1. 首先创建一个search—space 的json文件
like this
{
"batch_size": {"_type":"choice", "_value": [2000,5000,10000]},
"hidden_size1_lstm":{"_type":"choice","_value":[32, 64, 128]},
"hidden_size2_lstm":{"_type":"choice","_value":[32, 64, 128]},
"number_layer":{"_type":"choice","_value":[2,4,8]},
"seed":{"_type":"choice","_value":[1,2020,909305]},
"lr":{"_type":"choice","_value":[0.0001, 0.001, 0.01, 0.1]},
"bi":{"_type":"choice","_value":[1, 0]}
}
2.编写yml配置文件
like this
注释有详细解释
authorName: default
experimentName: PyTorch PAK_ETA Model
trialConcurrency: 1
maxExecDuration: 3h #最大执行时间
maxTrialNum: 10 #尝试的最多组合数
#choice: local, remote, pai
trainingServicePlatform: local
searchSpacePath: search_space.json ##指明space位置!!!
#choice: true, false
useAnnotation: false
tuner:
#choice: TPE, Random, Anneal, Evolution, BatchTuner, MetisTuner, GPTuner
#SMAC (SMAC should be installed through nnictl)
builtinTunerName: TPE ##选择参数的方式
classArgs:
#choice: maximize, minimize
optimize_mode: minimize ##根据损失函数返回结果 mse之类的loss越小越好,acc越大越好
trial:
command: python3 PAK.py #指明位置
codeDir: .
gpuNum: 0
在python文件中构建参数,只需要三个主要函数,同时最好学会args的使用
"""
A deep MNIST classifier using convolutional layers.
This file is a modification of the official pytorch mnist example:
https://github.com/pytorch/examples/blob/master/mnist/main.py
"""
import os
import argparse
import logging
import nni
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from nni.utils import merge_parameter
from torchvision import datasets, transforms
logger = logging.getLogger('mnist_AutoML')
class Net(nn.Module):
def __init__(self, hidden_size):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 20, 5, 1)
self.conv2 = nn.Conv2d(20, 50, 5, 1)
self.fc1 = nn.Linear(4*4*50, hidden_size)
self.fc2 = nn.Linear(hidden_size, 10)
def forward(self, x):
x = F.relu(self.conv1(x))
x = F.max_pool2d(x, 2, 2)
x = F.relu(self.conv2(x))
x = F.max_pool2d(x, 2, 2)
x = x.view(-1, 4*4*50)
x = F.relu(self.fc1(x))
x = self.fc2(x)
return F.log_softmax(x, dim=1)
def train(args, model, device, train_loader, optimizer, epoch):
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
if (args['batch_num'] is not None) and batch_idx >= args['batch_num']:
break
data, target = data.to(device), target.to(device)
optimizer.zero_grad()
output = model(data)
loss = F.nll_loss(output, target)
loss.backward()
optimizer.step()
if batch_idx % args['log_interval'] == 0:
logger.info('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.item()))
def test(args, model, device, test_loader):
model.eval()
test_loss = 0
correct = 0
with torch.no_grad():
for data, target in test_loader:
data, target = data.to(device), target.to(device)
output = model(data)
# sum up batch loss
test_loss += F.nll_loss(output, target, reduction='sum').item()
# get the index of the max log-probability
pred = output.argmax(dim=1, keepdim=True)
correct += pred.eq(target.view_as(pred)).sum().item()
test_loss /= len(test_loader.dataset)
accuracy = 100. * correct / len(test_loader.dataset)
logger.info('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_loader.dataset), accuracy))
return accuracy
def main(args):
use_cuda = not args['no_cuda'] and torch.cuda.is_available()
torch.manual_seed(args['seed'])
device = torch.device("cuda" if use_cuda else "cpu")
kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {}
data_dir = args['data_dir']
train_loader = torch.utils.data.DataLoader(
datasets.MNIST(data_dir, train=True, download=True,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args['batch_size'], shuffle=True, **kwargs)
test_loader = torch.utils.data.DataLoader(
datasets.MNIST(data_dir, train=False, transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=1000, shuffle=True, **kwargs)
hidden_size = args['hidden_size']
model = Net(hidden_size=hidden_size).to(device)
optimizer = optim.SGD(model.parameters(), lr=args['lr'],
momentum=args['momentum'])
for epoch in range(1, args['epochs'] + 1):
train(args, model, device, train_loader, optimizer, epoch)
test_acc = test(args, model, device, test_loader)
# report intermediate result
nni.report_intermediate_result(test_acc)
logger.debug('test accuracy %g', test_acc)
logger.debug('Pipe send intermediate result done.')
# report final result
nni.report_final_result(test_acc)
logger.debug('Final result is %g', test_acc)
logger.debug('Send final result done.')
def get_params():
# Training settings
parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
parser.add_argument("--data_dir", type=str,
default='./data', help="data directory")
parser.add_argument('--batch_size', type=int, default=64, metavar='N',
help='input batch size for training (default: 64)')
parser.add_argument("--batch_num", type=int, default=None)
parser.add_argument("--hidden_size", type=int, default=512, metavar='N',
help='hidden layer size (default: 512)')
parser.add_argument('--lr', type=float, default=0.01, metavar='LR',
help='learning rate (default: 0.01)')
parser.add_argument('--momentum', type=float, default=0.5, metavar='M',
help='SGD momentum (default: 0.5)')
parser.add_argument('--epochs', type=int, default=10, metavar='N',
help='number of epochs to train (default: 10)')
parser.add_argument('--seed', type=int, default=1, metavar='S',
help='random seed (default: 1)')
parser.add_argument('--no_cuda', action='store_true', default=False,
help='disables CUDA training')
parser.add_argument('--log_interval', type=int, default=1000, metavar='N',
help='how many batches to wait before logging training status')
args, _ = parser.parse_known_args()
return args
if __name__ == '__main__':
try:
# get parameters form tuner
tuner_params = nni.get_next_parameter()
logger.(tuner_params)
params = vars(merge_parameter(get_params(), tuner_params))
print(params)
main(params)
except Exception as exception:
logger.exception(exception)
raise
4.最后一步,启动!!!
nnictl create --config config.yml --port 1825
(端口号自己定义)
其他操作:
You can use these commands to get more information about the experiment
commands description
- nnictl experiment show -----> show the information of experiments
- nnictl trial ls ----> list all of trial jobs
- nnictl top ----> monitor the status of running experiments
- nnictl log stderr ----> show stderr log content
- nnictl log stdout —> show stdout log content
- nnictl stop ----> stop an experiment
- nnictl trial kill ----> kill a trial job by id
- nnictl --help ----> get help information about nnictl
(记得先装好nni ~~捂脸)
哒哒哒: