Skip to content
Snippets Groups Projects
Commit c5d7a0a9 authored by Konstantin Julius Lotzgeselle's avatar Konstantin Julius Lotzgeselle :speech_balloon:
Browse files

Commit for merge

parent 9e70f019
No related branches found
No related tags found
No related merge requests found
Expand all Show whitespace changes
Inline Side-by-side
example.ipynb 0 → 100644
+ 0
− 0
View file @ c5d7a0a9
exploration.ipynb
+ 175
− 185
View file @ c5d7a0a9
This diff is collapsed.
mt_training.ipynb 0 → 100644
+ 207
− 0
View file @ c5d7a0a9
%% Cell type:code id: tags:
``` python
```
%% Cell type:code id: tags:
``` python
import os
import torch
import torch.optim as optim
def train(rank, args, model, device, dataset, dataloader_kwargs):
torch.manual_seed(args.seed + rank)
train_loader = torch.utils.data.DataLoader(dataset, **dataloader_kwargs)
optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum)
for epoch in range(1, args.epochs + 1):
train_epoch(epoch, args, model, device, train_loader, optimizer)
def test(args, model, device, dataset, dataloader_kwargs):
torch.manual_seed(args.seed)
test_loader = torch.utils.data.DataLoader(dataset, **dataloader_kwargs)
test_epoch(model, device, test_loader)
def train_epoch(epoch, args, model, device, data_loader, optimizer):
model.train()
pid = os.getpid()
for batch_idx, (data, target) in enumerate(data_loader):
optimizer.zero_grad()
output = model(data.to(device))
loss = F.nll_loss(output, target.to(device))
loss.backward()
optimizer.step()
if batch_idx % args.log_interval == 0:
print('{}\tTrain Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
pid, epoch, batch_idx * len(data), len(data_loader.dataset),
100. * batch_idx / len(data_loader), loss.item()))
if args.dry_run:
break
def test_epoch(model, device, data_loader):
model.eval()
test_loss = 0
correct = 0
with torch.no_grad():
for data, target in data_loader:
output = model(data.to(device))
test_loss += F.nll_loss(output, target.to(device), reduction='sum').item() # sum up batch loss
pred = output.max(1)[1] # get the index of the max log-probability
correct += pred.eq(target.to(device)).sum().item()
test_loss /= len(data_loader.dataset)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(data_loader.dataset),
100. * correct / len(data_loader.dataset)))
```
%% Cell type:code id: tags:
``` python
from __future__ import print_function
import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.multiprocessing as mp
from torch.utils.data.sampler import Sampler
# Training settings
parser = argparse.ArgumentParser(description='Yes, I can copy-paste')
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('--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')
parser.add_argument('--num-processes', type=int, default=2, metavar='N',
help='how many training processes to use (default: 2)')
parser.add_argument('--cuda', action='store_true', default=False,
help='enables CUDA training')
parser.add_argument('--mps', action='store_true', default=False,
help='enables macOS GPU training')
parser.add_argument('--save_model', action='store_true', default=False,
help='save the trained model to state_dict')
parser.add_argument('--dry-run', action='store_true', default=False,
help='quickly check a single pass')
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)
if __name__ == '__main__':
args = parser.parse_args()
use_cuda = args.cuda and torch.cuda.is_available()
use_mps = args.mps and torch.backends.mps.is_available()
if use_cuda:
device = torch.device("cuda")
elif use_mps:
device = torch.device("mps")
else:
device = torch.device("cpu")
kwargs = {'batch_size': args.batch_size,
'shuffle': True}
if use_cuda:
kwargs.update({'num_workers': 1,
'pin_memory': True,
})
torch.manual_seed(args.seed)
mp.set_start_method('spawn', force=True)
model = Net().to(device)
model.share_memory() # gradients are allocated lazily, so they are not shared here
processes = []
for rank in range(args.num_processes):
p = mp.Process(target=train, args=(rank, args, model, device,
dataset1, kwargs))
# We first train the model across `num_processes` processes
p.start()
processes.append(p)
for p in processes:
p.join()
if args.save_model:
torch.save(model.state_dict(), "MNIST_hogwild.pt")
# Once training is complete, we can test the model
test(args, model, device, dataset2, kwargs)
```
%% Output
---------------------------------------------------------------------------
ModuleNotFoundError Traceback (most recent call last)
Cell In[11], line 8
6 import torch.multiprocessing as mp
7 from torch.utils.data.sampler import Sampler
----> 8 from torchvision import datasets, transforms
10 from train import train, test
12 # Training settings
ModuleNotFoundError: No module named 'torchvision'
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment