diff --git a/paddle2.0_docs/image_segmentation/pets_image_segmentation_U_Net_like.ipynb b/paddle2.0_docs/image_segmentation/pets_image_segmentation_U_Net_like.ipynb
index d759e0336cf1a83123e4abfe197aa3fd9e3b82a4..febf0727af89087b63dcfe20c46f8b0daca94adf 100644
--- a/paddle2.0_docs/image_segmentation/pets_image_segmentation_U_Net_like.ipynb
+++ b/paddle2.0_docs/image_segmentation/pets_image_segmentation_U_Net_like.ipynb
@@ -9,7 +9,7 @@
    "source": [
     "# 基于U型语义分割模型实现的宠物图像分割\n",
     "\n",
-    "NOTE: 本示例教程依然在开发中，目前是基于2.0alpha版本的Paddle，未来会迁移到2.0beta版本。"
+    "本示例教程当前是基于2.0-beta版本Paddle做的案例实现，未来会随着2.0的系列版本发布进行升级。"
    ]
   },
   {
@@ -29,7 +29,7 @@
    "source": [
     "## 2.环境设置\n",
     "\n",
-    "本示例基于飞桨开源框架2.0版本。"
+    "导入一些比较基础常用的模块，确认自己的飞桨版本。"
    ]
   },
   {
@@ -40,7 +40,7 @@
     {
      "data": {
       "text/plain": [
-       "'2.0.0-alpha0'"
+       "'0.0.0'"
       ]
      },
      "execution_count": 2,
@@ -50,9 +50,13 @@
    ],
    "source": [
     "import os\n",
-    "import paddle\n",
+    "import io\n",
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
+    "from PIL import Image as PilImage\n",
+    "\n",
+    "import paddle\n",
+    "from paddle.nn import functional as F\n",
     "\n",
     "paddle.__version__"
    ]
@@ -90,7 +94,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 2,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -106,12 +110,12 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "% Total    % Received % Xferd  Average Speed   Time    Time     Time  Current\n",
+      "  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current\n",
       "                                 Dload  Upload   Total   Spent    Left  Speed\n",
-      "100  755M  100  755M    0     0  1148k      0  0:11:13  0:11:13 --:--:--  780k\n",
+      "100  755M  100  755M    0     0  2428k      0  0:05:18  0:05:18 --:--:-- 5592k  0  2071k      0  0:06:13  0:00:23  0:05:50 2304k    0     0  2239k      0  0:05:45  0:00:53  0:04:52 3108k0  2607k      0  0:04:56  0:01:05  0:03:51 4402k 0  0:04:33  0:01:15  0:03:18 4383k29  220M    0     0  2746k      0  0:04:41  0:01:22  0:03:19 1733k1:28  0:03:22 1395k476k      0  0:05:12  0:01:37  0:03:35 1507k 2320k      0  0:05:33  0:01:55  0:03:38 1297k2323k      0  0:05:32  0:01:58  0:03:34 2045k17  0:02:10  0:03:07 4157k  0  0:05:24  0:02:35  0:02:49 1542k 2381k      0  0:05:24  0:02:37  0:02:47 2077k   0  0:05:34  0:02:55  0:02:39 2520k5:34  0:02:56  0:02:38 2462k    0     0  2368k      0  0:05:26  0:03:24  0:02:02 2582k2444k      0  0:05:16  0:03:41  0:01:35 2174k:04:09  0:01:23 1638k13k      0  0:05:34  0:04:25  0:01:09 2396k2 3048k5M    0     0  2364k      0  0:05:27  0:04:56  0:00:31 2492k0  0:05:27  0:05:02  0:00:25 2114k\n",
       "  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current\n",
       "                                 Dload  Upload   Total   Spent    Left  Speed\n",
-      "100 18.2M  100 18.2M    0     0   893k      0  0:00:20  0:00:20 --:--:-- 1847k\n"
+      "100 18.2M  100 18.2M    0     0  1332k      0  0:00:14  0:00:14 --:--:-- 2580k90k      0  0:00:38  0:00:06  0:00:32  586k      0  0:00:20  0:00:11  0:00:09 1420k    0  1207k      0  0:00:15  0:00:13  0:00:02 2167k\n"
      ]
     }
    ],
@@ -129,9 +133,21 @@
     "id": "L5cP2CBz-Mra"
    },
    "source": [
-    "### 3.2 数据集整理\n",
+    "### 3.2 数据集概览\n",
+    "\n",
+    "首先我们先看看下载到磁盘上的文件结构是什么样，来了解一下我们的数据集。\n",
+    "\n",
+    "1. 首先看一下images.tar.gz这个压缩包，该文件解压后得到一个images目录，这个目录比较简单，里面直接放的是用类名和序号命名好的图片文件，每个图片是对应的宠物照片。\n",
+    "\n",
+    "```bash\n",
+    ".\n",
+    "├── samoyed_7.jpg\n",
+    "├── ......\n",
+    "└── samoyed_81.jpg\n",
+    "```\n",
+    "\n",
+    "2. 然后我们在看下annotations.tar.gz，文件解压后的目录里面包含以下内容，目录中的README文件将每个目录和文件做了比较详细的介绍，我们可以通过README来查看每个目录文件的说明。\n",
     "\n",
-    "首先我们先看看下载到磁盘上的文件结构是什么样的。首先看images.tar.gz，该文件解压后得到一个images目录，这个目录比较简单，里面直接放的是用类名和序号命名好的图片文件。然后我们在看下annotations.tar.gz文件解压后的目录，里面包含以下内容，我们可以通过README文件查看每个目录的说明介绍。\n",
     "```bash\n",
     ".\n",
     "├── README\n",
@@ -139,13 +155,20 @@
     "├── test.txt\n",
     "├── trainval.txt\n",
     "├── trimaps\n",
+    "│    ├── Abyssinian_1.png\n",
+    "│    ├── Abyssinian_10.png\n",
+    "│    ├── ......\n",
+    "│    └── yorkshire_terrier_99.png\n",
     "└── xmls\n",
+    "      ├── Abyssinian_1.xml\n",
+    "      ├── Abyssinian_10.xml\n",
+    "      ├── ......\n",
+    "      └── yorkshire_terrier_190.xml\n",
     "```\n",
-    "这次我们主要使用到images目录和annotations/trimaps目录，即原图文件和分割图像文件。\n",
     "\n",
-    "由于所有文件都是散落在文件夹中，在训练时我们需要使用的是数据集和标签对应的数据关系，所以我们第一步是对原始的数据集进行整理，得到数据集和标签两个数组，分别一一对应。这样可以在使用的时候能够很方便的找到原始数据和标签的对应关系，否则对于原有的文件夹图片数据无法直接应用。\n",
+    "本次我们主要使用到images和annotations/trimaps两个目录，即原图和三元图像文件，前者作为训练的输入数据，后者是对应的标签数据。\n",
     "\n",
-    "在这里是用了一个非常简单的方法，按照文件名称进行排序。因为刚好数据和标签的文件名是按照这个逻辑制作的，名字都一样，只有扩展名不一样。"
+    "我们来看看这个数据集给我们提供了多少个训练样本。"
    ]
   },
   {
@@ -166,136 +189,39 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Number of samples: 7390\n",
-      "images/Abyssinian_1.jpg | annotations/trimaps/Abyssinian_1.png\n",
-      "images/Abyssinian_10.jpg | annotations/trimaps/Abyssinian_10.png\n",
-      "images/Abyssinian_100.jpg | annotations/trimaps/Abyssinian_100.png\n",
-      "images/Abyssinian_101.jpg | annotations/trimaps/Abyssinian_101.png\n",
-      "images/Abyssinian_102.jpg | annotations/trimaps/Abyssinian_102.png\n",
-      "images/Abyssinian_103.jpg | annotations/trimaps/Abyssinian_103.png\n",
-      "images/Abyssinian_104.jpg | annotations/trimaps/Abyssinian_104.png\n",
-      "images/Abyssinian_105.jpg | annotations/trimaps/Abyssinian_105.png\n",
-      "images/Abyssinian_106.jpg | annotations/trimaps/Abyssinian_106.png\n",
-      "images/Abyssinian_107.jpg | annotations/trimaps/Abyssinian_107.png\n"
+      "用于训练的图片样本数量: 7390\n"
      ]
     }
    ],
    "source": [
-    "input_dir = \"images/\"\n",
-    "target_dir = \"annotations/trimaps/\"\n",
-    "img_size = (160, 160)\n",
-    "num_classes = 4\n",
-    "batch_size = 32\n",
-    "\n",
-    "input_img_paths = sorted(\n",
-    "    [\n",
-    "        os.path.join(input_dir, fname)\n",
-    "        for fname in os.listdir(input_dir)\n",
-    "        if fname.endswith(\".jpg\")\n",
-    "    ]\n",
-    ")\n",
-    "target_img_paths = sorted(\n",
-    "    [\n",
-    "        os.path.join(target_dir, fname)\n",
-    "        for fname in os.listdir(target_dir)\n",
-    "        if fname.endswith(\".png\") and not fname.startswith(\".\")\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "print(\"Number of samples:\", len(input_img_paths))\n",
-    "\n",
-    "for input_path, target_path in zip(input_img_paths[:10], target_img_paths[:10]):\n",
-    "    print(input_path, \"|\", target_path)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "colab_type": "text",
-    "id": "rIcNAXLa--bK"
-   },
-   "source": [
-    "### 3.3 数据集抽样展示\n",
-    "\n",
-    "数据关系整理好之后我们来抽样检查下是否符合我们的预期。我们取出想要抽样查看的图片文件路径，然后通过matplotlib进行图像展示，这里要注意的是对于分割的标签文件因为是1通道的灰度图片，需要在使用imshow接口时注意下传参cmap='gray'。"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/",
-     "height": 479
-    },
-    "colab_type": "code",
-    "id": "ZB2qBHR7eSc7",
-    "outputId": "833dd067-64e7-44ed-e628-f7045d1be6e8"
-   },
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 432x288 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 432x288 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "from PIL import Image as PilImage\n",
+    "train_images_path = \"images/\"\n",
+    "label_images_path = \"annotations/trimaps/\"\n",
     "\n",
-    "def show_image(image, cmap=None):\n",
-    "    plt.figure()\n",
-    "\n",
-    "    if cmap is None:\n",
-    "        plt.imshow(image)\n",
-    "    else:\n",
-    "        plt.imshow(image, cmap=cmap)\n",
-    "        \n",
-    "    plt.axis('off')\n",
-    "    plt.show()\n",
-    "\n",
-    "\n",
-    "show_image(PilImage.open(input_img_paths[9]))\n",
-    "show_image(PilImage.open(target_img_paths[9]), 'gray')"
+    "print(\"用于训练的图片样本数量:\", len([os.path.join(train_images_path, image_name) \n",
+    "          for image_name in os.listdir(train_images_path) \n",
+    "          if image_name.endswith('.jpg')]))"
    ]
   },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "colab_type": "text",
-    "id": "QtGkmGoJEBIw"
-   },
+   "metadata": {},
    "source": [
-    "### 3.4 数据集Class定义\n",
+    "### 3.3 数据集类定义\n",
     "\n",
-    "PaddlePaddle数据集方案是使用Dataset（数据集定义）+DataLoader（数据集加载），那么在整理好数据集和标签对应关系后，我们继续准备框架训练使用的数据集Class，继承paddle.io.Dataset进行数据集子类定义。\n",
+    "飞桨（PaddlePaddle）数据集加载方案是统一使用Dataset（数据集定义） + DataLoader（多进程数据集加载）。\n",
     "\n",
-    "继承父类实现以下两个方法：\n",
+    "首先我们先进行数据集的定义，数据集定义主要是实现一个新的Dataset类，继承父类paddle.io.Dataset，并实现父类中以下两个抽象方法，`__getitem__`和`__len__`：\n",
     "\n",
     "```python\n",
+    "class MyDataset(Dataset):\n",
+    "    def __init__(self):\n",
+    "        ...\n",
+    "        \n",
     "    # 每次迭代时返回数据和对应的标签\n",
     "    def __getitem__(self, idx):\n",
     "        return x, y\n",
     "\n",
-    "    # 返回整个数据集的数目\n",
+    "    # 返回整个数据集的总数\n",
     "    def __len__(self):\n",
     "        return count(samples)\n",
     "```\n",
@@ -309,48 +235,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "colab": {},
-    "colab_type": "code",
-    "id": "oOzLKg5PeSc-"
-   },
+   "execution_count": 4,
+   "metadata": {},
    "outputs": [],
    "source": [
-    "import paddle\n",
-    "import numpy as np\n",
-    "import io\n",
+    "import random\n",
     "\n",
-    "from paddle.incubate import hapi\n",
     "from paddle.io import Dataset\n",
-    "from paddle.incubate.hapi.vision.transforms import transforms\n",
-    "\n",
-    "\n",
-    "def load_img(path, image_size=None, color_mode='rgb'):\n",
-    "    \"\"\"\n",
-    "    统一的图像处理接口封装，用于规整图像大小和通道\n",
-    "    \"\"\"\n",
-    "    with open(path, 'rb') as f:\n",
-    "        img = PilImage.open(io.BytesIO(f.read()))\n",
-    "        if color_mode == 'grayscale':\n",
-    "            # if image is not already an 8-bit, 16-bit or 32-bit grayscale image\n",
-    "            # convert it to an 8-bit grayscale image.\n",
-    "            if img.mode not in ('L', 'I;16', 'I'):\n",
-    "                img = img.convert('L')\n",
-    "        elif color_mode == 'rgba':\n",
-    "            if img.mode != 'RGBA':\n",
-    "                img = img.convert('RGBA')\n",
-    "        elif color_mode == 'rgb':\n",
-    "            if img.mode != 'RGB':\n",
-    "                img = img.convert('RGB')\n",
-    "        else:\n",
-    "            raise ValueError('color_mode must be \"grayscale\", \"rgb\", or \"rgba\"')\n",
-    "\n",
-    "        if image_size is not None:\n",
-    "            if img.size != image_size:\n",
-    "                img = img.resize(image_size, PilImage.NEAREST)\n",
-    "\n",
-    "        return img\n",
+    "from paddle.vision.transforms import transforms\n",
     "\n",
     "\n",
     "class ImgTranspose(object):\n",
@@ -367,18 +259,88 @@
     "            \n",
     "        return img.transpose(self.format)\n",
     "\n",
-    "class PetDataSet(Dataset):\n",
+    "class PetDataset(Dataset):\n",
     "    \"\"\"\n",
     "    数据集定义\n",
     "    \"\"\"\n",
-    "    def __init__(self, image_size, input_img_paths, target_img_paths):\n",
-    "        self.image_size = image_size\n",
-    "        self.input_img_paths = input_img_paths\n",
-    "        self.target_img_paths = target_img_paths\n",
+    "    def __init__(self, image_path, label_path, mode='train'):\n",
+    "        \"\"\"\n",
+    "        构造函数\n",
+    "        \"\"\"\n",
+    "        self.image_size = (160, 160)\n",
+    "        self.image_path = image_path\n",
+    "        self.label_path = label_path\n",
+    "        self.mode = mode.lower()\n",
+    "        self.eval_image_num = 1000\n",
+    "        \n",
+    "        assert self.mode in ['train', 'test'], \\\n",
+    "            \"mode should be 'train' or 'test', but got {}\".format(self.mode)\n",
+    "        \n",
+    "        self._parse_dataset()\n",
     "        \n",
     "        self.transforms = transforms.Compose([\n",
     "            ImgTranspose((2, 0, 1))\n",
     "        ])\n",
+    "        \n",
+    "    def _sort_images(self, image_dir, image_type):\n",
+    "        \"\"\"\n",
+    "        对文件夹内的图像进行按照文件名排序\n",
+    "        \"\"\"\n",
+    "        files = []\n",
+    "\n",
+    "        for image_name in os.listdir(image_dir):\n",
+    "            if image_name.endswith('.{}'.format(image_type)) \\\n",
+    "                    and not image_name.startswith('.'):\n",
+    "                files.append(os.path.join(image_dir, image_name))\n",
+    "\n",
+    "        return sorted(files)\n",
+    "        \n",
+    "    def _parse_dataset(self):\n",
+    "        \"\"\"\n",
+    "        由于所有文件都是散落在文件夹中，在训练时我们需要使用的是数据集和标签对应的数据关系，\n",
+    "        所以我们第一步是对原始的数据集进行整理，得到数据集和标签两个数组，分别一一对应。\n",
+    "        这样可以在使用的时候能够很方便的找到原始数据和标签的对应关系，否则对于原有的文件夹图片数据无法直接应用。\n",
+    "        在这里是用了一个非常简单的方法，按照文件名称进行排序。\n",
+    "        因为刚好数据和标签的文件名是按照这个逻辑制作的，名字都一样，只有扩展名不一样。\n",
+    "        \"\"\"\n",
+    "        temp_train_images = self._sort_images(self.image_path, 'jpg')\n",
+    "        temp_label_images = self._sort_images(self.label_path, 'png')\n",
+    "\n",
+    "        random.Random(1337).shuffle(temp_train_images)\n",
+    "        random.Random(1337).shuffle(temp_label_images)\n",
+    "        \n",
+    "        if self.mode == 'train':\n",
+    "            self.train_images = temp_train_images[:-self.eval_image_num]\n",
+    "            self.label_images = temp_label_images[:-self.eval_image_num]\n",
+    "        else:\n",
+    "            self.train_images = temp_train_images[-self.eval_image_num:]\n",
+    "            self.label_images = temp_label_images[-self.eval_image_num:]\n",
+    "    \n",
+    "    def _load_img(self, path, color_mode='rgb'):\n",
+    "        \"\"\"\n",
+    "        统一的图像处理接口封装，用于规整图像大小和通道\n",
+    "        \"\"\"\n",
+    "        with open(path, 'rb') as f:\n",
+    "            img = PilImage.open(io.BytesIO(f.read()))\n",
+    "            if color_mode == 'grayscale':\n",
+    "                # if image is not already an 8-bit, 16-bit or 32-bit grayscale image\n",
+    "                # convert it to an 8-bit grayscale image.\n",
+    "                if img.mode not in ('L', 'I;16', 'I'):\n",
+    "                    img = img.convert('L')\n",
+    "            elif color_mode == 'rgba':\n",
+    "                if img.mode != 'RGBA':\n",
+    "                    img = img.convert('RGBA')\n",
+    "            elif color_mode == 'rgb':\n",
+    "                if img.mode != 'RGB':\n",
+    "                    img = img.convert('RGB')\n",
+    "            else:\n",
+    "                raise ValueError('color_mode must be \"grayscale\", \"rgb\", or \"rgba\"')\n",
+    "\n",
+    "            if self.image_size is not None:\n",
+    "                if img.size != self.image_size:\n",
+    "                    img = img.resize(self.image_size, PilImage.NEAREST)\n",
+    "\n",
+    "            return img\n",
     "\n",
     "    def __getitem__(self, idx):\n",
     "        \"\"\"\n",
@@ -387,25 +349,16 @@
     "        # 花了比较多的时间在数据处理这里，需要处理成模型能适配的格式，踩了一些坑（比如有不是RGB格式的）\n",
     "        # 有图片会出现通道数和期望不符的情况，需要进行相关考虑\n",
     "\n",
-    "        # 图片的路径信息\n",
-    "        input_img_path = self.input_img_paths[idx]\n",
-    "\n",
-    "        # 用PIL的Image来读取图像文件，并经过numpy转换为数组\n",
-    "        # img_x = Image.open(input_img_path)\n",
-    "        img_x = load_img(input_img_path, self.image_size)\n",
-    "        x = np.array(img_x, dtype='float32')\n",
+    "        # 加载原始图像\n",
+    "        train_image = self._load_img(self.train_images[idx])\n",
+    "        x = np.array(train_image, dtype='float32')\n",
     "\n",
     "        # 对图像进行预处理，统一大小，转换维度格式（HWC => CHW）\n",
     "        x = self.transforms(x)\n",
-    "        # print(input_img_path)\n",
-    "        # print(x.shape)\n",
     "        \n",
-    "        # Label图像路径\n",
-    "        target_img_path = self.target_img_paths[idx]  \n",
-    "\n",
-    "        # 加载图像\n",
-    "        img_y = load_img(target_img_path, self.image_size, color_mode=\"grayscale\")  \n",
-    "        y = np.array(img_y, dtype='uint8')  \n",
+    "        # 加载Label图像\n",
+    "        label_image = self._load_img(self.label_images[idx], color_mode=\"grayscale\")  \n",
+    "        y = np.array(label_image, dtype='uint8')  \n",
     "\n",
     "        # 图像预处理\n",
     "        # Label图像是二维的数组(size, size)，升维到(size, size, 1)后才能用于最后loss计算\n",
@@ -415,7 +368,10 @@
     "        return x, y.astype('int64')\n",
     "        \n",
     "    def __len__(self):\n",
-    "        return len(self.target_img_paths)"
+    "        \"\"\"\n",
+    "        返回数据集总数\n",
+    "        \"\"\"\n",
+    "        return len(self.train_images)"
    ]
   },
   {
@@ -425,14 +381,14 @@
     "id": "GYxTHfbBESSG"
    },
    "source": [
-    "### 3.5 PetDataSet抽样展示\n",
+    "### 3.4 PetDataSet数据集抽样展示\n",
     "\n",
-    "实现好Dataset数据集后，我们来测试一下数据集是否符合预期，因为Dataset是一个可以被迭代的Class，我们通过for循环从里面读取数据来用matplotlib进行展示。"
+    "实现好Dataset数据集后，我们来测试一下数据集是否符合预期，因为Dataset是一个可以被迭代的Class，我们通过for循环从里面读取数据来用matplotlib进行展示，这里要注意的是对于分割的标签文件因为是1通道的灰度图片，需要在使用imshow接口时注意下传参cmap='gray'。"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -445,21 +401,9 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
-       "<Figure size 432x288 with 1 Axes>"
-      ]
-     },
-     "metadata": {
-      "needs_background": "light"
-     },
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 432x288 with 1 Axes>"
+       "<Figure size 432x288 with 2 Axes>"
       ]
      },
      "metadata": {
@@ -469,22 +413,29 @@
     }
    ],
    "source": [
-    "import matplotlib.pyplot as plt\n",
+    "# 训练数据集\n",
+    "train_dataset = PetDataset(train_images_path, label_images_path, mode='train')\n",
     "\n",
+    "# 验证数据集\n",
+    "val_dataset = PetDataset(train_images_path, label_images_path, mode='test')\n",
     "\n",
-    "for i in PetDataSet((160, 160), input_img_paths, target_img_paths):\n",
-    "    # 原图\n",
-    "    plt.figure()\n",
-    "    plt.imshow(i[0].transpose((1, 2, 0)).astype('uint8'))\n",
-    "    plt.axis(\"off\")\n",
-    "    plt.show()\n",
+    "# 抽样一个数据\n",
+    "image, label = train_dataset[0]\n",
     "\n",
-    "    # Mask\n",
-    "    plt.figure()\n",
-    "    plt.imshow(np.squeeze(i[1], axis=0).astype('uint8'), cmap='gray')\n",
-    "    plt.axis(\"off\")\n",
-    "    plt.show()\n",
-    "    break"
+    "# 进行图片的展示\n",
+    "plt.figure()\n",
+    "\n",
+    "plt.subplot(1,2,1), \n",
+    "plt.title('Train Image')\n",
+    "plt.imshow(image.transpose((1, 2, 0)).astype('uint8'))\n",
+    "plt.axis('off')\n",
+    "\n",
+    "plt.subplot(1,2,2), \n",
+    "plt.title('Label')\n",
+    "plt.imshow(np.squeeze(label, axis=0).astype('uint8'), cmap='gray')\n",
+    "plt.axis('off')\n",
+    "\n",
+    "plt.show()"
    ]
   },
   {
@@ -508,14 +459,13 @@
    "source": [
     "### 4.1 自定义模型可视化工具类\n",
     "\n",
-    "因为目前Hapi中没有对应Keras的summary接口，无法展示网络结构和每层的输入输出结构信息，所以自定义了一个工具类来实现网络结构可视化。\n",
     "\n",
-    "@TODO，替换为summary接口调用\n"
+    "@TODO，summary接口正在PR中，等Merge后替换为summary接口调用。\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -523,16 +473,8 @@
    },
    "outputs": [],
    "source": [
-    "import paddle\n",
-    "\n",
     "from tabulate import tabulate\n",
     "\n",
-    "from paddle.incubate.hapi.model import Model\n",
-    "from paddle import nn\n",
-    "from paddle.nn import Layer, Sequential\n",
-    "from paddle.incubate.hapi.model import Input\n",
-    "\n",
-    "\n",
     "class ModelTools(object):\n",
     "    def __init__(self):\n",
     "        self.debug_table_data = []\n",
@@ -587,14 +529,14 @@
     "id": "wi-ouGZL--BN"
    },
    "source": [
-    "### 4.2 自定义SeparableConv2D接口\n",
+    "### 4.2 定义SeparableConv2d接口\n",
     "\n",
-    "这里我们是继承paddle.nn.Layer自定义了一个SeparableConv2D Layer类，整个过程是把`filter_size * filter_size * num_filters`的Conv2D操作拆解为两个子Conv2D，先对输入数据的每个通道使用`filter_size * filter_size * 1`的卷积核进行计算，输入输出通道数目相同，之后在使用`1 * 1 * num_filters`的卷积核计算，减少卷积操作中的训练参数，提升性能。"
+    "我们为了减少卷积操作中的训练参数来提升性能，是继承paddle.nn.Layer自定义了一个SeparableConv2d Layer类，整个过程是把`filter_size * filter_size * num_filters`的Conv2d操作拆解为两个子Conv2d，先对输入数据的每个通道使用`filter_size * filter_size * 1`的卷积核进行计算，输入输出通道数目相同，之后在使用`1 * 1 * num_filters`的卷积核计算。"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -602,48 +544,39 @@
    },
    "outputs": [],
    "source": [
-    "class SeparableConv2D(Layer):\n",
+    "class SeparableConv2d(paddle.nn.Layer):\n",
     "    def __init__(self, \n",
-    "                 num_channels, \n",
-    "                 num_filters, \n",
-    "                 filter_size, \n",
-    "                 padding=0, \n",
+    "                 in_channels, \n",
+    "                 out_channels, \n",
+    "                 kernel_size, \n",
     "                 stride=1, \n",
+    "                 padding=0, \n",
     "                 dilation=1, \n",
     "                 groups=None, \n",
-    "                 param_attr=None, \n",
+    "                 weight_attr=None, \n",
     "                 bias_attr=None, \n",
-    "                 use_cudnn=True, \n",
-    "                 act=None, \n",
-    "                 data_format=\"NCHW\", \n",
-    "                 dtype=\"float32\"):\n",
-    "        super(SeparableConv2D, self).__init__()\n",
+    "                 data_format=\"NCHW\"):\n",
+    "        super(SeparableConv2d, self).__init__()\n",
     "        # 第一次卷积操作没有偏置参数\n",
-    "        self.conv_1 = nn.Conv2D(num_channels, \n",
-    "                             num_channels, \n",
-    "                             filter_size, \n",
-    "                             padding=padding,\n",
-    "                             stride=stride,\n",
-    "                             dilation=dilation,\n",
-    "                             groups=num_channels, \n",
-    "                             param_attr=param_attr, \n",
-    "                             bias_attr=False, \n",
-    "                             use_cudnn=use_cudnn, \n",
-    "                             act=None, \n",
-    "                             data_format=data_format, \n",
-    "                             dtype=dtype)\n",
-    "        self.pointwise = nn.Conv2D(num_channels, \n",
-    "                             num_filters, \n",
-    "                             1, \n",
-    "                             padding=0, \n",
-    "                             stride=1, \n",
-    "                             dilation=1, \n",
-    "                             groups=1, \n",
-    "                             bias_attr=bias_attr, \n",
-    "                             use_cudnn=use_cudnn, \n",
-    "                             act=act, \n",
-    "                             data_format=data_format, \n",
-    "                             dtype=dtype)\n",
+    "        self.conv_1 = paddle.nn.Conv2d(in_channels, \n",
+    "                                       in_channels, \n",
+    "                                       kernel_size, \n",
+    "                                       stride=stride,\n",
+    "                                       padding=padding,\n",
+    "                                       dilation=dilation,\n",
+    "                                       groups=in_channels, \n",
+    "                                       weight_attr=weight_attr, \n",
+    "                                       bias_attr=False,  \n",
+    "                                       data_format=data_format)\n",
+    "        self.pointwise = paddle.nn.Conv2d(in_channels, \n",
+    "                                          out_channels, \n",
+    "                                          1, \n",
+    "                                          stride=1, \n",
+    "                                          padding=0, \n",
+    "                                          dilation=1, \n",
+    "                                          groups=1, \n",
+    "                                          weight_attr=weight_attr, \n",
+    "                                          data_format=data_format)\n",
     "        \n",
     "    def forward(self, inputs):\n",
     "        x = self.conv_1(inputs)\n",
@@ -659,14 +592,14 @@
     "id": "zNyzlqQmBEEi"
    },
    "source": [
-    "### 4.3 自定义Encoder编码器Layer\n",
+    "### 4.3 定义Encoder编码器\n",
     "\n",
-    "我们将网络结构中的Encoder下采样过程进行了一个自定义Layer封装，方便后续调用，减少代码编写，下采样是有一个模型逐渐向下画曲线的一个过程，这个过程中是不断的重复一个单元结构将通道数不断增加，形状不断缩小，并且引入残差网络结构，我们将这些都抽象出来进行统一封装。\n"
+    "我们将网络结构中的Encoder下采样过程进行了一个Layer封装，方便后续调用，减少代码编写，下采样是有一个模型逐渐向下画曲线的一个过程，这个过程中是不断的重复一个单元结构将通道数不断增加，形状不断缩小，并且引入残差网络结构，我们将这些都抽象出来进行统一封装。"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 8,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -674,16 +607,27 @@
    },
    "outputs": [],
    "source": [
-    "class Encoder(Layer):\n",
-    "    def __init__(self, num_channels, filters, tools):\n",
+    "class Encoder(paddle.nn.Layer):\n",
+    "    def __init__(self, in_channels, out_channels, tools):\n",
     "        super(Encoder, self).__init__()\n",
     "        self.tools = tools\n",
-    "        self.relu = nn.ReLU()\n",
-    "        self.separable_conv_01 = SeparableConv2D(num_channels, filters, 3, padding='SAME')\n",
-    "        self.bn = nn.BatchNorm(filters)\n",
-    "        self.separable_conv_02 = SeparableConv2D(filters, filters, 3, padding='SAME')\n",
-    "        self.pool = nn.Pool2D(pool_size=3, pool_type='max', pool_stride=2, pool_padding=1) \n",
-    "        self.residual_conv = nn.Conv2D(num_channels, filters, 1, stride=2, padding='SAME')\n",
+    "        \n",
+    "        self.relu = paddle.nn.ReLU()\n",
+    "        self.separable_conv_01 = SeparableConv2d(in_channels, \n",
+    "                                                 out_channels, \n",
+    "                                                 kernel_size=3, \n",
+    "                                                 padding='same')\n",
+    "        self.bn = paddle.nn.BatchNorm2d(out_channels)\n",
+    "        self.separable_conv_02 = SeparableConv2d(out_channels, \n",
+    "                                                 out_channels, \n",
+    "                                                 kernel_size=3, \n",
+    "                                                 padding='same')\n",
+    "        self.pool = paddle.nn.MaxPool2d(kernel_size=3, stride=2, padding=1)\n",
+    "        self.residual_conv = paddle.nn.Conv2d(in_channels, \n",
+    "                                              out_channels, \n",
+    "                                              kernel_size=1, \n",
+    "                                              stride=2, \n",
+    "                                              padding='same')\n",
     "\n",
     "    def forward(self, inputs):\n",
     "        previous_block_activation = inputs\n",
@@ -708,14 +652,14 @@
     "id": "nPBRD42WGmuH"
    },
    "source": [
-    "### 4.4 自定义Decoder解码器Layer\n",
+    "### 4.4 定义Decoder解码器\n",
     "\n",
     "在通道数达到最大得到高级语义特征图后，网络结构会开始进行decode操作，进行上采样，通道数逐渐减小，对应图片尺寸逐步增加，直至恢复到原图像大小，那么这个过程里面也是通过不断的重复相同结构的残差网络完成，我们也是为了减少代码编写，将这个过程定义一个Layer来放到模型组网中使用。"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 9,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -723,17 +667,26 @@
    },
    "outputs": [],
    "source": [
-    "class Decoder(Layer):\n",
-    "    def __init__(self, num_channels, num_filters, tools):\n",
+    "class Decoder(paddle.nn.Layer):\n",
+    "    def __init__(self, in_channels, out_channels, tools):\n",
     "        super(Decoder, self).__init__()\n",
     "        self.tools = tools\n",
     "\n",
-    "        self.relu = nn.ReLU()\n",
-    "        self.conv_transpose_01 = nn.Conv2DTranspose(num_channels, num_filters, 3, padding='SAME')\n",
-    "        self.conv_transpose_02 = nn.Conv2DTranspose(num_filters, num_filters, 3, padding='SAME')\n",
-    "        self.bn = nn.BatchNorm(num_filters)\n",
-    "        self.upsample = nn.UpSample(scale=2.0)\n",
-    "        self.residual_conv = nn.Conv2D(num_channels, num_filters, 1, padding='SAME')\n",
+    "        self.relu = paddle.nn.ReLU()\n",
+    "        self.conv_transpose_01 = paddle.nn.ConvTranspose2d(in_channels, \n",
+    "                                                           out_channels, \n",
+    "                                                           kernel_size=3, \n",
+    "                                                           padding='same')\n",
+    "        self.conv_transpose_02 = paddle.nn.ConvTranspose2d(out_channels, \n",
+    "                                                           out_channels, \n",
+    "                                                           kernel_size=3, \n",
+    "                                                           padding='same')\n",
+    "        self.bn = paddle.nn.BatchNorm2d(out_channels)\n",
+    "        self.upsample = paddle.nn.UpSample(scale_factor=2.0)\n",
+    "        self.residual_conv = paddle.nn.Conv2d(in_channels, \n",
+    "                                              out_channels, \n",
+    "                                              kernel_size=1, \n",
+    "                                              padding='same')\n",
     "\n",
     "    def forward(self, inputs):\n",
     "        previous_block_activation = inputs\n",
@@ -766,7 +719,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 10,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -774,37 +727,43 @@
    },
    "outputs": [],
    "source": [
-    "class PetModel(Model):\n",
+    "class PetModel(paddle.nn.Layer):\n",
     "    def __init__(self, num_classes, tools):\n",
     "        super(PetModel, self).__init__()\n",
     "        self.tools = tools\n",
     "\n",
-    "        self.conv_1 = nn.Conv2D(3, 32, 3, padding='SAME', stride=2)\n",
-    "        self.bn = nn.BatchNorm(32)\n",
-    "        self.relu = nn.ReLU()\n",
+    "        self.conv_1 = paddle.nn.Conv2d(3, 32, \n",
+    "                                       kernel_size=3,\n",
+    "                                       stride=2,\n",
+    "                                       padding='same')\n",
+    "        self.bn = paddle.nn.BatchNorm2d(32)\n",
+    "        self.relu = paddle.nn.ReLU()\n",
     "\n",
-    "        num_channels = 32\n",
+    "        in_channels = 32\n",
     "        self.encoders = []\n",
     "        self.encoder_list = [64, 128, 256]\n",
     "        self.decoder_list = [256, 128, 64, 32]\n",
     "\n",
     "        # 根据下采样个数和配置循环定义子Layer，避免重复写一样的程序\n",
-    "        for num_filters in self.encoder_list:\n",
-    "            block = self.add_sublayer('encoder_%s'.format(num_filters),\n",
-    "                                      Encoder(num_channels, num_filters, self.tools))\n",
+    "        for out_channels in self.encoder_list:\n",
+    "            block = self.add_sublayer('encoder_%s'.format(out_channels),\n",
+    "                                      Encoder(in_channels, out_channels, self.tools))\n",
     "            self.encoders.append(block)\n",
-    "            num_channels = num_filters\n",
+    "            in_channels = out_channels\n",
     "\n",
     "        self.decoders = []\n",
     "\n",
     "        # 根据上采样个数和配置循环定义子Layer，避免重复写一样的程序\n",
-    "        for num_filters in self.decoder_list:\n",
-    "            block = self.add_sublayer('decoder_%s'.format(num_filters), \n",
-    "                                      Decoder(num_channels, num_filters, self.tools))\n",
+    "        for out_channels in self.decoder_list:\n",
+    "            block = self.add_sublayer('decoder_%s'.format(out_channels), \n",
+    "                                      Decoder(in_channels, out_channels, self.tools))\n",
     "            self.decoders.append(block)\n",
-    "            num_channels = num_filters\n",
+    "            in_channels = out_channels\n",
     "\n",
-    "        self.output_conv = nn.Conv2D(num_channels, num_classes, 3, padding='SAME')\n",
+    "        self.output_conv = paddle.nn.Conv2d(in_channels, \n",
+    "                                            num_classes, \n",
+    "                                            kernel_size=3, \n",
+    "                                            padding='same')\n",
     "    \n",
     "    def forward(self, inputs):\n",
     "        y = self.tools.invoke(self.conv_1, inputs)\n",
@@ -837,7 +796,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 11,
    "metadata": {
     "colab": {
      "base_uri": "https://localhost:8080/",
@@ -857,71 +816,71 @@
       "|       Layer        |               In Shape                |     Out Shape     | Param Num |\n",
       "+--------------------+---------------------------------------+-------------------+-----------+\n",
       "|      conv2d_0      |           [1, 3, 160, 160]            |  [1, 32, 80, 80]  |    896    |\n",
-      "|    batch_norm_0    |            [1, 32, 80, 80]            |  [1, 32, 80, 80]  |    128    |\n",
+      "|   batch_norm2d_0   |            [1, 32, 80, 80]            |  [1, 32, 80, 80]  |    128    |\n",
       "|      re_lu_0       |            [1, 32, 80, 80]            |  [1, 32, 80, 80]  |     0     |\n",
       "|      re_lu_1       |            [1, 32, 80, 80]            |  [1, 32, 80, 80]  |     0     |\n",
       "| separable_conv2d_0 |            [1, 32, 80, 80]            |  [1, 64, 80, 80]  |   2400    |\n",
-      "|    batch_norm_1    |            [1, 64, 80, 80]            |  [1, 64, 80, 80]  |    256    |\n",
+      "|   batch_norm2d_1   |            [1, 64, 80, 80]            |  [1, 64, 80, 80]  |    256    |\n",
       "|      re_lu_1       |            [1, 64, 80, 80]            |  [1, 64, 80, 80]  |     0     |\n",
       "| separable_conv2d_1 |            [1, 64, 80, 80]            |  [1, 64, 80, 80]  |   4736    |\n",
-      "|    batch_norm_1    |            [1, 64, 80, 80]            |  [1, 64, 80, 80]  |    256    |\n",
-      "|      pool2d_0      |            [1, 64, 80, 80]            |  [1, 64, 40, 40]  |     0     |\n",
+      "|   batch_norm2d_1   |            [1, 64, 80, 80]            |  [1, 64, 80, 80]  |    256    |\n",
+      "|    max_pool2d_0    |            [1, 64, 80, 80]            |  [1, 64, 40, 40]  |     0     |\n",
       "|      conv2d_5      |            [1, 32, 80, 80]            |  [1, 64, 40, 40]  |   2112    |\n",
       "|        ADD         |   [1, 64, 40, 40] + [1, 64, 40, 40]   |  [1, 64, 40, 40]  |     0     |\n",
       "|      re_lu_2       |            [1, 64, 40, 40]            |  [1, 64, 40, 40]  |     0     |\n",
       "| separable_conv2d_2 |            [1, 64, 40, 40]            | [1, 128, 40, 40]  |   8896    |\n",
-      "|    batch_norm_2    |           [1, 128, 40, 40]            | [1, 128, 40, 40]  |    512    |\n",
+      "|   batch_norm2d_2   |           [1, 128, 40, 40]            | [1, 128, 40, 40]  |    512    |\n",
       "|      re_lu_2       |           [1, 128, 40, 40]            | [1, 128, 40, 40]  |     0     |\n",
       "| separable_conv2d_3 |           [1, 128, 40, 40]            | [1, 128, 40, 40]  |   17664   |\n",
-      "|    batch_norm_2    |           [1, 128, 40, 40]            | [1, 128, 40, 40]  |    512    |\n",
-      "|      pool2d_1      |           [1, 128, 40, 40]            | [1, 128, 20, 20]  |     0     |\n",
+      "|   batch_norm2d_2   |           [1, 128, 40, 40]            | [1, 128, 40, 40]  |    512    |\n",
+      "|    max_pool2d_1    |           [1, 128, 40, 40]            | [1, 128, 20, 20]  |     0     |\n",
       "|     conv2d_10      |            [1, 64, 40, 40]            | [1, 128, 20, 20]  |   8320    |\n",
       "|        ADD         |  [1, 128, 20, 20] + [1, 128, 20, 20]  | [1, 128, 20, 20]  |     0     |\n",
       "|      re_lu_3       |           [1, 128, 20, 20]            | [1, 128, 20, 20]  |     0     |\n",
       "| separable_conv2d_4 |           [1, 128, 20, 20]            | [1, 256, 20, 20]  |   34176   |\n",
-      "|    batch_norm_3    |           [1, 256, 20, 20]            | [1, 256, 20, 20]  |   1024    |\n",
+      "|   batch_norm2d_3   |           [1, 256, 20, 20]            | [1, 256, 20, 20]  |   1024    |\n",
       "|      re_lu_3       |           [1, 256, 20, 20]            | [1, 256, 20, 20]  |     0     |\n",
       "| separable_conv2d_5 |           [1, 256, 20, 20]            | [1, 256, 20, 20]  |   68096   |\n",
-      "|    batch_norm_3    |           [1, 256, 20, 20]            | [1, 256, 20, 20]  |   1024    |\n",
-      "|      pool2d_2      |           [1, 256, 20, 20]            | [1, 256, 10, 10]  |     0     |\n",
+      "|   batch_norm2d_3   |           [1, 256, 20, 20]            | [1, 256, 20, 20]  |   1024    |\n",
+      "|    max_pool2d_2    |           [1, 256, 20, 20]            | [1, 256, 10, 10]  |     0     |\n",
       "|     conv2d_15      |           [1, 128, 20, 20]            | [1, 256, 10, 10]  |   33024   |\n",
       "|        ADD         |  [1, 256, 10, 10] + [1, 256, 10, 10]  | [1, 256, 10, 10]  |     0     |\n",
       "|      re_lu_4       |           [1, 256, 10, 10]            | [1, 256, 10, 10]  |     0     |\n",
-      "| conv2d_transpose_0 |           [1, 256, 10, 10]            | [1, 256, 10, 10]  |  590080   |\n",
-      "|    batch_norm_4    |           [1, 256, 10, 10]            | [1, 256, 10, 10]  |   1024    |\n",
+      "| conv_transpose2d_0 |           [1, 256, 10, 10]            | [1, 256, 10, 10]  |  590080   |\n",
+      "|   batch_norm2d_4   |           [1, 256, 10, 10]            | [1, 256, 10, 10]  |   1024    |\n",
       "|      re_lu_4       |           [1, 256, 10, 10]            | [1, 256, 10, 10]  |     0     |\n",
-      "| conv2d_transpose_1 |           [1, 256, 10, 10]            | [1, 256, 10, 10]  |  590080   |\n",
-      "|    batch_norm_4    |           [1, 256, 10, 10]            | [1, 256, 10, 10]  |   1024    |\n",
+      "| conv_transpose2d_1 |           [1, 256, 10, 10]            | [1, 256, 10, 10]  |  590080   |\n",
+      "|   batch_norm2d_4   |           [1, 256, 10, 10]            | [1, 256, 10, 10]  |   1024    |\n",
       "|    up_sample_0     |           [1, 256, 10, 10]            | [1, 256, 20, 20]  |     0     |\n",
       "|    up_sample_0     |           [1, 256, 10, 10]            | [1, 256, 20, 20]  |     0     |\n",
       "|     conv2d_16      |           [1, 256, 20, 20]            | [1, 256, 20, 20]  |   65792   |\n",
       "|        ADD         |  [1, 256, 20, 20] + [1, 256, 20, 20]  | [1, 256, 20, 20]  |     0     |\n",
       "|      re_lu_5       |           [1, 256, 20, 20]            | [1, 256, 20, 20]  |     0     |\n",
-      "| conv2d_transpose_2 |           [1, 256, 20, 20]            | [1, 128, 20, 20]  |  295040   |\n",
-      "|    batch_norm_5    |           [1, 128, 20, 20]            | [1, 128, 20, 20]  |    512    |\n",
+      "| conv_transpose2d_2 |           [1, 256, 20, 20]            | [1, 128, 20, 20]  |  295040   |\n",
+      "|   batch_norm2d_5   |           [1, 128, 20, 20]            | [1, 128, 20, 20]  |    512    |\n",
       "|      re_lu_5       |           [1, 128, 20, 20]            | [1, 128, 20, 20]  |     0     |\n",
-      "| conv2d_transpose_3 |           [1, 128, 20, 20]            | [1, 128, 20, 20]  |  147584   |\n",
-      "|    batch_norm_5    |           [1, 128, 20, 20]            | [1, 128, 20, 20]  |    512    |\n",
+      "| conv_transpose2d_3 |           [1, 128, 20, 20]            | [1, 128, 20, 20]  |  147584   |\n",
+      "|   batch_norm2d_5   |           [1, 128, 20, 20]            | [1, 128, 20, 20]  |    512    |\n",
       "|    up_sample_1     |           [1, 128, 20, 20]            | [1, 128, 40, 40]  |     0     |\n",
       "|    up_sample_1     |           [1, 256, 20, 20]            | [1, 256, 40, 40]  |     0     |\n",
       "|     conv2d_17      |           [1, 256, 40, 40]            | [1, 128, 40, 40]  |   32896   |\n",
       "|        ADD         |  [1, 128, 40, 40] + [1, 128, 40, 40]  | [1, 128, 40, 40]  |     0     |\n",
       "|      re_lu_6       |           [1, 128, 40, 40]            | [1, 128, 40, 40]  |     0     |\n",
-      "| conv2d_transpose_4 |           [1, 128, 40, 40]            |  [1, 64, 40, 40]  |   73792   |\n",
-      "|    batch_norm_6    |            [1, 64, 40, 40]            |  [1, 64, 40, 40]  |    256    |\n",
+      "| conv_transpose2d_4 |           [1, 128, 40, 40]            |  [1, 64, 40, 40]  |   73792   |\n",
+      "|   batch_norm2d_6   |            [1, 64, 40, 40]            |  [1, 64, 40, 40]  |    256    |\n",
       "|      re_lu_6       |            [1, 64, 40, 40]            |  [1, 64, 40, 40]  |     0     |\n",
-      "| conv2d_transpose_5 |            [1, 64, 40, 40]            |  [1, 64, 40, 40]  |   36928   |\n",
-      "|    batch_norm_6    |            [1, 64, 40, 40]            |  [1, 64, 40, 40]  |    256    |\n",
+      "| conv_transpose2d_5 |            [1, 64, 40, 40]            |  [1, 64, 40, 40]  |   36928   |\n",
+      "|   batch_norm2d_6   |            [1, 64, 40, 40]            |  [1, 64, 40, 40]  |    256    |\n",
       "|    up_sample_2     |            [1, 64, 40, 40]            |  [1, 64, 80, 80]  |     0     |\n",
       "|    up_sample_2     |           [1, 128, 40, 40]            | [1, 128, 80, 80]  |     0     |\n",
       "|     conv2d_18      |           [1, 128, 80, 80]            |  [1, 64, 80, 80]  |   8256    |\n",
       "|        ADD         |   [1, 64, 80, 80] + [1, 64, 80, 80]   |  [1, 64, 80, 80]  |     0     |\n",
       "|      re_lu_7       |            [1, 64, 80, 80]            |  [1, 64, 80, 80]  |     0     |\n",
-      "| conv2d_transpose_6 |            [1, 64, 80, 80]            |  [1, 32, 80, 80]  |   18464   |\n",
-      "|    batch_norm_7    |            [1, 32, 80, 80]            |  [1, 32, 80, 80]  |    128    |\n",
+      "| conv_transpose2d_6 |            [1, 64, 80, 80]            |  [1, 32, 80, 80]  |   18464   |\n",
+      "|   batch_norm2d_7   |            [1, 32, 80, 80]            |  [1, 32, 80, 80]  |    128    |\n",
       "|      re_lu_7       |            [1, 32, 80, 80]            |  [1, 32, 80, 80]  |     0     |\n",
-      "| conv2d_transpose_7 |            [1, 32, 80, 80]            |  [1, 32, 80, 80]  |   9248    |\n",
-      "|    batch_norm_7    |            [1, 32, 80, 80]            |  [1, 32, 80, 80]  |    128    |\n",
+      "| conv_transpose2d_7 |            [1, 32, 80, 80]            |  [1, 32, 80, 80]  |   9248    |\n",
+      "|   batch_norm2d_7   |            [1, 32, 80, 80]            |  [1, 32, 80, 80]  |    128    |\n",
       "|    up_sample_3     |            [1, 32, 80, 80]            | [1, 32, 160, 160] |     0     |\n",
       "|    up_sample_3     |            [1, 64, 80, 80]            | [1, 64, 160, 160] |     0     |\n",
       "|     conv2d_19      |           [1, 64, 160, 160]           | [1, 32, 160, 160] |   2080    |\n",
@@ -933,19 +892,16 @@
     }
    ],
    "source": [
-    "img_size = (160, 160)\n",
+    "paddle.disable_static()\n",
+    "\n",
     "num_classes = 4\n",
     "model_tools = ModelTools()\n",
+    "model = PetModel(num_classes, model_tools)\n",
     "\n",
-    "with paddle.imperative.guard():\n",
-    "    model = PetModel(num_classes, model_tools)\n",
-    "\n",
-    "    for i in PetDataSet((160, 160), input_img_paths, target_img_paths):\n",
-    "        data = paddle.imperative.to_variable(np.expand_dims(i[0].astype('float32'), 0))\n",
-    "        res = model(data)\n",
-    "        break\n",
+    "data = paddle.to_tensor(np.expand_dims(train_dataset[0][0].astype('float32'), 0))\n",
+    "res = model(data)\n",
     "\n",
-    "    model_tools.show()"
+    "model_tools.show()"
    ]
   },
   {
@@ -958,45 +914,6 @@
     "## 5.模型训练"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "colab_type": "text",
-    "id": "b5DWGu50J8Fc"
-   },
-   "source": [
-    "### 5.1 训练数据集生成\n",
-    "\n",
-    "将所有的数据集文件进行随机打乱并切分，划分为训练数据集和评估数据集，使用之前定义好的PetDataset类进行训练和评估数据集的实例化，以便后续在fit接口中直接使用。"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {
-    "colab": {},
-    "colab_type": "code",
-    "id": "fTio14QjeSdK"
-   },
-   "outputs": [],
-   "source": [
-    "import random\n",
-    "\n",
-    "\n",
-    "# 进行随机打乱和切分数据集，这个部分根据自己的实际任务需要完成即可，非框架标准内容\n",
-    "val_samples = 1000\n",
-    "random.Random(1337).shuffle(input_img_paths)\n",
-    "random.Random(1337).shuffle(target_img_paths)\n",
-    "train_input_img_paths = input_img_paths[:-val_samples]\n",
-    "train_target_img_paths = target_img_paths[:-val_samples]\n",
-    "val_input_img_paths = input_img_paths[-val_samples:]\n",
-    "val_target_img_paths = target_img_paths[-val_samples:]\n",
-    "\n",
-    "# 使用切分好的数据进行数据集的实例化\n",
-    "train_dataset = PetDataSet(img_size, train_input_img_paths, train_target_img_paths)\n",
-    "val_dataset = PetDataSet(img_size, val_input_img_paths, val_target_img_paths)"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {
@@ -1004,14 +921,14 @@
     "id": "8Sskbyz58X4J"
    },
    "source": [
-    "### 5.2 配置信息\n",
+    "### 5.1 配置信息\n",
     "\n",
     "定义训练BATCH_SIZE、训练轮次和计算设备等信息。"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": null,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -1019,18 +936,10 @@
    },
    "outputs": [],
    "source": [
-    "from paddle.optimizer import RMSPropOptimizer\n",
-    "from paddle.incubate.hapi.callbacks import Callback\n",
-    "from paddle.incubate.hapi.metrics import Metric\n",
-    "from paddle.incubate.hapi.model import set_device\n",
-    "from paddle.incubate.hapi.loss import Loss\n",
-    "import paddle.fluid as fluid\n",
-    "\n",
     "BATCH_SIZE = 32\n",
     "EPOCHS = 15\n",
-    "dynamic = True\n",
-    "device = set_device('gpu')\n",
-    "paddle.enable_imperative(device) if dynamic else None"
+    "device = paddle.set_device('gpu')\n",
+    "paddle.disable_static(device)"
    ]
   },
   {
@@ -1042,12 +951,12 @@
    "source": [
     "### 5.3 自定义Loss\n",
     "\n",
-    "@TODO，替换成Beta中统一的Loss API，不需要自定义了。"
+    "在这个任务中我们使用SoftmaxWithCrossEntropy损失函数来做计算，飞桨中有functional形式的API，这里我们做一个自定义操作，实现一个Class形式API放到模型训练中使用。没有直接使用CrossEntropyLoss的原因主要是对计算维度的自定义需求，本次需要进行softmax计算的维度是1，不是默认的最后一维，所以我们采用上面提到的损失函数，通过axis参数来指定softmax计算维度。"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 13,
    "metadata": {
     "colab": {},
     "colab_type": "code",
@@ -1055,68 +964,16 @@
    },
    "outputs": [],
    "source": [
-    "class SoftmaxWithCrossEntropy(Loss):\n",
-    "    def __init__(self, average=True):\n",
-    "        super(SoftmaxWithCrossEntropy, self).__init__(average)\n",
-    "\n",
-    "    def forward(self, outputs, labels):\n",
-    "        return [\n",
-    "            fluid.layers.softmax_with_cross_entropy(\n",
-    "                o, l, return_softmax=False, axis=1) for o, l in zip(outputs, labels)\n",
-    "        ]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "colab_type": "text",
-    "id": "Cc7_MqWr8jj5"
-   },
-   "source": [
-    "### 5.4 自定义Metric\n",
-    "\n",
-    "Paddle里面有一个functional形式的mean_iou接口，我们需要使用一个Class形式的API，这里我们来自定义实现一个。"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 31,
-   "metadata": {
-    "colab": {},
-    "colab_type": "code",
-    "id": "vCjCdfBK8Dai"
-   },
-   "outputs": [],
-   "source": [
-    "class MIOUMetric(Metric):\n",
-    "    def __init__(self, num_classes, name=None, *args, **kwargs):\n",
-    "        super(MIOUMetric, self).__init__(*args, **kwargs)\n",
-    "        self.num_classes = num_classes\n",
-    "        self._name = name or 'miou'\n",
-    "        self.reset()\n",
-    "    \n",
-    "    def add_metric_op(self, output, label):\n",
-    "        return paddle.metric.mean_iou(output.astype('int64'), label, self.num_classes)\n",
-    "\n",
-    "    def update(self, mean_iou, out_wrong, out_correct, *args):\n",
-    "        print(out_correct)\n",
-    "        exit()\n",
-    "        return mean_iou\n",
-    "\n",
-    "    def reset(self):\n",
-    "        # do nothing\n",
-    "        self.total = [0.]\n",
-    "        self.count = [0]\n",
-    "\n",
-    "    def accumulate(self):\n",
-    "        res = []\n",
-    "        for t, c in zip(self.total, self.count):\n",
-    "            res.append(float(t) / c)\n",
-    "\n",
-    "        return res\n",
-    "\n",
-    "    def name(self):\n",
-    "        return self._name"
+    "class SoftmaxWithCrossEntropy(paddle.nn.Layer):\n",
+    "    def __init__(self):\n",
+    "        super(SoftmaxWithCrossEntropy, self).__init__()\n",
+    "\n",
+    "    def forward(self, input, label):\n",
+    "        loss = F.softmax_with_cross_entropy(input, \n",
+    "                                            label, \n",
+    "                                            return_softmax=False,\n",
+    "                                            axis=1)\n",
+    "        return paddle.mean(loss)"
    ]
   },
   {
@@ -1126,7 +983,7 @@
     "id": "rj6MPPMkJIdZ"
    },
    "source": [
-    "### 5.5 启动模型训练\n",
+    "### 5.4 启动模型训练\n",
     "\n",
     "使用模型代码进行Model实例生成，使用prepare接口定义优化器、损失函数和评价指标等信息，用于后续训练使用。在所有初步配置完成后，调用fit接口开启训练执行过程，调用fit时只需要将前面定义好的训练数据集、测试数据集、训练轮次（Epoch）和批次大小（batch_size）配置好即可。"
    ]
@@ -1144,34 +1001,22 @@
     "outputId": "9b37dd07-746b-41cc-c8e2-687a83b1ad75",
     "tags": []
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Epoch 1/1\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "optim = RMSPropOptimizer(learning_rate=0.001, \n",
-    "                         rho=0.9, \n",
-    "                         momentum=0.0, \n",
-    "                         epsilon=1e-07, \n",
-    "                         centered=False,\n",
-    "                         parameter_list=model.parameters())\n",
+    "optim = paddle.optimizer.RMSProp(learning_rate=0.001, \n",
+    "                                 rho=0.9, \n",
+    "                                 momentum=0.0, \n",
+    "                                 epsilon=1e-07, \n",
+    "                                 centered=False,\n",
+    "                                 parameters=model.parameters())\n",
+    "model = paddle.Model(PetModel(num_classes, model_tools))\n",
     "model.prepare(optim, \n",
-    "    SoftmaxWithCrossEntropy(),\n",
-    "    MIOUMetric(num_classes),\n",
-    "    [Input([None, 3, 160, 160], 'float32', name='image')],\n",
-    "    [Input([None, 1, 160, 160], 'int64', name='label')],\n",
-    "    device=device\n",
-    ")\n",
+    "              SoftmaxWithCrossEntropy())\n",
     "\n",
     "model.fit(train_dataset, \n",
     "    val_dataset, \n",
-    "    epochs=1, \n",
-    "    batch_size=32\n",
+    "    epochs=EPOCHS, \n",
+    "    batch_size=BATCH_SIZE\n",
     ")"
    ]
   },
@@ -1209,8 +1054,7 @@
    },
    "outputs": [],
    "source": [
-    "predict_dataset = PetDataSet(img_size, val_input_img_paths, val_target_img_paths)\n",
-    "val_preds = model.predict(predict_dataset)"
+    "predict_results = model.predict(val_dataset)"
    ]
   },
   {
@@ -1220,7 +1064,9 @@
     "id": "-DpAEFBSJioy"
    },
    "source": [
-    "### 6.2 预测结果可视化"
+    "### 6.2 预测结果可视化\n",
+    "\n",
+    "从我们的预测数据集中抽3个动物来看看预测的效果，展示一下原图、标签图和预测结果。"
    ]
   },
   {
@@ -1233,15 +1079,12 @@
    },
    "outputs": [],
    "source": [
-    "import matplotlib.pyplot as plt\n",
-    "\n",
-    "\n",
     "plt.figure(figsize=(10, 10))\n",
-    "# Display mask predicted by our model\n",
+    "\n",
     "i = 0\n",
     "mask_idx = 0\n",
     "\n",
-    "for data in PetDataSet(img_size, val_input_img_paths, val_target_img_paths):\n",
+    "for data in val_dataset:\n",
     "    if i > 8: \n",
     "        break\n",
     "    plt.subplot(3, 3, i + 1)\n",