Example of MNIST using RNN (pytorch#752)

* Example of MNIST using RNN

* Example of MNIST using RNN: Changed RNN type to LSTM and changed variable names

* Example of MNIST using RNN: Resolving review comments

* Example of MNIST using RNN: Removing unintentional new line

mnist_rnn/README.md

@@ -0,0 +1,10 @@
+# Example of MNIST using RNN
+
+## Motivation
+Create pytorch example similar to Official Tensorflow Keras RNN example using MNIST [here](https://www.tensorflow.org/guide/keras/rnn) 
+
+```bash
+pip install -r requirements.txt
+python main.py
+# CUDA_VISIBLE_DEVICES=2 python main.py  # to specify GPU id to ex. 2
+```

mnist_rnn/main.py

@@ -0,0 +1,132 @@
+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.rnn = nn.LSTM(input_size=28, hidden_size=64, batch_first=True)
+        self.batchnorm = nn.BatchNorm1d(64)
+        self.dropout1 = nn.Dropout2d(0.25)
+        self.dropout2 = nn.Dropout2d(0.5)
+        self.fc1 = nn.Linear(64, 32)
+        self.fc2 = nn.Linear(32, 10)
+
+    def forward(self, input):
+        # Shape of input is (batch_size,1, 28, 28)
+        # converting shape of input to (batch_size, 28, 28)
+        # as required by RNN when batch_first is set True
+        input = input.reshape(-1, 28, 28)
+        output, hidden = self.rnn(input)
+
+        # RNN output shape is (seq_len, batch, input_size)
+        # Get last output of RNN
+        output = output[:, -1, :]
+        output = self.batchnorm(output)
+        output = self.dropout1(output)
+        output = self.fc1(output)
+        output = F.relu(output)
+        output = self.dropout2(output)
+        output = self.fc2(output)
+        output = F.log_softmax(output, 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()))
+
+
+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 using RNN')
+    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=0.1, metavar='LR',
+                        help='learning rate (default: 0.1)')
+    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(model, device, test_loader)
+        scheduler.step()
+
+    if args.save_model:
+        torch.save(model.state_dict(), "mnist_rnn.pt")
+
+
+if __name__ == '__main__':
+    main()

mnist_rnn/requirements.txt

@@ -0,0 +1,2 @@
+torch
+torchvision