前面介紹了pytorch的一些基本用法，從這一節開始介紹pytorch在深度學習中的應用。在開始介紹之前，首先熟悉一下常用的概念和層。
class torch.nn.module
舉例：
import torch.nn as nn
import torch.nn.functional as f
class
model
(nn.module):
def__init__
(self):
super(model, self).__init__()
self.conv1 = nn.conv2d(1, 20, 5)
self.conv2 = nn.conv2d(20, 20, 5)
defforward
(self, x):
x = f.relu(self.conv1(x))
return f.relu(self.conv2(x))
class torch.nn.sequential(*args)
# example of using sequential
model = nn.sequential(
nn.conv2d(1,20,5),
nn.relu(),
nn.conv2d(20,64,5),
nn.relu()
)
class torch.nn.conv2d
(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=true)
其餘幾個引數跟caffe一樣。
2d normalization
class torch.nn.batchnorm2d
(num_features, eps=1e-05, momentum=0.1, affine=true)
batchnorm2d計算的是每個通道上的歸一化特徵，公式為
2d pooling
class torch.nn.maxpool2d
(kernel_size, stride=none, padding=0, dilation=1, return_indices=false, ceil_mode=false)
其餘引數和caffe一樣。
pooling之後的特徵圖大小計算方式為
接下來就是見證奇蹟的時刻，讓我們來看看乙個簡單的卷積神經網路是如何構建的。
首先和前面幾節一樣載入資料
import torch
import torch.nn as nn
import torchvision.datasets as dsets
import torchvision.transforms as transforms
from torch.autograd import variable
# hyper parameters
num_epochs = 5
batch_size = 100
learning_rate = 0.001
# mnist dataset
train_dataset = dsets.mnist(root='./data/',
train=true,
transform=transforms.totensor(),
download=true)
test_dataset = dsets.mnist(root='./data/',
train=false,
transform=transforms.totensor())
# data loader (input pipeline)
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)
# cnn model (2 conv layer)
class cnn(nn.module):
def __init__(self):
super(cnn, self).__init__()
self.layer1 = nn.sequential(
nn.conv2d(1, 16, kernel_size=5, padding=2),
nn.batchnorm2d(16),
nn.relu(),
nn.maxpool2d(2))
self.layer2 = nn.sequential(
nn.conv2d(16, 32, kernel_size=5, padding=2),
nn.batchnorm2d(32),
nn.relu(),
nn.maxpool2d(2))
self.fc = nn.linear(7*7*32, 10)
def forward(self, x):
out = self.layer1(x)
out = self.layer2(out)
out = out
.view(out
.size(0), -1)
out = self.fc(out)
return out
cnn = cnn()
# loss and optimizer
criterion = nn.crossentropyloss()
optimizer = torch.optim
.adam(cnn.parameters(), lr=learning_rate)
# train the model
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
images = variable(images)
labels = variable(labels)
# forward + backward + optimize
optimizer.zero_grad()
outputs = cnn(images)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
if (i+1) % 100 == 0:
print ('epoch [%d/%d], iter [%d/%d] loss: %.4f'
%(epoch+1, num_epochs, i+1, len(train_dataset)//batch_size, loss.data[0]))
# test the model
cnn.eval() # change model to 'eval' mode (bn uses moving mean/var).
correct = 0
total = 0
for images, labels in test_loader:
images = variable(images)
outputs = cnn(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum()
print('test accuracy of
the model on
the10000 test images: %d %%' % (100 * correct / total))
最終結果為正確率99%，訓練耗時7分鐘左右。按照前一節的做法改為gpu版本後，正確率為99%，訓練耗時34秒。由於載入資料只有乙個worker，將dataloader的num_workers設為4後，訓練耗時17秒。
相較於上一節的兩個線性層，本節的兩個卷積層加上乙個線性層的做法在準確率上有所提公升，並且參數量更少。上一節隱層的參數量為784x500=392000，這一節卷積層的參數量為16x1x5x5+32x16x5x5=13200。
PyTorch PyTorch高階教程三
前面介紹了使用pytorch構造cnn網路，這一節介紹點高階的東西lstm。以及我之前的一篇中文翻譯部落格 class torch.nn.lstm args,kwargs class rnn nn.module def init self,input size,hidden size,num lay...
Pytorch pytorch中的LSTM模型
pytorch中lstm的公式表示為 pytorch中lstm的定義如下 輸入資料格式 input seq len,batch,input size h0 num layers num directions,batch,hidden size c0 num layers num directions...
PyTorch PyTorch入門教程五
還是直接看 是如何寫的。從numpy中建立輸入與輸出。import torch import torch.nn as nn import numpy as np import matplotlib.pyplot as plt from torch.autograd import variable h...