Propose some modified codes for PyTorchZeroToAll

05_linear_regression.py

@@ -1,4 +1,3 @@
-
 import torch
 from torch.autograd import Variable
 
@@ -41,7 +40,7 @@ def forward(self, x):
 
     # Compute and print loss
     loss = criterion(y_pred, y_data)
-    print(epoch, loss.data[0])
+    print(epoch, loss.item())
 
     # Zero gradients, perform a backward pass, and update the weights.
     optimizer.zero_grad()

06_logistic_regression.py

@@ -41,7 +41,7 @@ def forward(self, x):
 
     # Compute and print loss
     loss = criterion(y_pred, y_data)
-    print(epoch, loss.data[0])
+    print(epoch, loss.item())
 
     # Zero gradients, perform a backward pass, and update the weights.
     optimizer.zero_grad()

07_diabets_logistic.py

@@ -3,7 +3,7 @@
 from torch.autograd import Variable
 import numpy as np
 
-xy = np.loadtxt('./data/diabetes.csv.gz', delimiter=',', dtype=np.float32)
+xy = np.loadtxt('./data/diabetes.csv', delimiter=',', dtype=np.float32)
 x_data = Variable(torch.from_numpy(xy[:, 0:-1]))
 y_data = Variable(torch.from_numpy(xy[:, [-1]]))
 
@@ -52,7 +52,7 @@ def forward(self, x):
 
     # Compute and print loss
     loss = criterion(y_pred, y_data)
-    print(epoch, loss.data[0])
+    print(epoch, loss.item())
 
     # Zero gradients, perform a backward pass, and update the weights.
     optimizer.zero_grad()

08_1_dataset_loader.py

@@ -29,7 +29,7 @@ def __len__(self):
 train_loader = DataLoader(dataset=dataset,
                           batch_size=32,
                           shuffle=True,
-                          num_workers=2)
+                          num_workers=2) #num_workers=0 in cpu version
 
 for epoch in range(2):
     for i, data in enumerate(train_loader, 0):

08_2_dataset_loade_logistic.py

@@ -12,7 +12,7 @@ class DiabetesDataset(Dataset):
 
     # Initialize your data, download, etc.
     def __init__(self):
-        xy = np.loadtxt('./data/diabetes.csv.gz',
+        xy = np.loadtxt('./data/diabetes.csv',
                         delimiter=',', dtype=np.float32)
         self.len = xy.shape[0]
         self.x_data = torch.from_numpy(xy[:, 0:-1])
@@ -29,7 +29,7 @@ def __len__(self):
 train_loader = DataLoader(dataset=dataset,
                           batch_size=32,
                           shuffle=True,
-                          num_workers=2)
+                          num_workers=2) #num_workers=0 in cpu version
 
 
 class Model(torch.nn.Module):
@@ -80,7 +80,7 @@ def forward(self, x):
 
         # Compute and print loss
         loss = criterion(y_pred, labels)
-        print(epoch, i, loss.data[0])
+        print(epoch, i, loss.item())
 
         # Zero gradients, perform a backward pass, and update the weights.
         optimizer.zero_grad()

09_2_softmax_mnist.py

@@ -67,18 +67,19 @@ def train(epoch):
         if batch_idx % 10 == 0:
             print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                 epoch, batch_idx * len(data), len(train_loader.dataset),
-                100. * batch_idx / len(train_loader), loss.data[0]))
+                100. * batch_idx / len(train_loader), loss.item()))
 
 
 def test():
     model.eval()
     test_loss = 0
     correct = 0
     for data, target in test_loader:
-        data, target = Variable(data, volatile=True), Variable(target)
+        with torch.no_grad():
+            data, target = Variable(data), Variable(target)
         output = model(data)
         # sum up batch loss
-        test_loss += criterion(output, target).data[0]
+        test_loss += criterion(output, target).item()
         # get the index of the max
         pred = output.data.max(1, keepdim=True)[1]
         correct += pred.eq(target.data.view_as(pred)).cpu().sum()

10_1_cnn_mnist.py

@@ -74,7 +74,8 @@ def test():
     test_loss = 0
     correct = 0
     for data, target in test_loader:
-        data, target = Variable(data, volatile=True), Variable(target)
+        with torch.no_grad():
+            data, target = Variable(data), Variable(target)
         output = model(data)
         # sum up batch loss
         test_loss += F.nll_loss(output, target, size_average=False).data[0]

11_1_toy_inception_mnist.py

@@ -104,18 +104,19 @@ def train(epoch):
         if batch_idx % 10 == 0:
             print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                 epoch, batch_idx * len(data), len(train_loader.dataset),
-                100. * batch_idx / len(train_loader), loss.data[0]))
+                100. * batch_idx / len(train_loader), loss.item()))
 
 
 def test():
     model.eval()
     test_loss = 0
     correct = 0
     for data, target in test_loader:
-        data, target = Variable(data, volatile=True), Variable(target)
+        with torch.no_grad():
+            data, target = Variable(data), Variable(target)
         output = model(data)
         # sum up batch loss
-        test_loss += F.nll_loss(output, target, size_average=False).data[0]
+        test_loss += F.nll_loss(output, target, size_average=False).item()
         # get the index of the max log-probability
         pred = output.data.max(1, keepdim=True)[1]
         correct += pred.eq(target.data.view_as(pred)).cpu().sum()

12_2_hello_rnn.py

@@ -72,6 +72,7 @@ def init_hidden(self):
     sys.stdout.write("predicted string: ")
     for input, label in zip(inputs, labels):
         # print(input.size(), label.size())
+        label = label.unsqueeze(0)
         hidden, output = model(hidden, input)
         val, idx = output.max(1)
         sys.stdout.write(idx2char[idx.data[0]])

12_4_hello_rnn_emb.py

@@ -27,12 +27,19 @@
 
 class Model(nn.Module):
 
-    def __init__(self):
+    def __init__(self, num_classes, input_size, hidden_size, num_layers, embedding_size):
         super(Model, self).__init__()
-        self.embedding = nn.Embedding(input_size, embedding_size)
-        self.rnn = nn.RNN(input_size=embedding_size,
+
+        self.num_classes = num_classes
+        self.num_layers = num_layers
+        self.input_size = input_size
+        self.hidden_size = hidden_size
+        self.embedding_size = embedding_size
+
+        self.embedding = nn.Embedding(self.input_size, self.embedding_size)
+        self.rnn = nn.RNN(input_size=self.embedding_size,
                           hidden_size=5, batch_first=True)
-        self.fc = nn.Linear(hidden_size, num_classes)
+        self.fc = nn.Linear(self.hidden_size, self.num_classes)
 
     def forward(self, x):
         # Initialize hidden and cell states
@@ -51,7 +58,7 @@ def forward(self, x):
 
 
 # Instantiate RNN model
-model = Model()
+model = Model(num_classes, input_size, hidden_size, num_layers, embedding_size)
 print(model)
 
 # Set loss and optimizer function