Paddle.Hub 初探：快速基于预训练模型实现猫的 12 分类

# 同步 PaddleClas 代码!git clone https://gitee.com/PaddlePaddle/PaddleClas -b develop --depth 1

import paddle# 加载 Repo 中的模型列表model_list = paddle.hub.list('PaddleClas', source='local', force_reload=False)print(model_list)# 查看模型帮助文档model_help = paddle.hub.help('PaddleClas', 'mobilenetv3_large_x1_25', source='local', force_reload=False)print(model_help)# 加载模型model = paddle.hub.load('PaddleClas', 'mobilenetv3_large_x1_25', source='local', force_reload=False)# 模型测试data = paddle.rand((1, 3, 224, 224))
out = model(data)print(out.shape) # [1, 1000]

!unzip -q -d /home/aistudio/data/data10954 /home/aistudio/data/data10954/cat_12_train.zip!unzip -q -d /home/aistudio/data/data10954 /home/aistudio/data/data10954/cat_12_test.zip

import osimport paddleimport random

total = []# 读取数据标签with open('/home/aistudio/data/data10954/train_list.txt', 'r', encoding='UTF-8') as f:    for line in f:        # 格式转换
        line = line[:-1].split('\t')
        total.append(' '.join(line)+'\n')# 打乱数据顺序random.shuffle(total)'''
切分数据集
95%的数据作为训练集
5%的数据作为验证集
'''split_num = int(len(total)*0.95) 

# 写入训练数据列表with open('/home/aistudio/data/data10954/train.txt', 'w', encoding='UTF-8') as f:    for line in total[:split_num]:
        f.write(line)# 写入验证数据列表with open('/home/aistudio/data/data10954/dev.txt', 'w', encoding='UTF-8') as f:    for line in total[split_num:]:
        f.write(line)# 写入测试数据列表with open('/home/aistudio/data/data10954/test.txt', 'w', encoding='UTF-8') as f:    for line in ['cat_12_test/%s\n' % img for img in os.listdir('/home/aistudio/data/data10954/cat_12_test')]:
        f.write(line)

import osimport paddleimport randomimport paddle.nn as nnimport paddle.vision.transforms as T# 构建数据集class CatDataset(paddle.io.Dataset):
    def __init__(self, transforms, dataset_path='/home/aistudio/data/data10954', mode='train'):
        self.mode = mode
        self.dataset_path = dataset_path
        self.transforms = transforms
        self.num_classes = 5

        if self.mode == 'train':
            self.file = 'train.txt'
        elif self.mode == 'dev':
            self.file = 'dev.txt'
        else:
            self.file = 'test.txt'
        self.file = os.path.join(dataset_path, self.file)        with open(self.file, 'r') as file:
            self.data = file.read()[:-1].split('\n')    def __getitem__(self, idx):
        if self.mode in ['train', 'dev']:
            img_path, grt = self.data[idx].split(' ')
            img_path = os.path.join(self.dataset_path, img_path)
            im = paddle.vision.image_load(img_path)
            im = im.convert("RGB")
            im = self.transforms(im)            return im, int(grt)        else:
            img_path = self.data[idx]
            img_path = os.path.join(self.dataset_path, img_path)
            im = paddle.vision.image_load(img_path)
            im = im.convert("RGB")
            im = self.transforms(im)            return im    def __len__(self):
        return len(self.data)# 加载数据集train_transforms = T.Compose([
    T.Resize(256),
    T.RandomCrop(224),
    T.RandomHorizontalFlip(),
    T.RandomVerticalFlip(),
    T.ToTensor(),
    T.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
])

test_transforms = T.Compose([
    T.Resize(256),
    T.CenterCrop(224),
    T.ToTensor(),
    T.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
])

train_dataset = CatDataset(train_transforms, mode='train')
dev_dataset = CatDataset(test_transforms, mode='dev')
test_dataset = CatDataset(test_transforms, mode='test')# 加载模型model = paddle.hub.load('PaddleClas', 'mobilenetv3_large_x0_5', source='local', force_reload=False, class_dim=12, pretrained=True)
model = paddle.Model(model)# 定义优化器opt = paddle.optimizer.Adam(learning_rate=0.001, parameters=model.parameters())# 配置模型model.prepare(optimizer=opt, loss=nn.CrossEntropyLoss(), metrics=paddle.metric.Accuracy(topk=(1, 5)))

model.fit(
    train_data=train_dataset, 
    eval_data=dev_dataset, 
    batch_size=32, 
    epochs=2, 
    eval_freq=1, 
    log_freq=1, 
    save_dir='save_models', 
    save_freq=1, 
    verbose=1, 
    drop_last=False, 
    shuffle=True,
    num_workers=0)

import numpy as np# 模型预测results = model.predict(test_dataset, batch_size=32, num_workers=0, stack_outputs=True, callbacks=None)# 对预测结果进行后处理total = []for img, result in zip(test_dataset.data, np.argmax(results[0], 1)):
    total.append('%s,%s\n' % (img.split('/')[-1], result))# 生成结果文件with open('result.csv','w') as f:    for line in total:
        f.write(line)