Neural network 从经过训练的卷积网络进行预测
这是我的Neural network 从经过训练的卷积网络进行预测,neural-network,deep-learning,computer-vision,conv-neural-network,pytorch,Neural Network,Deep Learning,Computer Vision,Conv Neural Network,Pytorch,这是我的卷积网络,它创建训练数据,然后通过relu激活使用单个卷积对该数据进行训练: train_dataset = [] mu, sigma = 0, 0.1 # mean and standard deviation num_instances = 10 for i in range(num_instances) : image = [] image_x = np.random.normal(mu, sigma, 1000).reshape((1 , 100, 10))
卷积
网络,它创建训练数据,然后通过relu
激活使用单个卷积
对该数据进行训练:
train_dataset = []
mu, sigma = 0, 0.1 # mean and standard deviation
num_instances = 10
for i in range(num_instances) :
image = []
image_x = np.random.normal(mu, sigma, 1000).reshape((1 , 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, 1000).reshape((1 , 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)
import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
# Device configuration
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
# device = 'cpu'
# Hyper parameters
num_epochs = 50
num_classes = 2
batch_size = 5
learning_rate = 0.001
# Convolutional neural network (two convolutional layers)
class ConvNet(nn.Module):
def __init__(self, num_classes=1):
super(ConvNet, self).__init__()
self.layer1 = nn.Sequential(
nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(16),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.layer2 = nn.Sequential(
nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(32),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.fc = nn.Linear(32*25*2, num_classes)
def forward(self, x):
out = self.layer1(x)
out = self.layer2(out)
out = out.reshape(out.size(0), -1)
out = self.fc(out)
return out
model = ConvNet(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_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)
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()))
要进行单个预测,我使用:
model(x2[10].unsqueeze_(0).cuda())
torch.argmax(model(x2[2].unsqueeze_(0).cuda()), dim=1)
哪些产出:
tensor([[ 4.4880, -4.3128]], device='cuda:0')
这是否应该返回预测形状(100,10)的图像张量
更新:为了执行预测,我使用:
model(x2[10].unsqueeze_(0).cuda())
torch.argmax(model(x2[2].unsqueeze_(0).cuda()), dim=1)
src:
在此上下文中,torch.argmax
返回最大化预测值的位置 正如您的网络所指出的,它不是“完全卷积的”:虽然您有两个nn.Conv2d
层,但在顶部仍然有一个“完全连接的”(akann.Linear
)层,它只输出二维(num_class
)输出张量
更具体地说,您的网络需要1x100x10输入(单通道,100 x 10像素图像)。在
self.layer1
之后,您有一个16x50x5张量(16个通道来自卷积,空间维度由最大池层减少)。在
self.layer2
之后,您有一个32x25x2张量(来自卷积的32个通道,空间维度减少了另一个最大池层)。最后,完全连接的
self.fc
nn.Linear
层获取整个32*25*2
维度输入张量,并从整个输入生成num_类
输出。否。最初维度(100,10)
的图像将通过上面定义的所有层[Conv->BN->ReLU->MaxPool->Conv->BN->ReLU->MaxPool->Linear]
,每层的输出维度根据每层的属性而变化(如MaxPool(2X2)
等)最后你从最后一个线性
层得到你的输出,它输出一个维度向量num_类
,在你的例子中是2。你得到的输出是正确的。@Koustav请看问题更新。实际上你的疑问我有点不清楚。我的意思是,torch.argmax()预测将返回最大值的索引。在上述情况下,它将是4.4880的索引。您是否得到或期望得到与此不同的东西?然后请提及。嘿!请允许我建议您在深入研究代码之前了解CNN图像分类的工作原理。如果您需要,我可以为您提供一些入门材料。我觉得这一部分需要稍微梳理一下。为了回答您的问题,数字4.4880
是通过在输入通过连续层时执行一系列乘积求和,并使用学习的权重(在训练时)得出的是的,最大值的索引是预测的类标签索引。CNN基础知识:(1)CS231n(圣杯):(2)中级帖子:(3)PyTorch示例: