基于 Jetson 在 kubeedge上 搭建 机器学习环境（docker/containerd）

1 2 3

sudo apt-get install python3-pip python3-dev -y sudo -H pip3 install jetson-stats sudo systemctl restart jtop.service

1 2 3 4

sudo apt update sudo apt install nvidia-jetpack sudo apt show nvidia-jetpack

1 2 3 4

sudo apt-get install -y nvidia-container-toolkit sudo nvidia-ctk runtime configure --runtime=containerd sudo systemctl restart containerd

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17

sudo apt-get update sudo apt-get install \ apt-transport-https \ ca-certificates \ curl \ gnupg \ lsb-release curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg echo \ "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/ubuntu \ $(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null sudo apt-get update sudo apt-get install docker-ce docker-ce-cli containerd.io

1 2 3 4 5 6 7 8 9 10

FROM nvcr.io/nvidia/l4t-base:r32.4.2 WORKDIR / RUN apt update && apt install -y --fix-missing make g++ python3-pip libhdf5-serial-dev hdf5-tools libhdf5-dev \ zlib1g-dev zip libjpeg8-dev liblapack-dev libblas-dev gfortran python3-h5py && \ pip3 install --no-cache-dir --upgrade pip && \ pip3 install --no-cache-dir --upgrade testresources setuptools cython && \ pip3 install --pre --no-cache-dir --extra-index-url https://developer.download.nvidia.com/compute/redist/jp/v44 tensorflow && \ apt-get clean CMD [ "bash" ]

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145

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.Dropout(0.25) self.dropout2 = nn.Dropout(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.relu(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), 100. * batch_idx / len(train_loader), loss.item())) if args.dry_run: break def test(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), 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=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('--no-mps', action='store_true', default=False, help='disables macOS GPU training') parser.add_argument('--dry-run', action='store_true', default=False, help='quickly check a single pass') 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() use_mps = not args.no_mps and torch.backends.mps.is_available() torch.manual_seed(args.seed) if use_cuda: device = torch.device("cuda") elif use_mps: device = torch.device("mps") else: device = torch.device("cpu") train_kwargs = {'batch_size': args.batch_size} test_kwargs = {'batch_size': args.test_batch_size} if use_cuda: cuda_kwargs = {'num_workers': 1, 'pin_memory': True, 'shuffle': True} train_kwargs.update(cuda_kwargs) test_kwargs.update(cuda_kwargs) transform=transforms.Compose([ transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,)) ]) dataset1 = datasets.MNIST('../data', train=True, download=True, transform=transform) dataset2 = datasets.MNIST('../data', train=False, transform=transform) train_loader = torch.utils.data.DataLoader(dataset1,**train_kwargs) test_loader = torch.utils.data.DataLoader(dataset2, **test_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(model, device, test_loader) scheduler.step() if args.save_model: torch.save(model.state_dict(), "mnist_cnn.pt") if __name__ == '__main__': main()

1 2 3

FROM nvcr.io/nvidia/l4t-pytorch:r35.2.1-pth2.0-py3 COPY pytorch-mnist.py /home/

1 2 3

sudo docker run -it --rm --runtime nvidia --network host -v /home/user/project:/location/in/container nvcr.io/nvidia/l4t-pytorch:r35.2.1-pth2.0-py3 python3 pytorch-minst.py

1 2 3

docker save nvcr.io/nvidia/l4t-pytorch:r35.2.1-pth2.0-py3 -o pytorch.tar ctr -n k8s.io images import pytorch.tar

1 2 3 4 5 6 7 8 9

ctr c create nvcr.io/nvidia/l4t-pytorch:r35.2.1-pth2.0-py3 gpu-demo ctr task start -d gpu-demo ctr task exec --exec-id 2 -t gpu-demo sh python3 pytorch-minst.py ctr tasks kill gpu-demo --signal SIGKILL

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16

apiVersion: v1 kind: Pod metadata: name: gpu-test spec: nodeSelector: kubernetes.io/hostname: edge1 containers: - image: docker.io/library/pytorch-mnist:latest imagePullPolicy: IfNotPresent name: gpu-test command: - "/bin/bash" - "-c" - "python3 /home/pytorch-mnist.py" restartPolicy: Never

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29

apiVersion: apps/v1 kind: Deployment metadata: name: gpu-test labels: app: gpu-test spec: replicas: 1 selector: matchLabels: app: gpu-test template: metadata: labels: app: gpu-test spec: containers: - name: gpu-test image: docker.io/library/pytorch-mnist:latest imagePullPolicy: IfNotPresent command: - "/bin/bash" - "-c" - "python3 /home/pytorch-mnist.py" strategy: type: RollingUpdate rollingUpdate: maxUnavailable: 25% maxSurge: 25%