|
- """
- 本示例是单数据集训练的教程,如果是多数据集,请参考多数据集训练教程train_for_multidataset.py,本示例不能用于多数据集!
- ######################## train lenet example ########################
- train lenet and get network model files(.ckpt)
- """
- """
- ######################## 训练环境使用说明 ########################
- 调试环境的镜像和训练环境的镜像是两个不同的镜像,工作的本地目录不同,注意区别!:
- 1、(1)本示例中单数据集训练上传的数据集结构
- MNISTData.zip
- ├── test
- │ ├── t10k-images-idx3-ubyte
- │ └── t10k-labels-idx1-ubyte
- └── train
- ├── train-images-idx3-ubyte
- └── train-labels-idx1-ubyte
-
- (2)本示例中单数据集在训练镜像中的数据集结构
- workroot
- ├── data
- | ├── test
- | └── train
-
- 2、单数据集训练需要预定义的函数
-
- ### (1)定义任务是训练环境还是调试环境(可参考的写法)###
- def WorkEnvironment(environment):
- if environment == 'train':
- workroot = '/home/work/user-job-dir' # 训练任务使用该参数,表示训练镜像本地路径
- elif environment == 'debug':
- workroot = '/home/ma-user/work' #调试任务使用该参数,表示调试镜像本地路径
- print('current work mode:' + environment + ', workroot:' + workroot)
- return workroot
-
- ### (2)将单数据集从obs拷贝到训练镜像中 (可参考的写法)###
- def ObsToEnv(obs_data_url, data_dir):
- try:
- mox.file.copy_parallel(obs_data_url, data_dir)
- print("Successfully Download {} to {}".format(obs_data_url, data_dir))
- except Exception as e:
- print('moxing download {} to {} failed: '.format(obs_data_url, data_dir) + str(e))
- return
- ### (3)将输出的模型拷贝到obs(可参考的写法)###
- def EnvToObs(train_dir, obs_train_url):
- try:
- mox.file.copy_parallel(train_dir, obs_train_url)
- print("Successfully Upload {} to {}".format(train_dir,obs_train_url))
- except Exception as e:
- print('moxing upload {} to {} failed: '.format(train_dir,obs_train_url) + str(e))
- return
-
- 3、需要定义3个参数
- define 3 parameters for running on modelArts;
- --data_url,--train_url,--device_target,这3个参数在单数据集中是必须先定义的,缺一不可,否则会报错
-
- 4、数据集的使用方式
- 单数据集使用data_url作为输入,data_dir(即workroot + '/data')作为镜像中数据集的调用方式,具体请参考以下示例代码
-
- """
-
- import os
- import argparse
- import moxing as mox
- from config import mnist_cfg as cfg
- from dataset import create_dataset
- from lenet import LeNet5
- import mindspore.nn as nn
- from mindspore import context
- from mindspore.train.callback import ModelCheckpoint, CheckpointConfig, LossMonitor, TimeMonitor
- from mindspore.train import Model
- from mindspore.nn.metrics import Accuracy
- from mindspore.common import set_seed
-
- ######################## 定义任务是训练环境还是调试环境(固定写法)########################
- def WorkEnvironment(environment):
- if environment == 'train':
- workroot = '/home/work/user-job-dir' # 训练任务使用该参数,表示本地路径
- elif environment == 'debug':
- workroot = '/home/work' #调试任务使用该参数,表示本地路径
- print('current work mode:' + environment + ', workroot:' + workroot)
- return workroot
-
- ######################## 将多个数据集从obs拷贝到训练镜像中 (固定写法)########################
- def ObsToEnv(obs_data_url, data_dir):
- try:
- mox.file.copy_parallel(obs_data_url, data_dir)
- print("Successfully Download {} to {}".format(obs_data_url, data_dir))
- except Exception as e:
- print('moxing download {} to {} failed: '.format(obs_data_url, data_dir) + str(e))
- return
- ######################## 将输出的模型拷贝到obs(固定写法)########################
- def EnvToObs(train_dir, obs_train_url):
- try:
- mox.file.copy_parallel(train_dir, obs_train_url)
- print("Successfully Upload {} to {}".format(train_dir,obs_train_url))
- except Exception as e:
- print('moxing upload {} to {} failed: '.format(train_dir,obs_train_url) + str(e))
- return
-
- # define 3 parameters for running on modelArts;--data_url,--train_url,--device_target
- # 这3个参数在单数据集中是必须先定义的,缺一不可,否则会报错
- # data_url,train_url,device_target是固定用于在modelarts上训练的参数,表示数据集的路径和输出模型的路径,使用npu
- parser = argparse.ArgumentParser(description='MindSpore Lenet Example')
- parser.add_argument('--data_url',
- help='path to training/inference dataset folder',
- default= WorkEnvironment('train') + '/data/')
-
- parser.add_argument('--train_url',
- help='model folder to save/load',
- default= WorkEnvironment('train') + '/model/')
-
- parser.add_argument(
- '--device_target',
- type=str,
- default="Ascend",
- choices=['Ascend', 'CPU'],
- help='device where the code will be implemented (default: CPU),若要在启智平台上使用NPU,需要在启智平台训练界面上加上运行参数device_target=Ascend')
-
- #modelarts已经默认使用data_url和train_url
- parser.add_argument('--epoch_size',
- type=int,
- default=5,
- help='Training epochs.')
-
- if __name__ == "__main__":
- args = parser.parse_args()
- environment = 'train'
- workroot = WorkEnvironment(environment)
-
- #初始化数据和模型存放目录
- data_dir = workroot + '/data' #先在训练镜像中定义数据集路径
- train_dir = workroot + '/model' #先在训练镜像中定义输出路径
- if not os.path.exists(data_dir):
- os.makedirs(data_dir)
- if not os.path.exists(train_dir):
- os.makedirs(train_dir)
- ######################## 将数据集从obs拷贝到训练镜像中 (固定写法)########################
- # 在训练环境中定义data_url和train_url,并把数据从obs拷贝到相应的固定路径,以下写法是将数据拷贝到/home/work/user-job-dir/data/目录下,可修改为其他目录
- ObsToEnv(args.data_url,data_dir)
-
- #指定了训练所用的设备CPU还是Ascend NPU
- context.set_context(mode=context.GRAPH_MODE,
- device_target=args.device_target)
- #创建数据集
- ds_train = create_dataset(os.path.join(data_dir, "train"),
- cfg.batch_size)
- if ds_train.get_dataset_size() == 0:
- raise ValueError(
- "Please check dataset size > 0 and batch_size <= dataset size")
- #创建网络
- network = LeNet5(cfg.num_classes)
- net_loss = nn.SoftmaxCrossEntropyWithLogits(sparse=True, reduction="mean")
- net_opt = nn.Momentum(network.trainable_params(), cfg.lr, cfg.momentum)
- time_cb = TimeMonitor(data_size=ds_train.get_dataset_size())
-
- if args.device_target != "Ascend":
- model = Model(network,
- net_loss,
- net_opt,
- metrics={"accuracy": Accuracy()})
- else:
- model = Model(network,
- net_loss,
- net_opt,
- metrics={"accuracy": Accuracy()},
- amp_level="O2")
-
- config_ck = CheckpointConfig(
- save_checkpoint_steps=cfg.save_checkpoint_steps,
- keep_checkpoint_max=cfg.keep_checkpoint_max)
- #定义模型输出路径
- ckpoint_cb = ModelCheckpoint(prefix="checkpoint_lenet",
- directory=train_dir,
- config=config_ck)
- #开始训练
- print("============== Starting Training ==============")
- epoch_size = cfg['epoch_size']
- if (args.epoch_size):
- epoch_size = args.epoch_size
- print('epoch_size is: ', epoch_size)
-
- model.train(epoch_size,
- ds_train,
- callbacks=[time_cb, ckpoint_cb,
- LossMonitor()])
-
- #把训练后的模型数据从本地的运行环境拷贝回obs,在启智平台相对应的训练任务中会提供下载
- EnvToObs(train_dir, args.train_url)
-
|