使用PyTorch实施自定义数据集

Question

我正在尝试修改来自https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/01-basics/feedforward_neural_network/main.py的此前馈网络 利用我自己的数据集。

我定义了一个自定义数据集，其中包含两个1个暗淡数组作为输入，两个标量分别对应于输出：

x = torch.tensor([[5.5, 3,3,4] , [1 , 2,3,4], [9 , 2,3,4]])
print(x)

y = torch.tensor([1,2,3])
print(y)

import torch.utils.data as data_utils

my_train = data_utils.TensorDataset(x, y)
my_train_loader = data_utils.DataLoader(my_train, batch_size=50, shuffle=True)

我已经更新了超参数，以匹配新的input_size（2）和num_classes（3）。

我也将images = images.reshape(-1, 28*28).to(device)更改为images = images.reshape(-1, 4).to(device)

由于训练集很小，所以我将batch_size更改为1。

进行这些修改后，尝试训练时收到错误消息：

  

RuntimeError跟踪（最近的调用）   最后）在（）        51        52＃前传   ---> 53个输出=模型（图像）        54损失=标准（输出，标签）        55

     呼叫中的

/home/.local/lib/python3.6/site-packages/torch/nn/modules/module.py（自身，*输入，** kwargs）       489结果= self._slow_forward（* input，** kwargs）       490其他：   -> 491结果= self.forward（* input，** kwargs）       492 for self._forward_hooks.values（）的钩子：       493 hook_result =钩子（自身，输入，结果）

     

向前（自己，x）        31        32 def forward（自我，x）：   -> 33出= self.fc1（x）        34出= self.relu（出）        35 out = self.fc2（out）

     呼叫中的

/home/.local/lib/python3.6/site-packages/torch/nn/modules/module.py（自身，*输入，** kwargs）       489结果= self._slow_forward（* input，** kwargs）       490其他：   -> 491结果= self.forward（* input，** kwargs）       492 for self._forward_hooks.values（）的钩子：       493 hook_result =钩子（自身，输入，结果）

     

/home/.local/lib/python3.6/site-packages/torch/nn/modules/linear.py向前（自己，输入）        53        54 def forward（自己，输入）：   ---> 55 return F.linear（input，self.weight，self.bias）        56        57 def extra_repr（self）：

     

/home/.local/lib/python3.6/site-packages/torch/nn/functional.py   线性（输入，重量，偏差）       990如果input.dim（）== 2并且bias不是None：       991＃融合操作速度稍快   -> 992返回torch.addmm（bias，input，weight.t（））       993       994输出= input.matmul（weight.t（））

     

RuntimeError：大小不匹配，m1：[3 x 4]，m2：[2 x 3]，位于   /pytorch/aten/src/THC/generic/THCTensorMathBlas.cu:249

如何修改代码以匹配预期的维数？我不确定要更改所有需要更新的参数时要更改哪些代码？

更改前的来源：

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms


# Device configuration
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# Hyper-parameters 
input_size = 784
hidden_size = 500
num_classes = 10
num_epochs = 5
batch_size = 100
learning_rate = 0.001

# MNIST dataset 
train_dataset = torchvision.datasets.MNIST(root='../../data', 
                                           train=True, 
                                           transform=transforms.ToTensor(),  
                                           download=True)

test_dataset = torchvision.datasets.MNIST(root='../../data', 
                                          train=False, 
                                          transform=transforms.ToTensor())

# Data loader
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, 
                                          shuffle=False)

# Fully connected neural network with one hidden layer
class NeuralNet(nn.Module):
    def __init__(self, input_size, hidden_size, num_classes):
        super(NeuralNet, self).__init__()
        self.fc1 = nn.Linear(input_size, hidden_size) 
        self.relu = nn.ReLU()
        self.fc2 = nn.Linear(hidden_size, num_classes)  

    def forward(self, x):
        out = self.fc1(x)
        out = self.relu(out)
        out = self.fc2(out)
        return out

model = NeuralNet(input_size, hidden_size, num_classes).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)  

# Train the model
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):  
        # Move tensors to the configured device
        images = images.reshape(-1, 28*28).to(device)
        labels = labels.to(device)

        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)

        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if (i+1) % 100 == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}' 
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

# Test the model
# In test phase, we don't need to compute gradients (for memory efficiency)
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.reshape(-1, 28*28).to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Accuracy of the network on the 10000 test images: {} %'.format(100 * correct / total))

# Save the model checkpoint
torch.save(model.state_dict(), 'model.ckpt')

源帖子更改：

x = torch.tensor([[5.5, 3,3,4] , [1 , 2,3,4], [9 , 2,3,4]])
print(x)

y = torch.tensor([1,2,3])
print(y)

import torch.utils.data as data_utils

my_train = data_utils.TensorDataset(x, y)
my_train_loader = data_utils.DataLoader(my_train, batch_size=50, shuffle=True)

print(my_train)

print(my_train_loader)

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms


# Device configuration
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# Hyper-parameters 
input_size = 2
hidden_size = 3
num_classes = 3
num_epochs = 5
batch_size = 1
learning_rate = 0.001

# MNIST dataset 
train_dataset = my_train

# Data loader
train_loader = my_train_loader

# Fully connected neural network with one hidden layer
class NeuralNet(nn.Module):
    def __init__(self, input_size, hidden_size, num_classes):
        super(NeuralNet, self).__init__()
        self.fc1 = nn.Linear(input_size, hidden_size) 
        self.relu = nn.ReLU()
        self.fc2 = nn.Linear(hidden_size, num_classes)  

    def forward(self, x):
        out = self.fc1(x)
        out = self.relu(out)
        out = self.fc2(out)
        return out

model = NeuralNet(input_size, hidden_size, num_classes).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)  

# Train the model
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):  
        # Move tensors to the configured device
        images = images.reshape(-1, 4).to(device)
        labels = labels.to(device)

        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)

        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if (i+1) % 100 == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}' 
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

# Test the model
# In test phase, we don't need to compute gradients (for memory efficiency)
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.reshape(-1, 4).to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Accuracy of the network on the 10000 test images: {} %'.format(100 * correct / total))

# Save the model checkpoint
torch.save(model.state_dict(), 'model.ckpt')

Answer 1

您需要将input_size更改为4（2 * 2），而不是更改为当前显示的代码2。
如果将其与原始MNIST示例进行比较，您会发现input_size设置为784（28 * 28），而不仅仅是28。