Add intro for case and new example

README.md

@@ -413,7 +413,7 @@
 | **智慧农林** | [耕地地块识别](https://mp.weixin.qq.com/s/JlDVmYlhN7sF0hpRlncDNw)               |             |
 | **智慧农林** | [AI识虫](https://aistudio.baidu.com/aistudio/projectdetail/439888)                     |   -   |
 | **智慧农林** | [基于PaddleX实现森林火灾监测](https://aistudio.baidu.com/aistudio/projectdetail/1968964?channelType=0&channel=0) | - |
-| **智慧医疗** | [医学常见中草药分类](https://aistudio.baidu.com/aistudio/projectdetail/1434738?channelType=0&channel=0)         | - |
+| **智慧医疗** | [图像分类网络VGG在中草药识别任务中的应用](https://aistudio.baidu.com/aistudio/projectdetail/2310126?channelType=0&channel=0) | 本案例使用VGG模型对中草药数据集进行分类识别，案例详细的讲解了数据读取和预处理，模型介绍，训练，优化，评估，预测，部署这一完整流程，同时提供带有详细注释的代码 |
 | **智慧医疗** | [眼疾识别](https://www.paddlepaddle.org.cn/tutorials/projectdetail/1630501)                   | - |
 | **智慧生活** | [智能相册分类](https://aistudio.baidu.com/aistudio/projectdetail/2057379) | - |
 | **智慧生活** | [老北京城影像修复](https://aistudio.baidu.com/aistudio/projectdetail/1161285?channelType=0&channel=0) | - |

examples/Identification of Chinese herbal medicine/dataloader.py

@@ -0,0 +1,80 @@
+# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# coding=utf-8
+import os
+from PIL import Image
+import numpy as np
+import paddle
+from paddle.io import Dataset
+
+
+# 定义数据读取器
+class dataset(Dataset):
+    def __init__(self, data_path, mode='train'):
+        """
+        数据读取器
+        :param data_path: 数据集所在路径
+        :param mode: train or eval
+        """
+        super().__init__()
+        self.data_path = data_path
+        self.img_paths = []
+        self.labels = []
+
+        if mode == 'train':
+            with open(
+                    os.path.join(self.data_path, "train.txt"),
+                    "r",
+                    encoding="utf-8") as f:
+                self.info = f.readlines()
+            for img_info in self.info:
+                img_path, label = img_info.strip().split('\t')
+                self.img_paths.append(img_path)
+                self.labels.append(int(label))
+
+        else:
+            with open(
+                    os.path.join(self.data_path, "eval.txt"),
+                    "r",
+                    encoding="utf-8") as f:
+                self.info = f.readlines()
+            for img_info in self.info:
+                img_path, label = img_info.strip().split('\t')
+                self.img_paths.append(img_path)
+                self.labels.append(int(label))
+
+    def __getitem__(self, index):
+        """
+        获取一组数据
+        :param index: 文件索引号
+        :return:
+        """
+        # 第一步打开图像文件并获取label值
+        img_path = self.img_paths[index]
+        img = Image.open(img_path)
+        if img.mode != 'RGB':
+            img = img.convert('RGB')
+        img = img.resize((224, 224), Image.BILINEAR)
+        #img = rand_flip_image(img)
+        img = np.array(img).astype('float32')
+        img = img.transpose((2, 0, 1)) / 255
+        label = self.labels[index]
+        label = np.array([label], dtype="int64")
+        return img, label
+
+    def print_sample(self, index: int=0):
+        print("文件名", self.img_paths[index], "\t标签值", self.labels[index])
+
+    def __len__(self):
+        return len(self.img_paths)

examples/Identification of Chinese herbal medicine/eval.py

@@ -0,0 +1,38 @@
+# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# coding=utf-8
+import numpy as np
+import paddle
+from model import VGGNet
+from dataloader import dataset
+
+#评估数据加载
+eval_dataset = dataset('/home/aistudio/data', mode='eval')
+eval_loader = paddle.io.DataLoader(eval_dataset, batch_size=8, shuffle=False)
+
+# 模型评估
+# 加载训练过程保存的最后一个模型
+model__state_dict = paddle.load('work/checkpoints/save_dir_final.pdparams')
+model_eval = VGGNet(num_classes=5)
+model_eval.set_state_dict(model__state_dict)
+model_eval.eval()
+accs = []
+# 开始评估
+for _, data in enumerate(eval_loader()):
+    x_data = data[0]
+    y_data = data[1]
+    predicts = model_eval(x_data)
+    acc = paddle.metric.accuracy(predicts, y_data)
+    accs.append(acc.numpy()[0])
+print('模型在验证集上的准确率为：', np.mean(accs))

examples/Identification of Chinese herbal medicine/label_dict.txt

@@ -0,0 +1,5 @@
+0 baihe
+1 gouqi
+2 dangshen
+3 jinyinhua
+4 huaihua

examples/Identification of Chinese herbal medicine/model.py

@@ -0,0 +1,107 @@
+# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# coding=utf-8
+import paddle
+
+
+# 定义卷积池化网络
+class ConvPool(paddle.nn.Layer):
+    '''卷积+池化'''
+
+    def __init__(
+            self,
+            num_channels,
+            num_filters,
+            filter_size,
+            pool_size,
+            pool_stride,
+            groups,
+            conv_stride=1,
+            conv_padding=1, ):
+        super(ConvPool, self).__init__()
+
+        # groups代表卷积层的数量
+        for i in range(groups):
+            self.add_sublayer(  #添加子层实例
+                'bb_%d' % i,
+                paddle.nn.Conv2D(  # layer
+                    in_channels=num_channels,  #通道数
+                    out_channels=num_filters,  #卷积核个数
+                    kernel_size=filter_size,  #卷积核大小
+                    stride=conv_stride,  #步长
+                    padding=conv_padding,  #padding
+                ))
+            self.add_sublayer('relu%d' % i, paddle.nn.ReLU())
+            num_channels = num_filters
+
+        self.add_sublayer(
+            'Maxpool',
+            paddle.nn.MaxPool2D(
+                kernel_size=pool_size,  #池化核大小
+                stride=pool_stride  #池化步长
+            ))
+
+    def forward(self, inputs):
+        x = inputs
+        for prefix, sub_layer in self.named_children():
+            # print(prefix,sub_layer)
+            x = sub_layer(x)
+        return x
+
+
+# VGG网络
+class VGGNet(paddle.nn.Layer):
+    def __init__(self, num_classes):
+        super(VGGNet, self).__init__()
+        # 5个卷积池化操作
+        self.convpool01 = ConvPool(
+            3, 64, 3, 2, 2, 2)  #3:通道数，64：卷积核个数，3:卷积核大小，2:池化核大小，2:池化步长，2:连续卷积个数
+        self.convpool02 = ConvPool(64, 128, 3, 2, 2, 2)
+        self.convpool03 = ConvPool(128, 256, 3, 2, 2, 3)
+        self.convpool04 = ConvPool(256, 512, 3, 2, 2, 3)
+        self.convpool05 = ConvPool(512, 512, 3, 2, 2, 3)
+        self.pool_5_shape = 512 * 7 * 7
+        # 三个全连接层
+        self.fc01 = paddle.nn.Linear(self.pool_5_shape, 4096)
+        self.drop1 = paddle.nn.Dropout(p=0.5)
+        self.fc02 = paddle.nn.Linear(4096, 4096)
+        self.drop2 = paddle.nn.Dropout(p=0.5)
+        self.fc03 = paddle.nn.Linear(4096, num_classes)
+
+    def forward(self, inputs, label=None):
+        # print('input_shape:', inputs.shape) #[8, 3, 224, 224]
+        """前向计算"""
+        out = self.convpool01(inputs)
+        # print('convpool01_shape:', out.shape)           #[8, 64, 112, 112]
+        out = self.convpool02(out)
+        # print('convpool02_shape:', out.shape)           #[8, 128, 56, 56]
+        out = self.convpool03(out)
+        # print('convpool03_shape:', out.shape)           #[8, 256, 28, 28]
+        out = self.convpool04(out)
+        # print('convpool04_shape:', out.shape)           #[8, 512, 14, 14]
+        out = self.convpool05(out)
+        # print('convpool05_shape:', out.shape)           #[8, 512, 7, 7]
+
+        out = paddle.reshape(out, shape=[-1, 512 * 7 * 7])
+        out = self.fc01(out)
+        out = self.drop1(out)
+        out = self.fc02(out)
+        out = self.drop2(out)
+        out = self.fc03(out)
+
+        if label is not None:
+            acc = paddle.metric.accuracy(input=out, label=label)
+            return out, acc
+        else:
+            return out

examples/Identification of Chinese herbal medicine/test.py

@@ -0,0 +1,83 @@
+# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# coding=utf-8
+import os
+import zipfile
+from PIL import Image
+import time
+import paddle
+from dataloader import dataset
+from model import VGGNet
+import matplotlib.pyplot as plt
+import numpy as np
+
+
+def unzip_infer_data(src_path, target_path):
+    '''
+    解压预测数据集
+    '''
+    if (not os.path.isdir(target_path + "Chinese Medicine Infer")):
+        z = zipfile.ZipFile(src_path, 'r')
+        z.extractall(path=target_path)
+        z.close()
+
+
+def load_image(img_path):
+    '''
+    预测图片预处理
+    '''
+    img = Image.open(img_path)
+    if img.mode != 'RGB':
+        img = img.convert('RGB')
+    img = img.resize((224, 224), Image.BILINEAR)
+    img = np.array(img).astype('float32')
+    img = img.transpose((2, 0, 1)) / 255  # HWC to CHW 及归一化
+    return img
+
+
+infer_src_path = '/home/aistudio/data/data105575/Chinese Medicine Infer.zip'
+infer_dst_path = '/home/aistudio/data/'
+unzip_infer_data(infer_src_path, infer_dst_path)
+
+label_dic = {}
+with open('/home/aistudio/label_dict.txt', 'r') as f:
+    lines = f.readlines()
+for line in lines:
+    num, name = line.split()
+    label_dic[num] = name
+
+# 加载训练过程保存的最后一个模型
+model__state_dict = paddle.load('work/checkpoints/save_dir_final.pdparams')
+model_predict = VGGNet(num_classes=5)
+model_predict.set_state_dict(model__state_dict)
+model_predict.eval()
+infer_imgs_path = os.listdir(infer_dst_path + "Chinese Medicine Infer")
+# print(infer_imgs_path)
+
+# 预测所有图片
+for infer_img_path in infer_imgs_path:
+    infer_img = load_image(infer_dst_path + "Chinese Medicine Infer/" +
+                           infer_img_path)
+    infer_img = infer_img[np.newaxis, :, :, :]  #reshape(-1,3,224,224)
+    infer_img = paddle.to_tensor(infer_img)
+    result = model_predict(infer_img)
+    lab = np.argmax(result.numpy())
+    print("样本: {},被预测为:{}".format(infer_img_path, label_dic[str(lab)]))
+    # 显示图片
+    #img = Image.open(infer_dst_path+"Chinese Medicine Infer/"+infer_img_path)
+    #plt.imshow(img)
+    #plt.axis('off')
+    #plt.show()
+    #sys.stdout.flush()
+    #time.sleep(0.5)