Skip to content

Instantly share code, notes, and snippets.

@georgepar
Last active May 30, 2019 14:34
Show Gist options
  • Save georgepar/1468fe613537f527b96086c8512afaa6 to your computer and use it in GitHub Desktop.
Save georgepar/1468fe613537f527b96086c8512afaa6 to your computer and use it in GitHub Desktop.
import mlflow
import mlflow.pytorch
class MlFlowLogger(object):
def __init__(self,
uri=None,
experiment_name=None,
model_path='models',
**params):
self.params = params
self.experiment_name = experiment_name
self.run = None
self.uri = uri
self.model_path = model_path
self.start()
def get_or_set_experiment(self):
print(mlflow.get_tracking_uri())
if self.experiment_name is None:
return
try:
mlflow.create_experiment(self.experiment_name)
except Exception:
print('Experiment {} already exists'
.format(self.experiment_name))
mlflow.set_experiment(self.experiment_name)
@staticmethod
def log_param(k, v):
mlflow.log_param(k, v)
def log_params(self, params=None):
if params is None:
params = self.params
for k, v in params.items():
self.log_param(k, v)
@staticmethod
def log_metric(k, v):
mlflow.log_metric(k, v)
def log_metrics(self, metrics):
for k, v in metrics.items():
self.log_metric(k, v)
def log_model(self, model):
""" for local saving of models """
mlflow.pytorch.save_model(model, self.model_path)
def start(self):
mlflow.set_tracking_uri(self.uri)
self.get_or_set_experiment()
self.run = mlflow.start_run()
self.log_params()
def end(self):
mlflow.end_run()
from __future__ import print_function
import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
import time
from mlflow_logger import MlFlowLogger
class Net(nn.Module):
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):
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, dim=1)
def train(args, model, device, train_loader, optimizer, epoch):
model.train()
running_loss = 0
total = 0
for batch_idx, (data, target) in enumerate(train_loader):
data, target = data.to(device), target.to(device)
optimizer.zero_grad()
output = model(data)
loss = F.nll_loss(output, target)
running_loss += loss.item()
total += 1
loss.backward()
optimizer.step()
if batch_idx % args.log_interval == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.item()))
avg_loss = float(running_loss) / total
return avg_loss
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)
test_loss += F.nll_loss(output, target, reduction='sum').item() # sum up batch loss
pred = output.max(1, keepdim=True)[1] # get the index of the max log-probability
correct += pred.eq(target.view_as(pred)).sum().item()
test_loss /= len(test_loader.dataset)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
return {'val_loss': test_loss, 'val_accuracy': 100. * correct / len(test_loader.dataset)}
def main():
# Training settings
parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
parser.add_argument('--batch-size', type=int, default=64, metavar='N',
help='input batch size for training (default: 64)')
parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',
help='input batch size for testing (default: 1000)')
parser.add_argument('--epochs', type=int, default=10, metavar='N',
help='number of epochs to train (default: 10)')
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('--no-cuda', action='store_true', default=False,
help='disables CUDA training')
parser.add_argument('--seed', type=int, default=1, metavar='S',
help='random seed (default: 1)')
parser.add_argument('--log-interval', type=int, default=10, metavar='N',
help='how many batches to wait before logging training status')
args = parser.parse_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")
config = vars(args)
import pprint
print('Running with configuration:')
pprint.pprint(config)
logger = MlFlowLogger(experiment_name='mnist', **config)
kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {}
train_loader = torch.utils.data.DataLoader(
datasets.MNIST('../data', 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', train=False, transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args.test_batch_size, shuffle=True, **kwargs)
model = Net().to(device)
optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum)
st1 = time.time()
final_accuracy = 0
for epoch in range(1, args.epochs + 1):
st = time.time()
train_loss = train(args, model, device, train_loader, optimizer, epoch)
et = time.time()
train_seconds = et - st
logger.log_metric('train_loss', train_loss)
logger.log_metric('train_seconds', train_seconds)
st = time.time()
val_metrics = test(args, model, device, test_loader)
logger.log_metrics(val_metrics)
et = time.time()
val_seconds = et - st
logger.log_metric('val_seconds', val_seconds)
final_accuracy = val_metrics['val_accuracy']
total_time = time.time() - st1
logger.log_metric('total_time', total_time)
logger.log_metric('final_accuracy', final_accuracy)
if __name__ == '__main__':
main()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment