Mnist torch example (#1522)

* add mnist pytorch example, change links in readme for mnist example

README.md

@@ -70,8 +70,8 @@ The tool dispatches and runs trial jobs generated by tuning algorithms to search
         <ul>
         <li><b>Examples</b></li>
          <ul>
-           <li><a href="examples/trials/mnist-distributed-pytorch">MNIST-pytorch</li></a>
-           <li><a href="examples/trials/mnist-distributed">MNIST-tensorflow</li></a>
+           <li><a href="examples/trials/mnist-pytorch">MNIST-pytorch</li></a>
+           <li><a href="examples/trials/mnist">MNIST-tensorflow</li></a>
            <li><a href="examples/trials/mnist-keras">MNIST-keras</li></a>
            <li><a href="docs/en_US/TrialExample/GbdtExample.md">Auto-gbdt</a></li>
            <li><a href="docs/en_US/TrialExample/Cifar10Examples.md">Cifar10-pytorch</li></a>

examples/trials/mnist-pytorch/config.yml

+authorName: default
+experimentName: example_mnist_pytorch
+trialConcurrency: 1
+maxExecDuration: 1h
+maxTrialNum: 10
+#choice: local, remote, pai
+trainingServicePlatform: local
+searchSpacePath: search_space.json
+#choice: true, false
+useAnnotation: false
+tuner:
+  #choice: TPE, Random, Anneal, Evolution, BatchTuner, MetisTuner, GPTuner
+  #SMAC (SMAC should be installed through nnictl)
+  builtinTunerName: TPE
+  classArgs:
+    #choice: maximize, minimize
+    optimize_mode: maximize
+trial:
+  command: python3 mnist.py
+  codeDir: .
+  gpuNum: 0

examples/trials/mnist-pytorch/config_assessor.yml

+authorName: default
+experimentName: example_mnist_pytorch
+trialConcurrency: 1
+maxExecDuration: 1h
+maxTrialNum: 50
+#choice: local, remote
+trainingServicePlatform: local
+searchSpacePath: search_space.json
+#choice: true, false
+useAnnotation: false
+tuner:
+  #choice: TPE, Random, Anneal, Evolution, BatchTuner, MetisTuner, GPTuner
+  #SMAC (SMAC should be installed through nnictl)
+  builtinTunerName: TPE
+  classArgs:
+    #choice: maximize, minimize
+    optimize_mode: maximize
+assessor:
+  #choice: Medianstop, Curvefitting
+  builtinAssessorName: Curvefitting
+  classArgs:
+    #choice: maximize, minimize
+    optimize_mode: maximize
+    epoch_num: 20
+    threshold: 0.9
+trial:
+  command: python3 mnist.py
+  codeDir: .
+  gpuNum: 0

examples/trials/mnist-pytorch/config_frameworkcontroller.yml

+authorName: default
+experimentName: example_mnist_pytorch
+trialConcurrency: 1
+maxExecDuration: 1h
+maxTrialNum: 10
+#choice: local, remote, pai, kubeflow
+trainingServicePlatform: frameworkcontroller
+searchSpacePath: search_space.json
+#choice: true, false
+useAnnotation: false
+tuner:
+  #choice: TPE, Random, Anneal, Evolution, BatchTuner, MetisTuner, GPTuner
+  builtinTunerName: TPE
+  classArgs:
+    #choice: maximize, minimize
+    optimize_mode: maximize
+assessor:
+  builtinAssessorName: Medianstop
+  classArgs:
+    optimize_mode: maximize
+  gpuNum: 0
+trial:
+  codeDir: .
+  taskRoles:
+    - name: worker
+      taskNum: 1
+      command: python3 mnist.py
+      gpuNum: 1
+      cpuNum: 1
+      memoryMB: 8192
+      image: msranni/nni:latest
+      frameworkAttemptCompletionPolicy:
+        minFailedTaskCount: 1
+        minSucceededTaskCount: 1
+frameworkcontrollerConfig:
+  storage: nfs
+  nfs:
+    # Your NFS server IP, like 10.10.10.10
+    server: {your_nfs_server_ip}
+    # Your NFS server export path, like /var/nfs/nni
+    path: {your_nfs_server_export_path}
\ No newline at end of file

examples/trials/mnist-pytorch/config_kubeflow.yml

+authorName: default
+experimentName: example_dist_pytorch
+trialConcurrency: 1
+maxExecDuration: 1h
+maxTrialNum: 1
+#choice: local, remote, pai, kubeflow
+trainingServicePlatform: kubeflow
+searchSpacePath: search_space.json
+#choice: true, false
+useAnnotation: false
+tuner:
+  #choice: TPE, Random, Anneal, Evolution, BatchTuner, MetisTuner, GPTuner
+  builtinTunerName: TPE
+  classArgs:
+    #choice: maximize, minimize
+    optimize_mode: maximize
+trial:
+  codeDir: .
+  worker:
+    replicas: 1
+    command: python3 mnist.py
+    gpuNum: 0
+    cpuNum: 1
+    memoryMB: 8192
+    image: msranni/nni:latest
+kubeflowConfig:
+  operator: tf-operator
+  apiVersion: v1alpha2
+  storage: nfs
+  nfs:
+    server: 10.10.10.10
+    path: /var/nfs/general
\ No newline at end of file

examples/trials/mnist-pytorch/config_pai.yml

+authorName: default
+experimentName: example_mnist_pytorch
+trialConcurrency: 1
+maxExecDuration: 1h
+maxTrialNum: 10
+#choice: local, remote, pai
+trainingServicePlatform: pai
+searchSpacePath: search_space.json
+#choice: true, false
+useAnnotation: false
+tuner:
+  #choice: TPE, Random, Anneal, Evolution, BatchTuner, MetisTuner, GPTuner
+  #SMAC (SMAC should be installed through nnictl)
+  builtinTunerName: TPE
+  classArgs:
+    #choice: maximize, minimize
+    optimize_mode: maximize
+trial:
+  command: python3 mnist.py
+  codeDir: .
+  gpuNum: 0
+  cpuNum: 1
+  memoryMB: 8196
+  #The docker image to run nni job on pai
+  image: msranni/nni:latest
+paiConfig:
+  #The username to login pai
+  userName: username
+  #The password to login pai
+  passWord: password
+  #The host of restful server of pai
+  host: 10.10.10.10
\ No newline at end of file

examples/trials/mnist-pytorch/config_windows.yml

+authorName: default
+experimentName: example_mnist_pytorch
+trialConcurrency: 1
+maxExecDuration: 1h
+maxTrialNum: 10
+#choice: local, remote, pai
+trainingServicePlatform: local
+searchSpacePath: search_space.json
+#choice: true, false
+useAnnotation: false
+tuner:
+  #choice: TPE, Random, Anneal, Evolution, BatchTuner, MetisTuner, GPTuner
+  #SMAC (SMAC should be installed through nnictl)
+  builtinTunerName: TPE
+  classArgs:
+    #choice: maximize, minimize
+    optimize_mode: maximize
+trial:
+  command: python mnist.py
+  codeDir: .
+  gpuNum: 0

examples/trials/mnist-pytorch/mnist.py

+"""
+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 argparse
+import logging
+import nni
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import torch.optim as optim
+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):
+        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 {}
+    train_loader = torch.utils.data.DataLoader(
+        datasets.MNIST(args['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(args['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.')
+
+    test_acc = test(args, model, device, test_loader)
+    # 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='/tmp/tensorflow/mnist/input_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("--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.debug(tuner_params)
+        params = vars(get_params())
+        params.update(tuner_params)
+        main(params)
+    except Exception as exception:
+        logger.exception(exception)
+        raise

examples/trials/mnist-pytorch/requirements.txt

+torch
+torchvision

examples/trials/mnist-pytorch/search_space.json

+{
+    "batch_size": {"_type":"choice", "_value": [16, 32, 64, 128]},
+    "hidden_size":{"_type":"choice","_value":[128, 256, 512, 1024]},
+    "lr":{"_type":"choice","_value":[0.0001, 0.001, 0.01, 0.1]},
+    "momentum":{"_type":"uniform","_value":[0, 1]}
+}