Improving mnist example model (pytorch#658)

* Fix formatting to comply with PEP8

* reimplementing conv net from keras examples

* reimplementing keras example mnist_cnn in pytorch

* adding learning rate scheduling

* remove previous mnist model

* change softmax layer name

* changes after review

* fix command line arguments

* remove unused attributes

mnist/main.py

@@ -5,25 +5,32 @@
 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, 20, 5, 1)
-        self.conv2 = nn.Conv2d(20, 50, 5, 1)
-        self.fc1 = nn.Linear(4*4*50, 500)
-        self.fc2 = nn.Linear(500, 10)
+        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 = 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.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)
-        return F.log_softmax(x, dim=1)
+        output = F.log_softmax(x, dim=1)
+        return output
 
 
 def train(args, model, device, train_loader, optimizer, epoch):
@@ -67,12 +74,12 @@ def main():
                         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',
+    parser.add_argument('--epochs', type=int, default=14, 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('--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',
@@ -105,11 +112,13 @@ def main():
         batch_size=args.test_batch_size, shuffle=True, **kwargs)
 
     model = Net().to(device)
-    optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum)
+    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")