Differences

This shows you the differences between two versions of the page.

--- tech:slurm [2020/04/29 09:17] – [Python] kohofer
+++ tech:slurm [2020/05/27 11:11] – [Example] kohofer
@@ Line 241: / Line 241: @@
   debug*       up   infinite      1   idle linux1
-If computer node is down
+If computer node is **<color #ed1c24>down</color>** or **<color #ed1c24>drain</color>**
 <code>
@@ Line 247: / Line 247: @@
 PARTITION AVAIL  TIMELIMIT  NODES  STATE NODELIST
 debug*       up   infinite      2   down gpu[02-03]
+sinfo
+PARTITION AVAIL  TIMELIMIT  NODES  STATE NODELIST
+gpu*         up   infinite      1  drain gpu02
+gpu*         up   infinite      1   down gpu03
 </code>
@@ Line 526: / Line 532: @@
 ...
 </code>
+===== Examples =====
+==== Example mnist ====
+An simple example to use nvidia GPU!
+The example consists of the following files:
+  * README.md
+  * requirements.txt
+  * main.job
+  * main.py
+Create a folder mnist and place the 4 files in there.
+  mkdir mnist
+cat README.md
+<code>
+# Basic MNIST Example
+```bash
+pip install -r requirements.txt
+python main.py
+# CUDA_VISIBLE_DEVICES=2 python main.py  # to specify GPU id to ex. 2
+```
+</code>
+  cat requirements.txt
+<code>
+torch
+torchvision
+</code>
+  cat main.job
+<code>
+#!/bin/bash
+#SBATCH --job-name=mnist
+#SBATCH --output=mnist.out
+#SBATCH --error=mnist.err
+#SBATCH --partition gpu
+#SBATCH --gres=gpu
+#SBATCH --mem-per-cpu=4gb
+#SBATCH --nodes 2
+#SBATCH --time=00:08:00
+#SBATCH --ntasks=10
+#SBATCH --mail-type=ALL
+#SBATCH --mail-user=<your-email@address.com>
+ml load miniconda3
+python3 main.py
+</code>
+{(xssnipper>,1, main.py slide,
+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
+from torch.optim.lr_scheduler import StepLR
+class Net(nn.Module):
+    def __init__(self):
+        super(Net, self).__init__()
+        self.conv1 = nn.Conv2d(1, 32, 3, 1)
+        self.conv2 = nn.Conv2d(32, 64, 3, 1)
+        self.dropout1 = nn.Dropout2d(0.25)
+        self.dropout2 = nn.Dropout2d(0.5)
+        self.fc1 = nn.Linear(9216, 128)
+        self.fc2 = nn.Linear(128, 10)
+    def forward(self, x):
+        x = self.conv1(x)
+        x = F.relu(x)
+        x = self.conv2(x)
+        x = F.max_pool2d(x, 2)
+        x = self.dropout1(x)
+        x = torch.flatten(x, 1)
+        x = self.fc1(x)
+        x = F.relu(x)
+        x = self.dropout2(x)
+        x = self.fc2(x)
+        output = F.log_softmax(x, dim=1)
+        return output
+def train(args, model, device, train_loader, optimizer, epoch):
+    model.train()
+    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)
+        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),
+. * 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)
+            test_loss += F.nll_loss(output, target, reduction='sum').item()  # sum up batch loss
+            pred = output.argmax(dim=1, keepdim=True)  # 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),
+. * 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=14, metavar='N',
+                        help='number of epochs to train (default: 14)')
+    parser.add_argument('--lr', type=float, default=1.0, metavar='LR',
+                        help='learning rate (default: 1.0)')
+    parser.add_argument('--gamma', type=float, default=0.7, metavar='M',
+                        help='Learning rate step gamma (default: 0.7)')
+    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')
+    parser.add_argument('--save-model', action='store_true', default=False,
+                        help='For Saving the current Model')
+    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")
+    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.Adadelta(model.parameters(), lr=args.lr)
+    scheduler = StepLR(optimizer, step_size=1, gamma=args.gamma)
+    for epoch in range(1, args.epochs + 1):
+        train(args, model, device, train_loader, optimizer, epoch)
+        test(args, model, device, test_loader)
+        scheduler.step()
+    if args.save_model:
+        torch.save(model.state_dict(), "mnist_cnn.pt")
+if __name__ == '__main__':
+    main()
+)}
 ===== Links =====
+https://www.admin-magazine.com/HPC/Articles/Warewulf-Cluster-Manager-Development-and-Run-Time/Warewulf-3-Code/MPICH2
+https://proteusmaster.urcf.drexel.edu/urcfwiki/index.php/Environment_Modules_Quick_Start_Guide
+https://en.wikipedia.org/wiki/Environment_Modules_(software)
 http://www.walkingrandomly.com/?p=5680
 https://modules.readthedocs.io/en/latest/index.html