, input_datas):
+        outputs = []
+
+        # 遍历输入数据进行预测
+        for input_data in input_datas:
+            self.input_tensor.copy_from_cpu(input_data)
+            self.predictor.zero_copy_run()
+            output = self.output_tensor.copy_to_cpu()
+            outputs.append(output)
+        
+        # 预测结果合并
+        outputs = np.concatenate(outputs, 0)
+
+        # 返回预测结果
+        return outputs
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_paprika_98/module.py b/hub_module/modules/image/style_transfer/animegan_v2_paprika_98/module.py
new file mode 100644
index 00000000..6daab807
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_paprika_98/module.py
@@ -0,0 +1,72 @@
+import os
+
+from paddlehub import Module
+from paddlehub.module.module import moduleinfo, serving
+
+from animegan_v2_paprika_98.model import Model
+from animegan_v2_paprika_98.processor import base64_to_cv2, cv2_to_base64, Processor
+
+@moduleinfo(
+    name="animegan_v2_paprika_98", # 模型名称
+    type="CV/style_transfer", # 模型类型
+    author="jm12138", # 作者名称
+    author_email="jm12138@qq.com", # 作者邮箱
+    summary="animegan_v2_paprika_98", # 模型介绍
+    version="1.0.0" # 版本号
+)
+class Animegan_V2_Paprika_98(Module):
+    # 初始化函数
+    def _initialize(self, use_gpu=False):
+        # 设置模型路径
+        self.model_path = os.path.join(self.directory, "animegan_v2_paprika_98")
+
+        # 加载模型
+        self.model = Model(self.model_path, use_gpu)     
+    
+    # 关键点检测函数
+    def style_transfer(
+        self,
+        images=None,
+        paths=None,
+        batch_size=1,
+        output_dir='output',
+        visualization=False,
+        min_size=32,
+        max_size=1024
+    ):
+        # 加载数据处理器
+        processor = Processor(
+            images, 
+            paths, 
+            batch_size, 
+            output_dir, 
+            min_size, 
+            max_size
+        )
+
+        # 模型预测
+        outputs = self.model.predict(processor.input_datas)
+
+        # 结果后处理
+        results = processor.postprocess(outputs, visualization)
+
+        # 返回结果
+        return results
+
+    # Hub Serving
+    @serving
+    def serving_method(self, images, **kwargs):
+        # 获取输入数据
+        images_decode = [base64_to_cv2(image) for image in images]
+
+        # 图片风格转换
+        results = self.style_transfer(images_decode, **kwargs)
+
+        # 对输出图片进行编码
+        encodes = []
+        for result in results:
+            encode = cv2_to_base64(result)
+            encodes.append(encode)
+            
+        # 返回结果
+        return encodes
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_paprika_98/processor.py b/hub_module/modules/image/style_transfer/animegan_v2_paprika_98/processor.py
new file mode 100644
index 00000000..777487d3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_paprika_98/processor.py
@@ -0,0 +1,133 @@
+import os
+import cv2 
+import time
+import base64
+import numpy as np
+
+__all__ = ['base64_to_cv2', 'cv2_to_base64', 'Processor']
+
+def check_dir(dir_path):
+    # 目录检查函数
+    if not os.path.exists(dir_path):
+        os.makedirs(dir_path)
+    elif os.path.isfile(dir_path):
+        os.remove(dir_path)
+        os.makedirs(dir_path)
+
+def base64_to_cv2(b64str):
+    # base64转cv2函数
+    data = base64.b64decode(b64str.encode('utf8'))
+    data = np.frombuffer(data, np.uint8)
+    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
+    return data
+
+def cv2_to_base64(image):
+    # cv2转base64函数
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+class Processor():
+    # 初始化函数
+    def __init__(
+        self, 
+        images=None, 
+        paths=None, 
+        batch_size=1, 
+        output_dir='output',
+        min_size=32,
+        max_size=1024
+    ):
+        # 变量设置
+        self.min_size = min_size
+        self.max_size = max_size
+
+        self.images = images
+        self.paths = paths
+        self.batch_size = batch_size
+        self.output_dir = output_dir
+
+        # 获取原始输入数据
+        self.datas = self.load_datas()
+
+        # 对原始输入数据进行预处理
+        self.input_datas = self.preprocess()
+
+    # 读取数据函数
+    def load_datas(self):
+        datas = []
+
+        # 读取数据列表
+        if self.paths is not None:
+            for im_path in self.paths:
+                assert os.path.isfile(im_path), "The {} isn't a valid file path.".format(im_path)
+                im = cv2.imread(im_path)
+                datas.append(im)
+
+        if self.images is not None:
+            datas = self.images
+        
+        # 返回数据列表
+        return datas
+
+    # 数据预处理函数
+    def preprocess(self):
+        input_datas = []
+
+        # 数据预处理
+        for i, img in enumerate(self.datas):
+            # 格式转换
+            img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+            
+            # 缩放图片
+            h, w = img.shape[:2]
+            if max(h,w)>self.max_size:
+                img = cv2.resize(img, (self.max_size, int(h/w*self.max_size))) if h<w else cv2.resize(img, (int(w/h*self.max_size), self.max_size))
+            elif min(h,w)<self.min_size:
+                img = cv2.resize(img, (self.min_size, int(h/w*self.min_size))) if h>w else cv2.resize(img, (int(w/h*self.min_size), self.min_size))
+
+            # 裁剪图片
+            h, w = img.shape[:2]
+            img = img[:h-(h%32), :w-(w%32), :]
+
+            # 归一化
+            img = img/127.5 - 1.0
+
+            # 新建维度
+            img = np.expand_dims(img, axis=0).astype('float32')
+
+            # 加入输入数据列表
+            input_datas.append(img)
+
+        # 数据按batch_size切分
+        input_datas = np.concatenate(input_datas, 0)
+        split_num = len(self.datas)//self.batch_size+1 if len(self.datas)%self.batch_size!=0 else len(self.datas)//self.batch_size
+        input_datas = np.array_split(input_datas, split_num)   
+
+        # 返回预处理完成的数据
+        return input_datas
+
+    def postprocess(self, outputs, visualization):
+        results = []
+
+        for im_id, output in enumerate(outputs):
+            # 反归一化
+            image = (output.squeeze() + 1.) / 2 * 255
+
+            # 限幅
+            image = np.clip(image, 0, 255).astype(np.uint8)
+
+            # 格式转换
+            image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+
+            # 可视化
+            if visualization:
+                # 检查输出目录
+                check_dir(self.output_dir)
+
+                # 写入输出图片
+                cv2.imwrite(os.path.join(self.output_dir, '%d_%d.jpg' % (im_id, time.time())), image)
+
+            results.append(image)
+
+        # 返回结果
+        return results
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_shinkai_33/README.md b/hub_module/modules/image/style_transfer/animegan_v2_shinkai_33/README.md
new file mode 100644
index 00000000..19aaff3a
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_shinkai_33/README.md
@@ -0,0 +1,127 @@
+## 模型概述
+AnimeGAN V2 图像风格转换模型
+
+模型可将输入的图像转换成Shinkai风格
+
+模型权重转换自AnimeGAN V2官方开源项目
+
+模型所使用的权重为Shinkai-33.ckpt
+
+模型详情请参考[AnimeGAN V2 开源项目](https://github.com/TachibanaYoshino/AnimeGANv2)
+
+## 模型安装
+
+```shell
+$hub install animegan_v2_shinkai_33
+```
+
+
+## API 说明
+
+```python
+def style_transfer(
+    self,
+    images=None,
+    paths=None,
+    batch_size=1,
+    output_dir='output',
+    visualization=False,
+    min_size=32,
+    max_size=1024
+)
+```
+
+风格转换API，将输入的图片转换为漫画风格。
+
+转换效果图如下：
+
+![输入图像](https://ai-studio-static-online.cdn.bcebos.com/bd002c4bb6a7427daf26988770bb18648b7d8d2bfd6746bfb9a429db4867727f)
+![输出图像](https://ai-studio-static-online.cdn.bcebos.com/776a84a0d97c452bbbe479592fbb8f5c6fe9c45f3b7e41fd8b7da80bf52ee668)
+
+
+**参数**
+
+* images (list\[numpy.ndarray\]): 图片数据，ndarray.shape 为 \[H, W, C\]，默认为 None；
+* paths (list\[str\]): 图片的路径，默认为 None；
+* batch\_size (int): batch 的大小，默认设为 1；
+* visualization (bool): 是否将识别结果保存为图片文件，默认设为 False；
+* output\_dir (str): 图片的保存路径，默认设为 output；
+* min\_size (int): 输入图片的短边最小尺寸，默认设为 32；
+* max\_size (int): 输入图片的短边最大尺寸，默认设为 1024。
+
+
+**返回**
+
+* res (list\[numpy.ndarray\]): 输出图像数据，ndarray.shape 为 \[H, W, C\]。
+
+
+## 预测代码示例
+
+```python
+import cv2
+import paddlehub as hub
+
+# 模型加载
+# use_gpu：是否使用GPU进行预测
+model = hub.Module('animegan_v2_shinkai_33', use_gpu=False)
+
+# 模型预测
+result = model.style_transfer(images=[cv2.imread('/PATH/TO/IMAGE')])
+
+# or
+# result = model.style_transfer(paths=['/PATH/TO/IMAGE'])
+```
+
+## 服务部署
+
+PaddleHub Serving可以部署一个在线图像风格转换服务。
+
+## 第一步：启动PaddleHub Serving
+
+运行启动命令：
+```shell
+$ hub serving start -m animegan_v2_shinkai_33
+```
+
+这样就完成了一个图像风格转换的在线服务API的部署，默认端口号为8866。
+
+**NOTE:** 如使用GPU预测，则需要在启动服务之前，请设置CUDA\_VISIBLE\_DEVICES环境变量，否则不用设置。
+
+## 第二步：发送预测请求
+
+配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果
+
+```python
+import requests
+import json
+import cv2
+import base64
+
+
+def cv2_to_base64(image):
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+
+# 发送HTTP请求
+data = {'images':[cv2_to_base64(cv2.imread("/PATH/TO/IMAGE"))]}
+headers = {"Content-type": "application/json"}
+url = "http://127.0.0.1:8866/predict/animegan_v2_shinkai_33"
+r = requests.post(url=url, headers=headers, data=json.dumps(data))
+
+# 打印预测结果
+print(r.json()["results"])
+```
+
+
+## 模型相关信息
+
+### 模型代码
+
+https://github.com/TachibanaYoshino/AnimeGANv2
+
+### 依赖
+
+paddlepaddle >= 1.8.0
+
+paddlehub >= 1.8.0
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_shinkai_33/model.py b/hub_module/modules/image/style_transfer/animegan_v2_shinkai_33/model.py
new file mode 100644
index 00000000..a72cf8a3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_shinkai_33/model.py
@@ -0,0 +1,67 @@
+import os
+import numpy as np
+
+from paddle.fluid.core import AnalysisConfig, create_paddle_predictor
+
+__all__ = ['Model']
+
+class Model():
+    # 初始化函数
+    def __init__(self, modelpath, use_gpu):
+        # 加载模型预测器
+        self.predictor = self.load_model(modelpath, use_gpu)
+
+        # 获取模型的输入输出
+        self.input_names = self.predictor.get_input_names()
+        self.output_names = self.predictor.get_output_names()
+        self.input_tensor = self.predictor.get_input_tensor(self.input_names[0])
+        self.output_tensor = self.predictor.get_output_tensor(self.output_names[0])
+
+    # 模型加载函数
+    def load_model(self, modelpath, use_gpu):
+        # 对运行位置进行配置
+        if use_gpu:
+            try:
+                places = os.environ["CUDA_VISIBLE_DEVICES"]
+                places = int(places[0])
+            except Exception as e:
+                print('Error: %s. Please set the environment variables "CUDA_VISIBLE_DEVICES".' % e)
+                use_gpu = False
+
+        # 加载模型参数
+        config = AnalysisConfig(modelpath)
+
+        # 设置参数
+        if use_gpu:   
+            config.enable_use_gpu(100, places)
+        else:
+            config.disable_gpu()
+            config.enable_mkldnn()
+        config.disable_glog_info()
+        config.switch_ir_optim(True)
+        config.enable_memory_optim()
+        config.switch_use_feed_fetch_ops(False)
+        config.switch_specify_input_names(True)
+        
+        # 通过参数加载模型预测器
+        predictor = create_paddle_predictor(config)
+        
+        # 返回预测器
+        return predictor
+
+    # 模型预测函数
+    def predict(self, input_datas):
+        outputs = []
+
+        # 遍历输入数据进行预测
+        for input_data in input_datas:
+            self.input_tensor.copy_from_cpu(input_data)
+            self.predictor.zero_copy_run()
+            output = self.output_tensor.copy_to_cpu()
+            outputs.append(output)
+        
+        # 预测结果合并
+        outputs = np.concatenate(outputs, 0)
+
+        # 返回预测结果
+        return outputs
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_shinkai_33/module.py b/hub_module/modules/image/style_transfer/animegan_v2_shinkai_33/module.py
new file mode 100644
index 00000000..cc0612f2
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_shinkai_33/module.py
@@ -0,0 +1,72 @@
+import os
+
+from paddlehub import Module
+from paddlehub.module.module import moduleinfo, serving
+
+from animegan_v2_shinkai_33.model import Model
+from animegan_v2_shinkai_33.processor import base64_to_cv2, cv2_to_base64, Processor
+
+@moduleinfo(
+    name="animegan_v2_shinkai_33", # 模型名称
+    type="CV/style_transfer", # 模型类型
+    author="jm12138", # 作者名称
+    author_email="jm12138@qq.com", # 作者邮箱
+    summary="animegan_v2_shinkai_33", # 模型介绍
+    version="1.0.0" # 版本号
+)
+class Animegan_V2_Shinkai_33(Module):
+    # 初始化函数
+    def _initialize(self, use_gpu=False):
+        # 设置模型路径
+        self.model_path = os.path.join(self.directory, "animegan_v2_shinkai_33")
+
+        # 加载模型
+        self.model = Model(self.model_path, use_gpu)     
+    
+    # 关键点检测函数
+    def style_transfer(
+        self,
+        images=None,
+        paths=None,
+        batch_size=1,
+        output_dir='output',
+        visualization=False,
+        min_size=32,
+        max_size=1024
+    ):
+        # 加载数据处理器
+        processor = Processor(
+            images, 
+            paths, 
+            batch_size, 
+            output_dir, 
+            min_size, 
+            max_size
+        )
+
+        # 模型预测
+        outputs = self.model.predict(processor.input_datas)
+
+        # 结果后处理
+        results = processor.postprocess(outputs, visualization)
+
+        # 返回结果
+        return results
+
+    # Hub Serving
+    @serving
+    def serving_method(self, images, **kwargs):
+        # 获取输入数据
+        images_decode = [base64_to_cv2(image) for image in images]
+
+        # 图片风格转换
+        results = self.style_transfer(images_decode, **kwargs)
+
+        # 对输出图片进行编码
+        encodes = []
+        for result in results:
+            encode = cv2_to_base64(result)
+            encodes.append(encode)
+            
+        # 返回结果
+        return encodes
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_shinkai_33/processor.py b/hub_module/modules/image/style_transfer/animegan_v2_shinkai_33/processor.py
new file mode 100644
index 00000000..777487d3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_shinkai_33/processor.py
@@ -0,0 +1,133 @@
+import os
+import cv2 
+import time
+import base64
+import numpy as np
+
+__all__ = ['base64_to_cv2', 'cv2_to_base64', 'Processor']
+
+def check_dir(dir_path):
+    # 目录检查函数
+    if not os.path.exists(dir_path):
+        os.makedirs(dir_path)
+    elif os.path.isfile(dir_path):
+        os.remove(dir_path)
+        os.makedirs(dir_path)
+
+def base64_to_cv2(b64str):
+    # base64转cv2函数
+    data = base64.b64decode(b64str.encode('utf8'))
+    data = np.frombuffer(data, np.uint8)
+    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
+    return data
+
+def cv2_to_base64(image):
+    # cv2转base64函数
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+class Processor():
+    # 初始化函数
+    def __init__(
+        self, 
+        images=None, 
+        paths=None, 
+        batch_size=1, 
+        output_dir='output',
+        min_size=32,
+        max_size=1024
+    ):
+        # 变量设置
+        self.min_size = min_size
+        self.max_size = max_size
+
+        self.images = images
+        self.paths = paths
+        self.batch_size = batch_size
+        self.output_dir = output_dir
+
+        # 获取原始输入数据
+        self.datas = self.load_datas()
+
+        # 对原始输入数据进行预处理
+        self.input_datas = self.preprocess()
+
+    # 读取数据函数
+    def load_datas(self):
+        datas = []
+
+        # 读取数据列表
+        if self.paths is not None:
+            for im_path in self.paths:
+                assert os.path.isfile(im_path), "The {} isn't a valid file path.".format(im_path)
+                im = cv2.imread(im_path)
+                datas.append(im)
+
+        if self.images is not None:
+            datas = self.images
+        
+        # 返回数据列表
+        return datas
+
+    # 数据预处理函数
+    def preprocess(self):
+        input_datas = []
+
+        # 数据预处理
+        for i, img in enumerate(self.datas):
+            # 格式转换
+            img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+            
+            # 缩放图片
+            h, w = img.shape[:2]
+            if max(h,w)>self.max_size:
+                img = cv2.resize(img, (self.max_size, int(h/w*self.max_size))) if h<w else cv2.resize(img, (int(w/h*self.max_size), self.max_size))
+            elif min(h,w)<self.min_size:
+                img = cv2.resize(img, (self.min_size, int(h/w*self.min_size))) if h>w else cv2.resize(img, (int(w/h*self.min_size), self.min_size))
+
+            # 裁剪图片
+            h, w = img.shape[:2]
+            img = img[:h-(h%32), :w-(w%32), :]
+
+            # 归一化
+            img = img/127.5 - 1.0
+
+            # 新建维度
+            img = np.expand_dims(img, axis=0).astype('float32')
+
+            # 加入输入数据列表
+            input_datas.append(img)
+
+        # 数据按batch_size切分
+        input_datas = np.concatenate(input_datas, 0)
+        split_num = len(self.datas)//self.batch_size+1 if len(self.datas)%self.batch_size!=0 else len(self.datas)//self.batch_size
+        input_datas = np.array_split(input_datas, split_num)   
+
+        # 返回预处理完成的数据
+        return input_datas
+
+    def postprocess(self, outputs, visualization):
+        results = []
+
+        for im_id, output in enumerate(outputs):
+            # 反归一化
+            image = (output.squeeze() + 1.) / 2 * 255
+
+            # 限幅
+            image = np.clip(image, 0, 255).astype(np.uint8)
+
+            # 格式转换
+            image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+
+            # 可视化
+            if visualization:
+                # 检查输出目录
+                check_dir(self.output_dir)
+
+                # 写入输出图片
+                cv2.imwrite(os.path.join(self.output_dir, '%d_%d.jpg' % (im_id, time.time())), image)
+
+            results.append(image)
+
+        # 返回结果
+        return results
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_shinkai_53/README.md b/hub_module/modules/image/style_transfer/animegan_v2_shinkai_53/README.md
new file mode 100644
index 00000000..44dfdcf7
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_shinkai_53/README.md
@@ -0,0 +1,127 @@
+## 模型概述
+AnimeGAN V2 图像风格转换模型
+
+模型可将输入的图像转换成Shinkai风格
+
+模型权重转换自AnimeGAN V2官方开源项目
+
+模型所使用的权重为Shinkai-53.ckpt
+
+模型详情请参考[AnimeGAN V2 开源项目](https://github.com/TachibanaYoshino/AnimeGANv2)
+
+## 模型安装
+
+```shell
+$hub install animegan_v2_shinkai_53
+```
+
+
+## API 说明
+
+```python
+def style_transfer(
+    self,
+    images=None,
+    paths=None,
+    batch_size=1,
+    output_dir='output',
+    visualization=False,
+    min_size=32,
+    max_size=1024
+)
+```
+
+风格转换API，将输入的图片转换为漫画风格。
+
+转换效果图如下：
+
+![输入图像](https://ai-studio-static-online.cdn.bcebos.com/bd002c4bb6a7427daf26988770bb18648b7d8d2bfd6746bfb9a429db4867727f)
+![输出图像](https://ai-studio-static-online.cdn.bcebos.com/fa4ba157e73c48658c4c9c6b8b92f5c99231d1d19556472788b1e5dd58d5d6cc)
+
+
+**参数**
+
+* images (list\[numpy.ndarray\]): 图片数据，ndarray.shape 为 \[H, W, C\]，默认为 None；
+* paths (list\[str\]): 图片的路径，默认为 None；
+* batch\_size (int): batch 的大小，默认设为 1；
+* visualization (bool): 是否将识别结果保存为图片文件，默认设为 False；
+* output\_dir (str): 图片的保存路径，默认设为 output；
+* min\_size (int): 输入图片的短边最小尺寸，默认设为 32；
+* max\_size (int): 输入图片的短边最大尺寸，默认设为 1024。
+
+
+**返回**
+
+* res (list\[numpy.ndarray\]): 输出图像数据，ndarray.shape 为 \[H, W, C\]。
+
+
+## 预测代码示例
+
+```python
+import cv2
+import paddlehub as hub
+
+# 模型加载
+# use_gpu：是否使用GPU进行预测
+model = hub.Module('animegan_v2_shinkai_53', use_gpu=False)
+
+# 模型预测
+result = model.style_transfer(images=[cv2.imread('/PATH/TO/IMAGE')])
+
+# or
+# result = model.style_transfer(paths=['/PATH/TO/IMAGE'])
+```
+
+## 服务部署
+
+PaddleHub Serving可以部署一个在线图像风格转换服务。
+
+## 第一步：启动PaddleHub Serving
+
+运行启动命令：
+```shell
+$ hub serving start -m animegan_v2_shinkai_53
+```
+
+这样就完成了一个图像风格转换的在线服务API的部署，默认端口号为8866。
+
+**NOTE:** 如使用GPU预测，则需要在启动服务之前，请设置CUDA\_VISIBLE\_DEVICES环境变量，否则不用设置。
+
+## 第二步：发送预测请求
+
+配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果
+
+```python
+import requests
+import json
+import cv2
+import base64
+
+
+def cv2_to_base64(image):
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+
+# 发送HTTP请求
+data = {'images':[cv2_to_base64(cv2.imread("/PATH/TO/IMAGE"))]}
+headers = {"Content-type": "application/json"}
+url = "http://127.0.0.1:8866/predict/animegan_v2_shinkai_53"
+r = requests.post(url=url, headers=headers, data=json.dumps(data))
+
+# 打印预测结果
+print(r.json()["results"])
+```
+
+
+## 模型相关信息
+
+### 模型代码
+
+https://github.com/TachibanaYoshino/AnimeGANv2
+
+### 依赖
+
+paddlepaddle >= 1.8.0
+
+paddlehub >= 1.8.0
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_shinkai_53/model.py b/hub_module/modules/image/style_transfer/animegan_v2_shinkai_53/model.py
new file mode 100644
index 00000000..a72cf8a3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_shinkai_53/model.py
@@ -0,0 +1,67 @@
+import os
+import numpy as np
+
+from paddle.fluid.core import AnalysisConfig, create_paddle_predictor
+
+__all__ = ['Model']
+
+class Model():
+    # 初始化函数
+    def __init__(self, modelpath, use_gpu):
+        # 加载模型预测器
+        self.predictor = self.load_model(modelpath, use_gpu)
+
+        # 获取模型的输入输出
+        self.input_names = self.predictor.get_input_names()
+        self.output_names = self.predictor.get_output_names()
+        self.input_tensor = self.predictor.get_input_tensor(self.input_names[0])
+        self.output_tensor = self.predictor.get_output_tensor(self.output_names[0])
+
+    # 模型加载函数
+    def load_model(self, modelpath, use_gpu):
+        # 对运行位置进行配置
+        if use_gpu:
+            try:
+                places = os.environ["CUDA_VISIBLE_DEVICES"]
+                places = int(places[0])
+            except Exception as e:
+                print('Error: %s. Please set the environment variables "CUDA_VISIBLE_DEVICES".' % e)
+                use_gpu = False
+
+        # 加载模型参数
+        config = AnalysisConfig(modelpath)
+
+        # 设置参数
+        if use_gpu:   
+            config.enable_use_gpu(100, places)
+        else:
+            config.disable_gpu()
+            config.enable_mkldnn()
+        config.disable_glog_info()
+        config.switch_ir_optim(True)
+        config.enable_memory_optim()
+        config.switch_use_feed_fetch_ops(False)
+        config.switch_specify_input_names(True)
+        
+        # 通过参数加载模型预测器
+        predictor = create_paddle_predictor(config)
+        
+        # 返回预测器
+        return predictor
+
+    # 模型预测函数
+    def predict(self, input_datas):
+        outputs = []
+
+        # 遍历输入数据进行预测
+        for input_data in input_datas:
+            self.input_tensor.copy_from_cpu(input_data)
+            self.predictor.zero_copy_run()
+            output = self.output_tensor.copy_to_cpu()
+            outputs.append(output)
+        
+        # 预测结果合并
+        outputs = np.concatenate(outputs, 0)
+
+        # 返回预测结果
+        return outputs
\ No newline at end of file
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_shinkai_53/module.py b/hub_module/modules/image/style_transfer/animegan_v2_shinkai_53/module.py
new file mode 100644
index 00000000..d733092d
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_shinkai_53/module.py
@@ -0,0 +1,72 @@
+import os
+
+from paddlehub import Module
+from paddlehub.module.module import moduleinfo, serving
+
+from animegan_v2_shinkai_53.model import Model
+from animegan_v2_shinkai_53.processor import base64_to_cv2, cv2_to_base64, Processor
+
+@moduleinfo(
+    name="animegan_v2_shinkai_53", # 模型名称
+    type="CV/style_transfer", # 模型类型
+    author="jm12138", # 作者名称
+    author_email="jm12138@qq.com", # 作者邮箱
+    summary="animegan_v2_shinkai_53", # 模型介绍
+    version="1.0.0" # 版本号
+)
+class Animegan_V2_Shinkai_53(Module):
+    # 初始化函数
+    def _initialize(self, use_gpu=False):
+        # 设置模型路径
+        self.model_path = os.path.join(self.directory, "animegan_v2_shinkai_53")
+
+        # 加载模型
+        self.model = Model(self.model_path, use_gpu)     
+    
+    # 关键点检测函数
+    def style_transfer(
+        self,
+        images=None,
+        paths=None,
+        batch_size=1,
+        output_dir='output',
+        visualization=False,
+        min_size=32,
+        max_size=1024
+    ):
+        # 加载数据处理器
+        processor = Processor(
+            images, 
+            paths, 
+            batch_size, 
+            output_dir, 
+            min_size, 
+            max_size
+        )
+
+        # 模型预测
+        outputs = self.model.predict(processor.input_datas)
+
+        # 结果后处理
+        results = processor.postprocess(outputs, visualization)
+
+        # 返回结果
+        return results
+
+    # Hub Serving
+    @serving
+    def serving_method(self, images, **kwargs):
+        # 获取输入数据
+        images_decode = [base64_to_cv2(image) for image in images]
+
+        # 图片风格转换
+        results = self.style_transfer(images_decode, **kwargs)
+
+        # 对输出图片进行编码
+        encodes = []
+        for result in results:
+            encode = cv2_to_base64(result)
+            encodes.append(encode)
+            
+        # 返回结果
+        return encodes
diff --git a/hub_module/modules/image/style_transfer/animegan_v2_shinkai_53/processor.py b/hub_module/modules/image/style_transfer/animegan_v2_shinkai_53/processor.py
new file mode 100644
index 00000000..777487d3
--- /dev/null
+++ b/hub_module/modules/image/style_transfer/animegan_v2_shinkai_53/processor.py
@@ -0,0 +1,133 @@
+import os
+import cv2 
+import time
+import base64
+import numpy as np
+
+__all__ = ['base64_to_cv2', 'cv2_to_base64', 'Processor']
+
+def check_dir(dir_path):
+    # 目录检查函数
+    if not os.path.exists(dir_path):
+        os.makedirs(dir_path)
+    elif os.path.isfile(dir_path):
+        os.remove(dir_path)
+        os.makedirs(dir_path)
+
+def base64_to_cv2(b64str):
+    # base64转cv2函数
+    data = base64.b64decode(b64str.encode('utf8'))
+    data = np.frombuffer(data, np.uint8)
+    data = cv2.imdecode(data, cv2.IMREAD_COLOR)
+    return data
+
+def cv2_to_base64(image):
+    # cv2转base64函数
+    data = cv2.imencode('.jpg', image)[1]
+    return base64.b64encode(data.tostring()).decode('utf8')
+
+class Processor():
+    # 初始化函数
+    def __init__(
+        self, 
+        images=None, 
+        paths=None, 
+        batch_size=1, 
+        output_dir='output',
+        min_size=32,
+        max_size=1024
+    ):
+        # 变量设置
+        self.min_size = min_size
+        self.max_size = max_size
+
+        self.images = images
+        self.paths = paths
+        self.batch_size = batch_size
+        self.output_dir = output_dir
+
+        # 获取原始输入数据
+        self.datas = self.load_datas()
+
+        # 对原始输入数据进行预处理
+        self.input_datas = self.preprocess()
+
+    # 读取数据函数
+    def load_datas(self):
+        datas = []
+
+        # 读取数据列表
+        if self.paths is not None:
+            for im_path in self.paths:
+                assert os.path.isfile(im_path), "The {} isn't a valid file path.".format(im_path)
+                im = cv2.imread(im_path)
+                datas.append(im)
+
+        if self.images is not None:
+            datas = self.images
+        
+        # 返回数据列表
+        return datas
+
+    # 数据预处理函数
+    def preprocess(self):
+        input_datas = []
+
+        # 数据预处理
+        for i, img in enumerate(self.datas):
+            # 格式转换
+            img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+            
+            # 缩放图片
+            h, w = img.shape[:2]
+            if max(h,w)>self.max_size:
+                img = cv2.resize(img, (self.max_size, int(h/w*self.max_size))) if h<w else cv2.resize(img, (int(w/h*self.max_size), self.max_size))
+            elif min(h,w)<self.min_size:
+                img = cv2.resize(img, (self.min_size, int(h/w*self.min_size))) if h>w else cv2.resize(img, (int(w/h*self.min_size), self.min_size))
+
+            # 裁剪图片
+            h, w = img.shape[:2]
+            img = img[:h-(h%32), :w-(w%32), :]
+
+            # 归一化
+            img = img/127.5 - 1.0
+
+            # 新建维度
+            img = np.expand_dims(img, axis=0).astype('float32')
+
+            # 加入输入数据列表
+            input_datas.append(img)
+
+        # 数据按batch_size切分
+        input_datas = np.concatenate(input_datas, 0)
+        split_num = len(self.datas)//self.batch_size+1 if len(self.datas)%self.batch_size!=0 else len(self.datas)//self.batch_size
+        input_datas = np.array_split(input_datas, split_num)   
+
+        # 返回预处理完成的数据
+        return input_datas
+
+    def postprocess(self, outputs, visualization):
+        results = []
+
+        for im_id, output in enumerate(outputs):
+            # 反归一化
+            image = (output.squeeze() + 1.) / 2 * 255
+
+            # 限幅
+            image = np.clip(image, 0, 255).astype(np.uint8)
+
+            # 格式转换
+            image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+
+            # 可视化
+            if visualization:
+                # 检查输出目录
+                check_dir(self.output_dir)
+
+                # 写入输出图片
+                cv2.imwrite(os.path.join(self.output_dir, '%d_%d.jpg' % (im_id, time.time())), image)
+
+            results.append(image)
+
+        # 返回结果
+        return results
\ No newline at end of file
-- 
GitLab