finish chapter 13

11_01_softmax.py

@@ -14,4 +14,9 @@ print('softmax numpy:', outputs)
 x = torch.tensor([2., 1., .1])
 outputs = torch.softmax(x, dim=0)
 print('inputs: ', x)
-print('softmax numpy:', outputs)
+print('softmax numpy:', outputs)
+
+outputs2 = torch.softmax(outputs, dim=0)
+print('inputs: ', outputs)
+print('softmax numpy:', outputs2)
+

13_feedforward.py

@@ -0,0 +1,105 @@
+'''
+put the last few chapters together to classify digits from MNIST dataset
+-> MNIST
+-> DataLoader, Transformation
+-> Loss + Optimizer
+-> Training Loop with batch training
+-> Model Evaluation
+-> GPU Support
+'''
+
+import torch
+import torch.nn as nn
+import torchvision
+import torchvision.transforms as transforms
+import matplotlib.pyplot as plt
+
+# device config
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+print(f'Device is {device}')
+
+# hyper parameters
+input_size = 784 # 28x28 pixel images
+hidden_size = 100 # PLAY WITH THIS
+num_classes = 10 # digits 0..9
+num_epochs = 2 # PLAY WITH THIS
+batch_size = 100
+learning_rate = .001
+
+# MNIST
+train_dataset = torchvision.datasets.MNIST(root='./data', train=True,
+    download=True, transform=transforms.ToTensor())
+
+test_dataset = torchvision.datasets.MNIST(root='./data', train=False,
+    transform=transforms.ToTensor())
+
+train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=batch_size, 
+    shuffle=True)
+
+test_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=batch_size)
+
+examples = iter(train_loader)
+samples, labels = examples.next()
+print(samples.shape, labels.shape)
+
+for i in range(6):
+    plt.subplot(2, 3, i+1)
+    plt.imshow(samples[i][0], cmap='gray')
+# plt.show()
+
+class NeuralNet(nn.Module):
+    def __init__(self, input_size, hidden_size, num_classes):
+        super(NeuralNet, self).__init__()
+        self.layers = nn.Sequential(
+            nn.Linear(input_size, hidden_size),
+            nn.ReLU(),
+            nn.Linear(hidden_size, num_classes)
+            # no softmax because its included in the CE loss function
+        )
+    
+    def forward(self, x):
+        return self.layers(x)
+
+model = NeuralNet(input_size, hidden_size, num_classes).to(device)
+print(model)
+
+# loss and optimizer
+criterion = nn.CrossEntropyLoss()
+optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
+
+# training loop
+num_total_steps = len(train_loader)
+for epoch in range(num_epochs):
+    for batch, (images, labels) in enumerate(train_loader):
+        # reshape 100, 1, 28, 28 -> 100, 784
+        images = images.reshape(-1, 28*28).to(device) # reshape and send to gpu if available
+        labels = labels.to(device)
+
+        # forward
+        outputs = model(images)
+        loss = criterion(outputs, labels)
+
+        # backward + update
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+
+        if (batch+1) % 100 == 0:
+            print(f'Epoch {epoch+1}/{num_epochs}, step {batch+1}/{num_total_steps}, loss = {loss.item():.4f}')
+
+# test
+with torch.no_grad():
+    n_correct = 0
+    n_samples = 0
+    for images, labels in test_loader:
+        images = images.reshape(-1, 28*28).to(device)
+        labels = labels.to(device)
+        outputs = model(images)
+
+        # value, index (index is class label)
+        _, predictions = torch.max(outputs, 1)
+        n_samples += labels.shape[0]
+        n_correct += (predictions==labels).sum().item()
+
+    acc = 100.*n_correct/n_samples
+    print(f'Accuracy = {acc}%')