code for saving the model is added

yunjey · yunjey · commit 86a0872430f3 · 2017-03-11T14:54:46.000+09:00
diff --git a/tutorials/01 - Linear Regression/main.py b/tutorials/01 - Linear Regression/main.py
@@ -58,4 +58,7 @@ def forward(self, x):
 plt.plot(x_train, y_train, 'ro', label='Original data')
 plt.plot(x_train, predicted, label='Fitted line')
 plt.legend()
-plt.show()
+plt.show()
+
+# Save the Model
+torch.save(model, 'model.pkl')
diff --git a/tutorials/02 - Logistic Regression/main.py b/tutorials/02 - Logistic Regression/main.py
@@ -13,12 +13,12 @@
 learning_rate = 0.001
 
 # MNIST Dataset (Images and Labels)
-train_dataset = dsets.MNIST(root='./data', 
+train_dataset = dsets.MNIST(root='../data', 
                             train=True, 
                             transform=transforms.ToTensor(),
                             download=True)
 
-test_dataset = dsets.MNIST(root='./data', 
+test_dataset = dsets.MNIST(root='../data', 
                            train=False, 
                            transform=transforms.ToTensor())
 
@@ -76,4 +76,7 @@ def forward(self, x):
     total += labels.size(0)
     correct += (predicted == labels).sum()
     
-print('Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total))
+print('Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total))
+
+# Save the Model
+torch.save(model, 'model.pkl')
diff --git a/tutorials/03 - Feedforward Neural Network/main-gpu.py b/tutorials/03 - Feedforward Neural Network/main-gpu.py
@@ -14,12 +14,12 @@
 learning_rate = 0.001
 
 # MNIST Dataset 
-train_dataset = dsets.MNIST(root='./data', 
+train_dataset = dsets.MNIST(root='../data', 
                             train=True, 
                             transform=transforms.ToTensor(),  
                             download=True)
 
-test_dataset = dsets.MNIST(root='./data', 
+test_dataset = dsets.MNIST(root='../data', 
                            train=False, 
                            transform=transforms.ToTensor())
 
diff --git a/tutorials/03 - Feedforward Neural Network/main.py b/tutorials/03 - Feedforward Neural Network/main.py
@@ -14,12 +14,12 @@
 learning_rate = 0.001
 
 # MNIST Dataset 
-train_dataset = dsets.MNIST(root='./data', 
+train_dataset = dsets.MNIST(root='../data', 
                             train=True, 
                             transform=transforms.ToTensor(),  
                             download=True)
 
-test_dataset = dsets.MNIST(root='./data', 
+test_dataset = dsets.MNIST(root='../data', 
                            train=False, 
                            transform=transforms.ToTensor())
 
diff --git a/tutorials/04 - Convolutional Neural Network/main-gpu.py b/tutorials/04 - Convolutional Neural Network/main-gpu.py
@@ -11,12 +11,12 @@
 learning_rate = 0.001
 
 # MNIST Dataset
-train_dataset = dsets.MNIST(root='./data/',
+train_dataset = dsets.MNIST(root='../data/',
                             train=True, 
                             transform=transforms.ToTensor(),
                             download=True)
 
-test_dataset = dsets.MNIST(root='./data/',
+test_dataset = dsets.MNIST(root='../data/',
                            train=False, 
                            transform=transforms.ToTensor())
 
@@ -77,14 +77,17 @@ def forward(self, x):
                    %(epoch+1, num_epochs, i+1, len(train_dataset)//batch_size, loss.data[0]))
 
 # Test the Model
-cnn.eval()  
+cnn.eval()    # Change model to 'eval' mode (BN uses moving mean/var).
 correct = 0
 total = 0
 for images, labels in test_loader:
     images = Variable(images).cuda()
     outputs = cnn(images)
     _, predicted = torch.max(outputs.data, 1)
     total += labels.size(0)
-    correct += (predicted == labels).sum()
+    correct += (predicted.cpu() == labels).sum()
 
-print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total))
+print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total))
+
+# Save the Trained Model
+torch.save(cnn, 'cnn.pkl')
diff --git a/tutorials/04 - Convolutional Neural Network/main.py b/tutorials/04 - Convolutional Neural Network/main.py
@@ -11,12 +11,12 @@
 learning_rate = 0.001
 
 # MNIST Dataset
-train_dataset = dsets.MNIST(root='./data/',
+train_dataset = dsets.MNIST(root='../data/',
                             train=True, 
                             transform=transforms.ToTensor(),
                             download=True)
 
-test_dataset = dsets.MNIST(root='./data/',
+test_dataset = dsets.MNIST(root='../data/',
                            train=False, 
                            transform=transforms.ToTensor())
 
@@ -77,7 +77,7 @@ def forward(self, x):
                    %(epoch+1, num_epochs, i+1, len(train_dataset)//batch_size, loss.data[0]))
 
 # Test the Model
-cnn.eval()  
+cnn.eval()  # Change model to 'eval' mode (BN uses moving mean/var).
 correct = 0
 total = 0
 for images, labels in test_loader:
@@ -87,4 +87,7 @@ def forward(self, x):
     total += labels.size(0)
     correct += (predicted == labels).sum()
 
-print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total))
+print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total))
+
+# Save the Trained Model
+torch.save(cnn, 'cnn.pkl')
diff --git a/tutorials/05 - Deep Residual Network/main-gpu.py b/tutorials/05 - Deep Residual Network/main-gpu.py
@@ -14,12 +14,12 @@
     transforms.ToTensor()])
 
 # CIFAR-10 Dataset
-train_dataset = dsets.CIFAR10(root='./data/',
+train_dataset = dsets.CIFAR10(root='../data/',
                                train=True, 
                                transform=transform,
                                download=True)
 
-test_dataset = dsets.CIFAR10(root='./data/',
+test_dataset = dsets.CIFAR10(root='../data/',
                               train=False, 
                               transform=transforms.ToTensor())
 
@@ -109,7 +109,7 @@ def forward(self, x):
 optimizer = torch.optim.Adam(resnet.parameters(), lr=lr)
     
 # Training 
-for epoch in range(40):
+for epoch in range(80):
     for i, (images, labels) in enumerate(train_loader):
         images = Variable(images.cuda())
         labels = Variable(labels.cuda())
@@ -122,14 +122,15 @@ def forward(self, x):
         optimizer.step()
         
         if (i+1) % 100 == 0:
-            print ("Epoch [%d/%d], Iter [%d/%d] Loss: %.4f" %(epoch+1, 40, i+1, 500, loss.data[0]))
+            print ("Epoch [%d/%d], Iter [%d/%d] Loss: %.4f" %(epoch+1, 80, i+1, 500, loss.data[0]))
 
     # Decaying Learning Rate
     if (epoch+1) % 20 == 0:
         lr /= 3
         optimizer = torch.optim.Adam(resnet.parameters(), lr=lr) 
         
 # Test
+resnet.eval()
 correct = 0
 total = 0
 for images, labels in test_loader:
@@ -139,4 +140,7 @@ def forward(self, x):
     total += labels.size(0)
     correct += (predicted.cpu() == labels).sum()
 
-print('Accuracy of the model on the test images: %d %%' % (100 * correct / total))
+print('Accuracy of the model on the test images: %d %%' % (100 * correct / total))
+
+# Save the Model
+torch.save(resnet, 'resnet.pkl')
diff --git a/tutorials/05 - Deep Residual Network/main.py b/tutorials/05 - Deep Residual Network/main.py
@@ -14,12 +14,12 @@
     transforms.ToTensor()])
 
 # CIFAR-10 Dataset
-train_dataset = dsets.CIFAR10(root='./data/',
+train_dataset = dsets.CIFAR10(root='../data/',
                                train=True, 
                                transform=transform,
                                download=True)
 
-test_dataset = dsets.CIFAR10(root='./data/',
+test_dataset = dsets.CIFAR10(root='../data/',
                               train=False, 
                               transform=transforms.ToTensor())
 
@@ -130,6 +130,7 @@ def forward(self, x):
         optimizer = torch.optim.Adam(resnet.parameters(), lr=lr) 
 
 # Test
+resnet.eval()
 correct = 0
 total = 0
 for images, labels in test_loader:
@@ -139,4 +140,7 @@ def forward(self, x):
     total += labels.size(0)
     correct += (predicted == labels).sum()
 
-print('Accuracy of the model on the test images: %d %%' % (100 * correct / total))
+print('Accuracy of the model on the test images: %d %%' % (100 * correct / total))
+
+# Save the Model
+torch.save(resnet, 'resnet.pkl')
diff --git a/tutorials/06 - Recurrent Neural Network/main-gpu.py b/tutorials/06 - Recurrent Neural Network/main-gpu.py
@@ -16,12 +16,12 @@
 learning_rate = 0.01
 
 # MNIST Dataset
-train_dataset = dsets.MNIST(root='./data/',
+train_dataset = dsets.MNIST(root='../data/',
                             train=True, 
                             transform=transforms.ToTensor(),
                             download=True)
 
-test_dataset = dsets.MNIST(root='./data/',
+test_dataset = dsets.MNIST(root='../data/',
                            train=False, 
                            transform=transforms.ToTensor())
 
@@ -87,4 +87,7 @@ def forward(self, x):
     total += labels.size(0)
     correct += (predicted.cpu() == labels).sum()
 
-print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total)) 
+print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total)) 
+
+# Save the Model
+torch.save(rnn, 'rnn.pkl')
diff --git a/tutorials/06 - Recurrent Neural Network/main.py b/tutorials/06 - Recurrent Neural Network/main.py
@@ -16,12 +16,12 @@
 learning_rate = 0.01
 
 # MNIST Dataset
-train_dataset = dsets.MNIST(root='./data/',
+train_dataset = dsets.MNIST(root='../data/',
                             train=True, 
                             transform=transforms.ToTensor(),
                             download=True)
 
-test_dataset = dsets.MNIST(root='./data/',
+test_dataset = dsets.MNIST(root='../data/',
                            train=False, 
                            transform=transforms.ToTensor())
 
@@ -87,4 +87,7 @@ def forward(self, x):
     total += labels.size(0)
     correct += (predicted == labels).sum()
 
-print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total)) 
+print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total)) 
+
+# Save the Model
+torch.save(rnn, 'rnn.pkl')
diff --git a/tutorials/07 - Bidirectional Recurrent Neural Network/main-gpu.py b/tutorials/07 - Bidirectional Recurrent Neural Network/main-gpu.py
@@ -16,12 +16,12 @@
 learning_rate = 0.003
 
 # MNIST Dataset
-train_dataset = dsets.MNIST(root='./data/',
+train_dataset = dsets.MNIST(root='../data/',
                             train=True, 
                             transform=transforms.ToTensor(),
                             download=True)
 
-test_dataset = dsets.MNIST(root='./data/',
+test_dataset = dsets.MNIST(root='../data/',
                            train=False, 
                            transform=transforms.ToTensor())
 
@@ -88,4 +88,7 @@ def forward(self, x):
     total += labels.size(0)
     correct += (predicted.cpu() == labels).sum()
 
-print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total)) 
+print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total)) 
+
+# Save the Model
+torch.save(rnn, 'rnn.pkl')
diff --git a/tutorials/07 - Bidirectional Recurrent Neural Network/main.py b/tutorials/07 - Bidirectional Recurrent Neural Network/main.py
@@ -16,12 +16,12 @@
 learning_rate = 0.003
 
 # MNIST Dataset
-train_dataset = dsets.MNIST(root='./data/',
+train_dataset = dsets.MNIST(root='../data/',
                             train=True, 
                             transform=transforms.ToTensor(),
                             download=True)
 
-test_dataset = dsets.MNIST(root='./data/',
+test_dataset = dsets.MNIST(root='../data/',
                            train=False, 
                            transform=transforms.ToTensor())
 
@@ -88,4 +88,7 @@ def forward(self, x):
     total += labels.size(0)
     correct += (predicted == labels).sum()
 
-print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total)) 
+print('Test Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total)) 
+
+# Save the Model
+torch.save(rnn, 'rnn.pkl')
diff --git a/tutorials/08 - Language Model/data_utils.py b/tutorials/08 - Language Model/data_utils.py
@@ -0,0 +1,46 @@
+import torch
+import os
+
+class Dictionary(object):
+    def __init__(self):
+        self.word2idx = {}
+        self.idx2word = {}
+        self.idx = 0
+    
+    def add_word(self, word):
+        if not word in self.word2idx:
+            self.word2idx[word] = self.idx
+            self.idx2word[self.idx] = word
+            self.idx += 1
+    
+    def __len__(self):
+        return len(self.word2idx)
+    
+class Corpus(object):
+    def __init__(self, path='./data'):
+        self.dictionary = Dictionary()
+        self.train = os.path.join(path, 'train.txt')
+        self.test = os.path.join(path, 'test.txt')
+
+    def get_data(self, path, batch_size=20):
+        # Add words to the dictionary
+        with open(path, 'r') as f:
+            tokens = 0
+            for line in f:
+                words = line.split() + ['<eos>']
+                tokens += len(words)
+                for word in words: 
+                    self.dictionary.add_word(word)  
+        
+        # Tokenize the file content
+        ids = torch.LongTensor(tokens)
+        token = 0
+        with open(path, 'r') as f:
+            for line in f:
+                words = line.split() + ['<eos>']
+                for word in words:
+                    ids[token] = self.dictionary.word2idx[word]
+                    token += 1
+        num_batches = ids.size(0) // batch_size
+        ids = ids[:num_batches*batch_size]
+        return ids.view(batch_size, -1)
diff --git a/tutorials/08 - Language Model/main-gpu.py b/tutorials/08 - Language Model/main-gpu.py
diff --git a/tutorials/08 - Language Model/main.py b/tutorials/08 - Language Model/main.py
diff --git a/tutorials/10 - Generative Adversarial Network/main-gpu.py b/tutorials/10 - Generative Adversarial Network/main-gpu.py
diff --git a/tutorials/10 - Generative Adversarial Network/main.py b/tutorials/10 - Generative Adversarial Network/main.py
