OpenI_Cloudbrain_Example/npu_mnist_example/train_epoch_upload.py

"""
示例选用的数据集是MnistDataset_mindspore.zip
数据集结构是：
 MnistDataset_mindspore.zip
  ├── test
  │   ├── t10k-images-idx3-ubyte
  │   └── t10k-labels-idx1-ubyte
  └── train
      ├── train-images-idx3-ubyte
      └── train-labels-idx1-ubyte 

模型文件夹结构是：
Mindspore_MNIST_Example_Model
├── checkpoint_lenet-1_1875.ckpt
      
使用注意事项：
1、在代码中加入args, unknown = parser.parse_known_args()，可忽略掉--ckpt_url参数报错等参数问题
2、用户需要调用c2net的python sdk包
"""

import os
import argparse
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 import load_checkpoint, load_param_into_net
from mindspore.train import Model
from mindspore.train.callback import Callback
#导入c2net包
from c2net.context import prepare, upload_output

class EnvToOpenIEpochEnd(Callback):
    """
    upload output to openi when epoch end
    """
    def epoch_end(self,run_context):
        upload_output() 


parser = argparse.ArgumentParser(description='MindSpore Lenet Example')
                   
parser.add_argument(
    '--device_target',
    type=str,
    default="Ascend",
    choices=['Ascend', 'CPU'],
    help='device where the code will be implemented (default: Ascend),if to use the CPU on the Qizhi platform:device_target=CPU')

parser.add_argument('--epoch_size',
                    type=int,
                    default=5,
                    help='Training epochs.')

if __name__ == "__main__":
    ###请在代码中加入args, unknown = parser.parse_known_args()，可忽略掉--ckpt_url参数报错等参数问题
    args, unknown = parser.parse_known_args()
    #初始化导入数据集和预训练模型到容器内
    c2net_context = prepare()
    #获取数据集路径
    MnistDataset_mindspore_path = c2net_context.dataset_path+"/"+"MnistDataset_mindspore"
    #获取预训练模型路径
    Mindspore_MNIST_Example_Model_path = c2net_context.pretrain_model_path+"/"+"Mindspore_MNIST_Example_Model"
    #获取输出路径
    output_path = c2net_context.output_path
  
    context.set_context(mode=context.GRAPH_MODE,device_target=args.device_target)
    #使用数据集的方式  
    ds_train = create_dataset(os.path.join(MnistDataset_mindspore_path, "train"),  cfg.batch_size)      
    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())
    load_param_into_net(network, load_checkpoint(os.path.join(Mindspore_MNIST_Example_Model_path, "checkpoint_lenet-1_1875.ckpt")))
    if args.device_target != "Ascend":
        model = Model(network,
                      net_loss,
                      net_opt,
                      metrics={"accuracy"})
    else:
        model = Model(network,
                      net_loss,
                      net_opt,
                      metrics={"accuracy"},
                      amp_level="O2")

    config_ck = CheckpointConfig(
        save_checkpoint_steps=cfg.save_checkpoint_steps,
        keep_checkpoint_max=cfg.keep_checkpoint_max)
    #将模型保存到c2net_context.output_path
    outputDirectory = output_path + "/"
    ckpoint_cb = ModelCheckpoint(prefix="checkpoint_lenet",
                                directory=outputDirectory,
                                config=config_ck)
    print("============== Starting Training ==============")
    epoch_size = cfg['epoch_size']
    if (args.epoch_size):
        epoch_size = args.epoch_size
        print('epoch_size is: ', epoch_size)

    # set callback functions
    callback =[time_cb,LossMonitor()]
    local_rank=int(os.getenv('RANK_ID'))
    #非必选，每个epoch结束后，都手动上传训练结果到启智平台，注意这样使用会占用很多内存，只有在部分特殊需要手动上传的任务才需要使用
    uploadOutput = EnvToOpenIEpochEnd()
    callback.append(uploadOutput) 
    # for data parallel, only save checkpoint on rank 0
    if local_rank==0 :
        callback.append(ckpoint_cb) 
    
    model.train(epoch_size,ds_train,callbacks=callback)