Question

使用下面的代码，我为每个训练数据创建10个实例，每个实例都有100个维度。每100个维度包含3个维度。因此它的形状是：（3，100，10）。这将模拟10个100像素的实例，每个实例具有3个通道以模拟RGB值

我已将此模型设置为仅在1到0之间分类。

在应用softmax层时，我收到错误消息：

RuntimeError：参数＃1'input'的期望张量具有相同的尺寸作为“结果”的张量；但4不等于3（而检查cudnn_convolution的参数）

我使用的是0.4.0（已使用print(torch.__version__)进行了检查）如何正确设置softmax图层的尺寸？我认为尺寸正确吗？

%reset -f

import os
import torch
from skimage import io, transform
import numpy as np
import matplotlib.pyplot as plt
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils
import torch.utils.data as data_utils
import torchvision
import numpy as np
from sklearn.preprocessing import scale
import torch.nn.functional as F
import torch.nn as nn
import torch.nn.functional as F
from random import randint

batch_size_value = 10

train_dataset = []
mu, sigma = 0, 0.1 # mean and standard deviation
num_instances = 10

# Create 3000 instance and reshape to (3 , 100, 10) , this emulates 10 instances of 100 pixels 
# each with 3 channels to emulate an RGB value

for i in range(num_instances) :
    image = []
    image_x = np.random.normal(mu, sigma, 3000).reshape((3 , 100, 10))
    train_dataset.append(image_x)

mu, sigma = 100, 0.80 # mean and standard deviation
for i in range(num_instances) :
    image = []
    image_x = np.random.normal(mu, sigma, 3000).reshape((3 , 100, 10))
    train_dataset.append(image_x)

labels_1 = [1 for i in range(num_instances)]
labels_0 = [0 for i in range(num_instances)]

labels = labels_1 + labels_0

print(labels)

x2 = torch.tensor(train_dataset).float()
y2 = torch.tensor(labels).long()

my_train2 = data_utils.TensorDataset(x2, y2)
train_loader2 = data_utils.DataLoader(my_train2, batch_size=batch_size_value, shuffle=False)

# print(x2)

# Device configuration
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
print('device' , device)
# device = 'cpu'

# Hyper parameters
num_epochs = 10
num_classes = 2
batch_size = 5
learning_rate = 0.001

# Convolutional neural network (two convolutional layers)
class ConvNet(nn.Module):
    def __init__(self):
        super(ConvNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, kernel_size=5) 
        self.conv2 = nn.Conv2d(6, 16, kernel_size=5)
        self.fc1   = nn.Linear(864, 120) 
        self.fc2   = nn.Linear(120, 84)
        self.fc3   = nn.Linear(84, num_classes)

    def forward(self, x):
        out = F.relu(self.conv1(x))
        out = F.max_pool2d(out, 2)
        out = F.relu(self.conv2(out))
        out = F.max_pool2d(out, 2)
        out = out.view(out.size(0), -1)
        out = F.relu(self.fc1(out))
        out = F.relu(self.fc2(out))
        out = self.fc3(out)

model = ConvNet().to(device)

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

# Train the model
total_step = len(train_loader2)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader2):
        images = images.to(device)
        labels = labels.to(device)

        # Forward pass
        outputs = model(images)
#         print(images)

        loss = criterion(outputs, labels)

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

        if (i % 10) == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}' 
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

更新：

删除这些行：

out = F.relu(self.conv2(out))
out = F.max_pool2d(out, 2)

修复了尺寸小于内核的问题。

Answer 1

您的代码中存在一个结构化问题和一个错误。这是解决方案。

class ConvNet(nn.Module):
    def __init__(self):
        super(ConvNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, kernel_size=5) 
        self.conv2 = nn.Conv2d(6, 16, kernel_size=1)  # kernel_size 5----> 1
        self.fc1   = nn.Linear(384, 120)              # FC NodeCount864--> 384
        self.fc2   = nn.Linear(120, 84)
        self.fc3   = nn.Linear(84, num_classes)

    def forward(self, x):
        out = F.relu(self.conv1(x))
        out = F.max_pool2d(out, 2)
        out = F.relu(self.conv2(out))
        out = F.max_pool2d(out, 2)
        out = out.view(out.size(0), -1)
        out = F.relu(self.fc1(out))
        out = F.relu(self.fc2(out))
        out = self.fc3(out)
        return out                        # Don't forget to return the output

参数＃1“输入”的期望张量具有相同的维数

1 个答案: