更新 'train.py'
This commit is contained in:
ychao_1983
parent
ec7c16f505
commit
864fce7e21
386
train.py
386
train.py
|
|
@ -1,193 +1,193 @@
|
|||
"""
|
||||
######################## single-dataset train lenet example ########################
|
||||
This example is a single-dataset training tutorial. If it is a multi-dataset, please refer to the multi-dataset training
|
||||
tutorial train_for_multidataset.py. This example cannot be used for multi-datasets!
|
||||
|
||||
######################## Instructions for using the training environment ########################
|
||||
The image of the debugging environment and the image of the training environment are two different images,
|
||||
and the working local directories are different. In the training task, you need to pay attention to the following points.
|
||||
1、(1)The structure of the dataset uploaded for single dataset training in this example
|
||||
MNISTData.zip
|
||||
├── test
|
||||
│ ├── t10k-images-idx3-ubyte
|
||||
│ └── t10k-labels-idx1-ubyte
|
||||
└── train
|
||||
├── train-images-idx3-ubyte
|
||||
└── train-labels-idx1-ubyte
|
||||
|
||||
(2)The dataset structure of the single dataset in the training image in this example
|
||||
workroot
|
||||
├── data
|
||||
| ├── test
|
||||
| └── train
|
||||
|
||||
2、Single dataset training requires predefined functions
|
||||
(1)Defines whether the task is a training environment or a debugging environment.
|
||||
def WorkEnvironment(environment):
|
||||
if environment == 'train':
|
||||
workroot = '/home/work/user-job-dir' #The training task uses this parameter to represent the local path of the training image
|
||||
elif environment == 'debug':
|
||||
workroot = '/home/ma-user/work' #The debug task uses this parameter to represent the local path of the debug image
|
||||
print('current work mode:' + environment + ', workroot:' + workroot)
|
||||
return workroot
|
||||
|
||||
(2)Copy single dataset from obs to training image.
|
||||
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)Copy the output model to obs.
|
||||
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、3 parameters need to be defined
|
||||
--data_url is the dataset you selected on the Qizhi platform
|
||||
|
||||
--data_url,--train_url,--device_target,These 3 parameters must be defined first in a single dataset task,
|
||||
otherwise an error will be reported.
|
||||
There is no need to add these parameters to the running parameters of the Qizhi platform,
|
||||
because they are predefined in the background, you only need to define them in your code.
|
||||
|
||||
4、How the dataset is used
|
||||
A single dataset uses data_url as the input, and data_dir (ie: workroot + '/data') as the calling method
|
||||
of the dataset in the image.
|
||||
For details, please refer to the following sample code.
|
||||
|
||||
"""
|
||||
|
||||
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
|
||||
|
||||
### Defines whether the task is a training environment or a debugging environment ###
|
||||
def WorkEnvironment(environment):
|
||||
if environment == 'train':
|
||||
workroot = '/home/work/user-job-dir'
|
||||
elif environment == 'debug':
|
||||
workroot = '/home/work'
|
||||
print('current work mode:' + environment + ', workroot:' + workroot)
|
||||
return workroot
|
||||
|
||||
### Copy single dataset from obs to training image###
|
||||
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
|
||||
### Copy the output model to obs###
|
||||
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
|
||||
|
||||
### --data_url,--train_url,--device_target,These 3 parameters must be defined first in a single dataset,
|
||||
### otherwise an error will be reported.
|
||||
###There is no need to add these parameters to the running parameters of the Qizhi platform,
|
||||
###because they are predefined in the background, you only need to define them in your code.
|
||||
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: 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__":
|
||||
args = parser.parse_args()
|
||||
### defining the training environment
|
||||
environment = 'train'
|
||||
workroot = WorkEnvironment(environment)
|
||||
|
||||
###Initialize the data and model directories in the training image###
|
||||
data_dir = workroot + '/data'
|
||||
train_dir = workroot + '/model'
|
||||
if not os.path.exists(data_dir):
|
||||
os.makedirs(data_dir)
|
||||
if not os.path.exists(train_dir):
|
||||
os.makedirs(train_dir)
|
||||
|
||||
### Copy the dataset from obs to the training image ###
|
||||
ObsToEnv(args.data_url,data_dir)
|
||||
|
||||
###Specifies the device CPU or Ascend NPU used for training###
|
||||
context.set_context(mode=context.GRAPH_MODE,
|
||||
device_target=args.device_target)
|
||||
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")
|
||||
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)
|
||||
ckpoint_cb = ModelCheckpoint(prefix="checkpoint_lenet",
|
||||
directory=train_dir,
|
||||
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)
|
||||
|
||||
model.train(epoch_size,
|
||||
ds_train,
|
||||
callbacks=[time_cb, ckpoint_cb,
|
||||
LossMonitor()])
|
||||
|
||||
###Copy the trained model data from the local running environment back to obs,
|
||||
###and download it in the training task corresponding to the Qizhi platform
|
||||
EnvToObs(train_dir, args.train_url)
|
||||
|
||||
"""
|
||||
######################## single-dataset train lenet example ########################
|
||||
This example is a single-dataset training tutorial. If it is a multi-dataset, please refer to the multi-dataset training
|
||||
tutorial train_for_multidataset.py. This example cannot be used for multi-datasets!
|
||||
|
||||
######################## Instructions for using the training environment ########################
|
||||
The image of the debugging environment and the image of the training environment are two different images,
|
||||
and the working local directories are different. In the training task, you need to pay attention to the following points.
|
||||
1、(1)The structure of the dataset uploaded for single dataset training in this example
|
||||
MNISTData.zip
|
||||
├── test
|
||||
│ ├── t10k-images-idx3-ubyte
|
||||
│ └── t10k-labels-idx1-ubyte
|
||||
└── train
|
||||
├── train-images-idx3-ubyte
|
||||
└── train-labels-idx1-ubyte
|
||||
|
||||
(2)The dataset structure of the single dataset in the training image in this example
|
||||
workroot
|
||||
├── data
|
||||
| ├── test
|
||||
| └── train
|
||||
|
||||
2、Single dataset training requires predefined functions
|
||||
(1)Defines whether the task is a training environment or a debugging environment.
|
||||
def WorkEnvironment(environment):
|
||||
if environment == 'train':
|
||||
workroot = '/home/work/user-job-dir' #The training task uses this parameter to represent the local path of the training image
|
||||
elif environment == 'debug':
|
||||
workroot = '/home/ma-user/work' #The debug task uses this parameter to represent the local path of the debug image
|
||||
print('current work mode:' + environment + ', workroot:' + workroot)
|
||||
return workroot
|
||||
|
||||
(2)Copy single dataset from obs to training image.
|
||||
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)Copy the output model to obs.
|
||||
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、3 parameters need to be defined
|
||||
--data_url is the dataset you selected on the Qizhi platform
|
||||
|
||||
--data_url,--train_url,--device_target,These 3 parameters must be defined first in a single dataset task,
|
||||
otherwise an error will be reported.
|
||||
There is no need to add these parameters to the running parameters of the Qizhi platform,
|
||||
because they are predefined in the background, you only need to define them in your code.
|
||||
|
||||
4、How the dataset is used
|
||||
A single dataset uses data_url as the input, and data_dir (ie: workroot + '/data') as the calling method
|
||||
of the dataset in the image.
|
||||
For details, please refer to the following sample code.
|
||||
|
||||
"""
|
||||
|
||||
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
|
||||
|
||||
### Defines whether the task is a training environment or a debugging environment ###
|
||||
def WorkEnvironment(environment):
|
||||
if environment == 'train':
|
||||
workroot = '/home/work/user-job-dir'
|
||||
elif environment == 'debug':
|
||||
workroot = '/home/work'
|
||||
print('current work mode:' + environment + ', workroot:' + workroot)
|
||||
return workroot
|
||||
|
||||
### Copy single dataset from obs to training image###
|
||||
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
|
||||
### Copy the output model to obs###
|
||||
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
|
||||
|
||||
### --data_url,--train_url,--device_target,These 3 parameters must be defined first in a single dataset,
|
||||
### otherwise an error will be reported.
|
||||
###There is no need to add these parameters to the running parameters of the Qizhi platform,
|
||||
###because they are predefined in the background, you only need to define them in your code.
|
||||
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: 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__":
|
||||
args, unknown = parser.parse_known_args()
|
||||
### defining the training environment
|
||||
environment = 'train'
|
||||
workroot = WorkEnvironment(environment)
|
||||
|
||||
###Initialize the data and model directories in the training image###
|
||||
data_dir = workroot + '/data'
|
||||
train_dir = workroot + '/model'
|
||||
if not os.path.exists(data_dir):
|
||||
os.makedirs(data_dir)
|
||||
if not os.path.exists(train_dir):
|
||||
os.makedirs(train_dir)
|
||||
|
||||
### Copy the dataset from obs to the training image ###
|
||||
ObsToEnv(args.data_url,data_dir)
|
||||
|
||||
###Specifies the device CPU or Ascend NPU used for training###
|
||||
context.set_context(mode=context.GRAPH_MODE,
|
||||
device_target=args.device_target)
|
||||
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")
|
||||
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)
|
||||
ckpoint_cb = ModelCheckpoint(prefix="checkpoint_lenet",
|
||||
directory=train_dir,
|
||||
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)
|
||||
|
||||
model.train(epoch_size,
|
||||
ds_train,
|
||||
callbacks=[time_cb, ckpoint_cb,
|
||||
LossMonitor()])
|
||||
|
||||
###Copy the trained model data from the local running environment back to obs,
|
||||
###and download it in the training task corresponding to the Qizhi platform
|
||||
EnvToObs(train_dir, args.train_url)
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue