Реализация пользовательского набора данных с помощью PyTorch

Я пытаюсь изменить эту прямую сеть, взятую из https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/01-basics/feedforward_neural_network/main.py, чтобы использовать мой собственный набор данных.

Я определяю пользовательский набор данных из двух 1 тусклых массивов в качестве входных и двух скаляров соответствующего выхода:

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)

Я обновил гиперпараметры, чтобы соответствовать новым параметрам input_size (2) & num_classes (3).

Я также сменил images = images.reshape(-1, 28*28).to(device) на images = images.reshape(-1, 4).to(device)

Поскольку минимальный набор тренировок изменился, я изменил batch_size на 1.

После внесения этих изменений я получаю ошибку при попытке тренировки:

RuntimeError Traceback (последний последний вызов) в() 51 52 # Переносный проход ---> 53 выхода = модель (изображения) 54 loss = критерий (выходы, метки) 55

/home/.local/lib/python3.6/site-packages/torch/nn/modules/module.py в вызове (self, * input, ** kwargs) 489 result = self._slow_forward (* input, ** kwargs ) 490 else: → 491 result = self.forward(* input, ** kwargs) 492 для hook in self._forward_hooks.values(): 493 hook_result = hook (self, input, result)

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

/home/.local/lib/python3.6/site-packages/torch/nn/modules/module.py в вызове (self, * input, ** kwargs) 489 result = self._slow_forward (* input, ** kwargs ) 490 else: → 491 result = self.forward(* input, ** kwargs) 492 для hook in self._forward_hooks.values(): 493 hook_result = hook (self, input, result)

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

/home/.local/lib/python3.6/site-packages/torch/nn/functional.py в линейном (вход, вес, смещение) 990, если input.dim() == 2 и смещение не равно None: 991 # fused op немного быстрее → 992 return torch.addmm (смещение, вход, weight.t()) 993 994 output = input.matmul(weight.t())

RuntimeError: несоответствие размера, m1: [3 x 4], m2: [2 x 3] at/pytorch/aten/src/THC/generic/THCTensorMathBlas.cu:249

Как изменить код в соответствии с ожидаемой размерностью? Я не знаю, какой код изменить, поскольку я изменил все параметры, требующие обновления?

Источник до изменений:

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')

Изменения исходного сообщения:

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')