利用Paddle2.1高层API实现9种蘑菇的识别

!unzip -oq /home/aistudio/data/data82495/mushrooms_train.zip -d work/

import paddle
paddle.seed(8888)import numpy as npfrom typing import Callable#参数配置config_parameters = {    "class_dim": 9,  #分类数
    "target_path":"/home/aistudio/work/",                     
    'train_image_dir': '/home/aistudio/work/trainImages',    'eval_image_dir': '/home/aistudio/work/evalImages',    'epochs':100,    'batch_size': 128,    'lr': 0.01}

import osimport randomfrom matplotlib import pyplot as pltfrom PIL import Image

imgs = []
paths = os.listdir('work/mushrooms_train')for path in paths:   
    img_path = os.path.join('work/mushrooms_train', path)    if os.path.isdir(img_path):
        img_paths = os.listdir(img_path)
        img = Image.open(os.path.join(img_path, random.choice(img_paths)))
        imgs.append((img, path))

f, ax = plt.subplots(3, 3, figsize=(12,12))for i, img in enumerate(imgs[:9]):
    ax[i//3, i%3].imshow(img[0])
    ax[i//3, i%3].axis('off')
    ax[i//3, i%3].set_title('label: %s' % img[1])
plt.show()

import osimport shutil

train_dir = config_parameters['train_image_dir']
eval_dir = config_parameters['eval_image_dir']
paths = os.listdir('work/mushrooms_train')if not os.path.exists(train_dir):
    os.mkdir(train_dir)if not os.path.exists(eval_dir):
    os.mkdir(eval_dir)for path in paths:
    imgs_dir = os.listdir(os.path.join('work/mushrooms_train', path))
    target_train_dir = os.path.join(train_dir,path)
    target_eval_dir = os.path.join(eval_dir,path)    if not os.path.exists(target_train_dir):
        os.mkdir(target_train_dir)    if not os.path.exists(target_eval_dir):
        os.mkdir(target_eval_dir)    for i in range(len(imgs_dir)):        if ' ' in imgs_dir[i]:
            new_name = imgs_dir[i].replace(' ', '_')        else:
            new_name = imgs_dir[i]
        target_train_path = os.path.join(target_train_dir, new_name)
        target_eval_path = os.path.join(target_eval_dir, new_name)     
        if i % 5 == 0:
            shutil.copyfile(os.path.join(os.path.join('work/mushrooms_train', path), imgs_dir[i]), target_eval_path)        else:
            shutil.copyfile(os.path.join(os.path.join('work/mushrooms_train', path), imgs_dir[i]), target_train_path)print('finished train val split!')

#数据集的定义class TowerDataset(paddle.io.Dataset):
    """
    步骤一：继承paddle.io.Dataset类
    """
    def __init__(self, transforms: Callable, mode: str ='train'):
        """
        步骤二：实现构造函数，定义数据读取方式
        """
        super(TowerDataset, self).__init__()
        
        self.mode = mode
        self.transforms = transforms

        train_image_dir = config_parameters['train_image_dir']
        eval_image_dir = config_parameters['eval_image_dir']

        train_data_folder = paddle.vision.DatasetFolder(train_image_dir)
        eval_data_folder = paddle.vision.DatasetFolder(eval_image_dir)        
        if self.mode  == 'train':
            self.data = train_data_folder        elif self.mode  == 'eval':
            self.data = eval_data_folder    def __getitem__(self, index):
        """
        步骤三：实现__getitem__方法，定义指定index时如何获取数据，并返回单条数据（训练数据，对应的标签）
        """
        data = np.array(self.data[index][0]).astype('float32')

        data = self.transforms(data)

        label = np.array([self.data[index][1]]).astype('int64')        
        return data, label        
    def __len__(self):
        """
        步骤四：实现__len__方法，返回数据集总数目
        """
        return len(self.data)

from paddle.vision import transforms as T#数据增强transform_train =T.Compose([T.Resize((256,256)),
                            T.RandomHorizontalFlip(5),
                            T.RandomRotation(15),
                            T.Transpose(),
                            T.Normalize(mean=[0, 0, 0],                           # 像素值归一化
                                        std =[255, 255, 255]),                    # transforms.ToTensor(), # transpose操作 + (img / 255),并且数据结构变为PaddleTensor
                            T.Normalize(mean=[0.50950350, 0.54632660, 0.57409690],# 减均值 除标准差    
                                        std= [0.26059777, 0.26041326, 0.29220656])# 计算过程：output[channel] = (input[channel] - mean[channel]) / std[channel]
                            ])
transform_eval =T.Compose([ T.Resize((256,256)),
                            T.Transpose(),
                            T.Normalize(mean=[0, 0, 0],                           # 像素值归一化
                                        std =[255, 255, 255]),                    # transforms.ToTensor(), # transpose操作 + (img / 255),并且数据结构变为PaddleTensor
                            T.Normalize(mean=[0.50950350, 0.54632660, 0.57409690],# 减均值 除标准差    
                                        std= [0.26059777, 0.26041326, 0.29220656])# 计算过程：output[channel] = (input[channel] - mean[channel]) / std[channel]
                            ])

train_dataset = TowerDataset(mode='train',transforms=transform_train)
eval_dataset  = TowerDataset(mode='eval', transforms=transform_eval )#数据异步加载train_loader = paddle.io.DataLoader(train_dataset, 
                                    places=paddle.CUDAPlace(0), 
                                    batch_size=128, 
                                    shuffle=True,                                    #num_workers=2,
                                    #use_shared_memory=True
                                    )
eval_loader = paddle.io.DataLoader (eval_dataset, 
                                    places=paddle.CUDAPlace(0), 
                                    batch_size=128,                                    #num_workers=2,
                                    #use_shared_memory=True
                                    )

print('训练集样本量: {}，验证集样本量: {}'.format(len(train_loader), len(eval_loader)))

import paddlefrom paddle.vision.models import mobilenet_v2
network=paddle.vision.models.mobilenet_v2(pretrained=True,num_classes=9)
model=paddle.Model(network)

#优化器选择class SaveBestModel(paddle.callbacks.Callback):
    def __init__(self, target=0.5, path='work/best_model', verbose=0):
        self.target = target
        self.epoch = None
        self.path = path    def on_epoch_end(self, epoch, logs=None):
        self.epoch = epoch    def on_eval_end(self, logs=None):
        if logs.get('acc') > self.target:
            self.target = logs.get('acc')
            self.model.save(self.path)            print('best acc is {} at epoch {}'.format(self.target, self.epoch))

callback_visualdl = paddle.callbacks.VisualDL(log_dir='work/mushroom')
callback_savebestmodel = SaveBestModel(target=0.5, path='work/best_model')
callbacks = [callback_visualdl, callback_savebestmodel]

base_lr = config_parameters['lr']
epochs = config_parameters['epochs']def make_optimizer(parameters=None):
    momentum = 0.9

    learning_rate= paddle.optimizer.lr.CosineAnnealingDecay(learning_rate=base_lr, T_max=epochs, verbose=False)
    weight_decay=paddle.regularizer.L2Decay(0.01)
    optimizer = paddle.optimizer.Momentum(
        learning_rate=learning_rate,
        momentum=momentum,
        weight_decay=weight_decay,
        parameters=parameters)    return optimizer

optimizer = make_optimizer(model.parameters())

model.prepare(optimizer,
              paddle.nn.CrossEntropyLoss(),
              paddle.metric.Accuracy())

model.fit(train_loader,
          eval_loader,
          epochs=100,
          batch_size=128,   
          callbacks=callbacks, 
          verbose=1)   # 日志展示格式

model.save(get('model_save_dir'))