开放能力
开发平台
行业应用
生态合作
开发与教学
资讯 社区 控制台
技术能力
语音技术
图像技术
文字识别
人脸与人体识别
视频技术
AR与VR
自然语言处理
知识图谱
数据智能
场景方案
部署方案
行业应用
智能教育
智能医疗
智能零售
智能工业
企业服务
智能政务
智能农业
信息服务
智能园区
智能硬件
BML 全功能AI开发平台

    Pytorch 1.7.1代码规范

    Pytorch 1.7.1代码规范

    基于Pytorch 1.7.1框架的MNIST图像分类,训练数据集pytorch_train_data.zip点击这里下载。
    如下所示是其超参搜索任务中一个超参数组合的训练代码,代码会通过argparse模块接受在平台中填写的信息,请保持一致。
    特别注意,示例采用的是进化算法进行超参搜索,每个试验在训练时会继承之前试验的权重,resume_checkpoint_path是权重的保存路径,由搜索算法自身提供,与job_id及trial_id一样,只需要在argparse中提供对应参数即可。

    pytorch1.7.1_autosearch.py示例代码

    # -*- coding:utf-8 -*-
    """ pytorch train demo """
    import argparse
    import torch
    import torch.nn as nn
    import torch.nn.functional as F
    import torch.optim as optim
    import torch.utils.data as data
    from torchvision import transforms
    import codecs
    import errno
    import gzip
    import numpy as np
    import os
    import time
    from PIL import Image
    from rudder_autosearch.sdk.amaas_tools import AMaasTools
    
    def parse_arg():
        """parse arguments"""
        parser = argparse.ArgumentParser(description='PyTorch1.7.1 MNIST Example')
        parser.add_argument('--train_dir', type=str, default='./train_data',
                            help='input data dir for training (default: ./train_data)')
        parser.add_argument('--test_dir', type=str, default='./test_data',
                            help='input data dir for test (default: ./test_data)')
        parser.add_argument('--output_dir', type=str, default='./output',
                            help='output dir for auto_search job (default: ./output)')
        parser.add_argument('--job_id', type=str, default="job-1234",
                            help='auto_search job id (default: "job-1234")')
        parser.add_argument('--trial_id', type=str, default="0-0",
                            help='auto_search id of a single trial (default: "0-0")')
        parser.add_argument('--metric', type=str, default="acc",
                            help='evaluation metric of the model')
        parser.add_argument('--data_sampling_scale', type=float, default=1.0,
                            help='sampling ratio of the data (default: 1.0)')
        parser.add_argument('--batch_size', type=int, default=64,
                            help='number of images input in an iteration (default: 64)')
        parser.add_argument('--lr', type=float, default=0.01,
                            help='learning rate (default: 0.01)')
        parser.add_argument('--momentum', type=float, default=0.5,
                            help='SGD momentum (default: 0.5)')
        parser.add_argument('--no_cuda', action='store_true', default=False,
                            help='disables CUDA training')
        parser.add_argument('--log_interval', type=int, default=10,
                            help='how many batches to wait before logging training status')
        parser.add_argument('--perturb_interval', type=int, default=10,
                            help='number of epochs to train (default: 10)')
        parser.add_argument('--resume_checkpoint_path', type=str, default="",
                            help='inherit the initial weight of the previous trial')
        args = parser.parse_args()
        args.output_dir = os.path.join(args.output_dir, args.job_id, args.trial_id)
        if not os.path.exists(args.output_dir):
            os.makedirs(args.output_dir)
        args.cuda = not args.no_cuda and torch.cuda.is_available()
    
    
        print("job_id: {}, trial_id: {}".format(args.job_id, args.trial_id))
        return args
    
    # 定义MNIST数据集的dataset
    class MNIST(data.Dataset):
        """
        MNIST dataset
        """
        training_file = 'training.pt'
        test_file = 'test.pt'
        classes = ['0 - zero', '1 - one', '2 - two', '3 - three', '4 - four',
                   '5 - five', '6 - six', '7 - seven', '8 - eight', '9 - nine']
    
        def __init__(self, root, train=True, transform=None, target_transform=None, data_sampling_scale=1):
            self.root = os.path.expanduser(root)
            self.transform = transform
            self.target_transform = target_transform
            self.train = train  # training set or test set
            self.data_sampling_scale = data_sampling_scale
            self.preprocess(root, train, False)
            if self.train:
                data_file = self.training_file
            else:
                data_file = self.test_file
            self.data, self.targets = torch.load(os.path.join(self.processed_folder, data_file))
    
        def __getitem__(self, index):
            """
            Args:
                index (int): Index
            Returns:
                tuple: (image, target) where target is index of the target class.
            """
            img, target = self.data[index], int(self.targets[index])
            # doing this so that it is consistent with all other datasets
            # to return a PIL Image
            img = Image.fromarray(img.numpy(), mode='L')
            if self.transform is not None:
                img = self.transform(img)
            if self.target_transform is not None:
                target = self.target_transform(target)
    
            return img, target
    
        def __len__(self):
            return len(self.data)
    
        @property
        def raw_folder(self):
            """
            raw folder
            """
            return os.path.join('/tmp', 'raw')
    
        @property
        def processed_folder(self):
            """
            processed folder
            """
            return os.path.join('/tmp', 'processed')
    
        # data preprocessing
        def preprocess(self, train_dir, train, remove_finished=False):
            """
            preprocess
            """
            makedir_exist_ok(self.raw_folder)
            makedir_exist_ok(self.processed_folder)
            train_list = ['train-images-idx3-ubyte.gz', 'train-labels-idx1-ubyte.gz']
            test_list = ['t10k-images-idx3-ubyte.gz', 't10k-labels-idx1-ubyte.gz']
            zip_list = train_list if train else test_list
            for zip_file in zip_list:
                print('Extracting {}'.format(zip_file))
                zip_file_path = os.path.join(train_dir, zip_file)
                raw_folder_path = os.path.join(self.raw_folder, zip_file)
                with open(raw_folder_path.replace('.gz', ''), 'wb') as out_f, gzip.GzipFile(zip_file_path) as zip_f:
                    out_f.write(zip_f.read())
                if remove_finished:
                    os.unlink(zip_file_path)
            if train:
                x_train = read_image_file(os.path.join(self.raw_folder, 'train-images-idx3-ubyte'))
                y_train = read_label_file(os.path.join(self.raw_folder, 'train-labels-idx1-ubyte'))
                np.random.seed(0)
                sample_data_num = int(self.data_sampling_scale * len(x_train))
                idx = np.arange(len(x_train))
                np.random.shuffle(idx)
                x_train, y_train = x_train[0:sample_data_num], y_train[0:sample_data_num]
                training_set = (x_train, y_train)
                with open(os.path.join(self.processed_folder, self.training_file), 'wb') as f:
                    torch.save(training_set, f)
            else:
                test_set = (
                    read_image_file(os.path.join(self.raw_folder, 't10k-images-idx3-ubyte')),
                    read_label_file(os.path.join(self.raw_folder, 't10k-labels-idx1-ubyte'))
                )
                with open(os.path.join(self.processed_folder, self.test_file), 'wb') as f:
                    torch.save(test_set, f)
    
    def get_int(b):
        """
        get int
        """
        return int(codecs.encode(b, 'hex'), 16)
    
    def read_label_file(path):
        """
        read label file
        """
        with open(path, 'rb') as f:
            data = f.read()
            assert get_int(data[:4]) == 2049
            length = get_int(data[4:8])
            parsed = np.frombuffer(data, dtype=np.uint8, offset=8)
            return torch.from_numpy(parsed).view(length).long()
    
    def read_image_file(path):
        """
        read image file
        """
        with open(path, 'rb') as f:
            data = f.read()
            assert get_int(data[:4]) == 2051
            length = get_int(data[4:8])
            num_rows = get_int(data[8:12])
            num_cols = get_int(data[12:16])
            parsed = np.frombuffer(data, dtype=np.uint8, offset=16)
            return torch.from_numpy(parsed).view(length, num_rows, num_cols)
    
    def makedir_exist_ok(dirpath):
        """
        Python2 support for os.makedirs(.., exist_ok=True)
        """
        try:
            os.makedirs(dirpath)
        except OSError as e:
            if e.errno == errno.EEXIST:
                pass
            else:
                raise
    
    def load_data(args):
        """load_data"""
        # 若无测试集,训练集做验证集
        if not os.path.exists(args.test_dir) or not os.listdir(args.test_dir):
            args.test_dir = args.train_dir
        # 将数据进行转化,从PIL.Image/numpy.ndarray的数据进转化为torch.FloadTensor
        trans = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])
        train_set = MNIST(root=args.train_dir, train=True, transform=trans, data_sampling_scale=args.data_sampling_scale)
        test_set = MNIST(root=args.test_dir, train=False, transform=trans)
        # 定义data reader
        train_loader = torch.utils.data.DataLoader(
            dataset=train_set,
            batch_size=args.batch_size,
            shuffle=True)
        test_loader = torch.utils.data.DataLoader(
            dataset=test_set,
            batch_size=args.batch_size,
            shuffle=False)
        return train_loader, test_loader
    
    # 定义网络模型
    class Net(nn.Module):
        """
        Net
        """
        def __init__(self):
            super(Net, self).__init__()
            self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
            self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
            self.conv2_drop = nn.Dropout2d()
            self.fc1 = nn.Linear(320, 50)
            self.fc2 = nn.Linear(50, 10)
    
        def forward(self, x):
            """
            forward
            """
            x = F.relu(F.max_pool2d(self.conv1(x), 2))
            x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
            x = x.view(-1, 320)
            x = F.relu(self.fc1(x))
            x = F.dropout(x, training=self.training)
            x = self.fc2(x)
            return F.log_softmax(x)
    
    def load_state_dict(model, resume_checkpoint_path):
        """load_state_dict"""
        if resume_checkpoint_path:
            model.load_state_dict(torch.load(resume_checkpoint_path))
    
    def run_train(model, args, train_loader):
        """run_train"""
        if args.cuda:
            # Move model to GPU.
            model.cuda()
        # 选择优化器
        optimizer = optim.SGD(model.parameters(), lr=args.lr,
                              momentum=args.momentum)
        for epoch in range(1, args.perturb_interval + 1):
            train(model, args, train_loader, optimizer, epoch)
    
    def train(model, args, train_loader, optimizer, epoch):
        """
        train
        """
        model.train()
        for batch_idx, (data, target) in enumerate(train_loader):
            if args.cuda:
                data, target = data.cuda(), target.cuda()
            optimizer.zero_grad()
            output = model(data)  # 获取预测值
            loss = F.nll_loss(output, target)  # 计算loss
            loss.backward()
            optimizer.step()
            if batch_idx % args.log_interval == 0:
                print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                    epoch, batch_idx, len(train_loader),
                    100. * batch_idx / len(train_loader), loss.item()))
    
    def evaluate(model, args, test_loader):
        """evaluate"""
        model.eval()
        test_loss = 0.
        test_accuracy = 0.
        for data, target in test_loader:
            if args.cuda:
                data, target = data.cuda(), target.cuda()
            output = model(data)
            # sum up batch loss
            test_loss += F.nll_loss(output, target, size_average=False).item()
            # get the index of the max log-probability
            pred = output.data.max(1, keepdim=True)[1]
            test_accuracy += pred.eq(target.data.view_as(pred)).cpu().float().sum()
        test_loss /= len(test_loader) * args.batch_size
        test_accuracy /= len(test_loader) * args.batch_size
        print('\nTest set: Average loss: {:.4f}, Accuracy: {:.2f}%\n'.format(
            test_loss, 100. * test_accuracy))
        return float(test_accuracy)
    
    def save(model, output_dir):
        """
        save
        """
        if not os.path.exists(output_dir):
            os.makedirs(output_dir)
        # 保存模型
        torch.save(model.state_dict(), os.path.join(output_dir, 'model.pkl'))
    
    def report_final(args, metric):
        """report_final_result"""
        # 结果上报sdk
        amaas_tools = AMaasTools(args.job_id, args.trial_id)
        metric_dict = {args.metric: metric}
        checkpoint_path = os.path.join(args.output_dir, 'model.pkl')
        for i in range(3):
            flag, ret_msg = amaas_tools.report_final_result(metric=metric_dict,
                                                            export_model_path=args.output_dir,
                                                            checkpoint_path=checkpoint_path)
            print("End Report, metric:{}, ret_msg:{}".format(metric, ret_msg))
            if flag:
                break
            time.sleep(1)
        assert flag, "Report final result to manager failed! Please check whether manager'address or manager'status " \
                     "is ok! "
    
    def main():
        """main"""
        # 获取参数
        args = parse_arg()
        # 加载数据集
        train_loader, test_loader = load_data(args)
        # 模型定义
        model = Net()
        # 继承之前实验的模型参数
        load_state_dict(model, args.resume_checkpoint_path)
        # 模型训练
        run_train(model, args, train_loader)
        # 模型保存
        save(model, args.output_dir)
        # 模型评估
        acc = evaluate(model, args, test_loader)
        # 上报结果
        report_final(args, metric=acc)
    
    if __name__ == '__main__':
        main()

    示例代码对应的yaml配置如下,请保持格式一致

    pbt_search_demo.yml示例内容

    #搜索算法参数
    search_strategy:
      algo: PBT_SEARCH #搜索策略:进化算法
      params:
        population_num: 8 #种群个体数量 | [1,10] int类型
        round: 10 #迭代轮数  |[5,50] int类型
        perturb_interval: 10 # 扰动间隔  | [1,20] int类型
        quantile_frac: 0.5 #扰动比例  | (0,0.5] float类型
        explore_prob: 0.25 #扰动概率 | (0,0.5] float类型
    
    #单次训练时数据的采样比例,单位%
    data_sampling_scale: 100 #|(0,100] int类型
    
    #评价指标参数
    metrics:
      name: acc #评价指标 | 任意字符串 str类型
      goal: MAXIMIZE #最大值/最小值 | str类型   MAXIMIZE or MINIMIZE   必须为这两个之一(也即支持大写)
      expected_value: 100 #早停标准值,评价指标超过该值则结束整个超参搜索,单位% |无限制 int类型
    
    #搜索参数空间
    search_space:
      batch_size:
        htype: choice
        value: [64, 128, 256, 512]
      lr:
        htype: loguniform
        value: [0.0001, 0.1]
      momentum:
        htype: uniform
        value: [0.1, 0.9]

    pytorch_predict.py示例代码

    #!/usr/bin/env python
    # -*- coding: utf-8 -*-
    """
    @license: Copyright (c) 2019 Baidu.com, Inc. All Rights Reserved.
    @desc: 图像预测算法示例
    """
    import logging
    import torch
    import torch.nn as nn
    import torch.nn.functional as F
    import base64
    import json
    from PIL import Image
    from io import BytesIO
    from torchvision import datasets, models, transforms
    MODEL_FILE_NAME = 'model.pkl'  # 模型文件名称
    def get_image_transform():
        """获取图片处理的transform
        Args:
            data_type: string, type of data(train/test)
        Returns:
            torchvision.transforms.Compose
        """
        trans = transforms.Compose([transforms.Resize((28, 28)),
                                    transforms.ToTensor(),
                                    transforms.Normalize((0.5,), (1.0,))])
        return trans
    def model_fn(model_dir):
        """模型加载
        Args:
            model_dir: 模型路径,该目录存储的文件为在自动搜索作业中选择的输出路径下产出的文件
        Returns:
            加载好的模型对象
        """
        class Net(nn.Module):
            """Net"""
            def __init__(self):
                super(Net, self).__init__()
                self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
                self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
                self.conv2_drop = nn.Dropout2d()
                self.fc1 = nn.Linear(320, 50)
                self.fc2 = nn.Linear(50, 10)
            def forward(self, x):
                """
                forward
                """
                x = F.relu(F.max_pool2d(self.conv1(x), 2))
                x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
                x = x.view(-1, 320)
                x = F.relu(self.fc1(x))
                x = F.dropout(x, training=self.training)
                x = self.fc2(x)
                return F.log_softmax(x)
        model = Net()
        meta_info_path = "%s/%s" % (model_dir, MODEL_FILE_NAME)
        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
        model.load_state_dict(torch.load(meta_info_path, map_location=device))
        model.to(device)
        logging.info("device type: " + str(device))
        return model
    def input_fn(request):
        """对输入进行格式化,处理为预测需要的输入格式
        Args:
            request: api请求的json
        Returns:
            预测需要的输入数据,一般为tensor
        """
        instances = request['instances']
        transform_composes = get_image_transform()
        arr_tensor_data = []
        for instance in instances:
            decoded_data = base64.b64decode(instance['data'].encoding("utf8"))
            byte_stream = BytesIO(decoded_data)
            roiImg = Image.open(byte_stream)
            target_data = transform_composes(roiImg)
            arr_tensor_data.append(target_data)
        tensor_data = torch.stack(arr_tensor_data, dim=0)
        return tensor_data
    def output_fn(predict_result):
        """进行输出格式化
        Args:
            predict_result: 预测结果
        Returns:
            格式化后的预测结果,需能够json序列化以便接口返回
        """
        js_str = None
        if type(predict_result) == torch.Tensor:
            list_prediction = predict_result.detach().cpu().numpy().tolist()
            js_str = json.dumps(list_prediction)
        return js_str
    上一篇
    PaddlePaddle 2.1.1代码规范
    下一篇
    Sklearn 0.23.2代码规范