pytorch構(gòu)建網(wǎng)絡(luò)模型的4種方法

更新時(shí)間：2018年04月13日 16:52:43 作者：denny402

這篇文章主要為大家詳細(xì)介紹了pytorch構(gòu)建網(wǎng)絡(luò)模型的4種方法，具有一定的參考價(jià)值，感興趣的小伙伴們可以參考一下

利用pytorch來(lái)構(gòu)建網(wǎng)絡(luò)模型有很多種方法，以下簡(jiǎn)單列出其中的四種。

假設(shè)構(gòu)建一個(gè)網(wǎng)絡(luò)模型如下：

卷積層--》Relu層--》池化層--》全連接層--》Relu層--》全連接層

首先導(dǎo)入幾種方法用到的包：

import torch
import torch.nn.functional as F
from collections import OrderedDict

第一種方法

# Method 1 -----------------------------------------

class Net1(torch.nn.Module):
  def __init__(self):
    super(Net1, self).__init__()
    self.conv1 = torch.nn.Conv2d(3, 32, 3, 1, 1)
    self.dense1 = torch.nn.Linear(32 * 3 * 3, 128)
    self.dense2 = torch.nn.Linear(128, 10)

  def forward(self, x):
    x = F.max_pool2d(F.relu(self.conv(x)), 2)
    x = x.view(x.size(0), -1)
    x = F.relu(self.dense1(x))
    x = self.dense2(x)
    return x

print("Method 1:")
model1 = Net1()
print(model1)

這種方法比較常用，早期的教程通常就是使用這種方法。

第二種方法

# Method 2 ------------------------------------------
class Net2(torch.nn.Module):
  def __init__(self):
    super(Net2, self).__init__()
    self.conv = torch.nn.Sequential(
      torch.nn.Conv2d(3, 32, 3, 1, 1),
      torch.nn.ReLU(),
      torch.nn.MaxPool2d(2))
    self.dense = torch.nn.Sequential(
      torch.nn.Linear(32 * 3 * 3, 128),
      torch.nn.ReLU(),
      torch.nn.Linear(128, 10)
    )

  def forward(self, x):
    conv_out = self.conv1(x)
    res = conv_out.view(conv_out.size(0), -1)
    out = self.dense(res)
    return out

print("Method 2:")
model2 = Net2()
print(model2)

這種方法利用torch.nn.Sequential（）容器進(jìn)行快速搭建，模型的各層被順序添加到容器中。缺點(diǎn)是每層的編號(hào)是默認(rèn)的阿拉伯?dāng)?shù)字，不易區(qū)分。

第三種方法：

# Method 3 -------------------------------
class Net3(torch.nn.Module):
  def __init__(self):
    super(Net3, self).__init__()
    self.conv=torch.nn.Sequential()
    self.conv.add_module("conv1",torch.nn.Conv2d(3, 32, 3, 1, 1))
    self.conv.add_module("relu1",torch.nn.ReLU())
    self.conv.add_module("pool1",torch.nn.MaxPool2d(2))
    self.dense = torch.nn.Sequential()
    self.dense.add_module("dense1",torch.nn.Linear(32 * 3 * 3, 128))
    self.dense.add_module("relu2",torch.nn.ReLU())
    self.dense.add_module("dense2",torch.nn.Linear(128, 10))

  def forward(self, x):
    conv_out = self.conv1(x)
    res = conv_out.view(conv_out.size(0), -1)
    out = self.dense(res)
    return out

print("Method 3:")
model3 = Net3()
print(model3)

這種方法是對(duì)第二種方法的改進(jìn)：通過(guò)add_module()添加每一層，并且為每一層增加了一個(gè)單獨(dú)的名字。

第四種方法：

# Method 4 ------------------------------------------
class Net4(torch.nn.Module):
  def __init__(self):
    super(Net4, self).__init__()
    self.conv = torch.nn.Sequential(
      OrderedDict(
        [
          ("conv1", torch.nn.Conv2d(3, 32, 3, 1, 1)),
          ("relu1", torch.nn.ReLU()),
          ("pool", torch.nn.MaxPool2d(2))
        ]
      ))

    self.dense = torch.nn.Sequential(
      OrderedDict([
        ("dense1", torch.nn.Linear(32 * 3 * 3, 128)),
        ("relu2", torch.nn.ReLU()),
        ("dense2", torch.nn.Linear(128, 10))
      ])
    )

  def forward(self, x):
    conv_out = self.conv1(x)
    res = conv_out.view(conv_out.size(0), -1)
    out = self.dense(res)
    return out

print("Method 4:")
model4 = Net4()
print(model4)

是第三種方法的另外一種寫(xiě)法，通過(guò)字典的形式添加每一層，并且設(shè)置單獨(dú)的層名稱。

完整代碼：

import torch
import torch.nn.functional as F
from collections import OrderedDict

# Method 1 -----------------------------------------

class Net1(torch.nn.Module):
  def __init__(self):
    super(Net1, self).__init__()
    self.conv1 = torch.nn.Conv2d(3, 32, 3, 1, 1)
    self.dense1 = torch.nn.Linear(32 * 3 * 3, 128)
    self.dense2 = torch.nn.Linear(128, 10)

  def forward(self, x):
    x = F.max_pool2d(F.relu(self.conv(x)), 2)
    x = x.view(x.size(0), -1)
    x = F.relu(self.dense1(x))
    x = self.dense2()
    return x

print("Method 1:")
model1 = Net1()
print(model1)


# Method 2 ------------------------------------------
class Net2(torch.nn.Module):
  def __init__(self):
    super(Net2, self).__init__()
    self.conv = torch.nn.Sequential(
      torch.nn.Conv2d(3, 32, 3, 1, 1),
      torch.nn.ReLU(),
      torch.nn.MaxPool2d(2))
    self.dense = torch.nn.Sequential(
      torch.nn.Linear(32 * 3 * 3, 128),
      torch.nn.ReLU(),
      torch.nn.Linear(128, 10)
    )

  def forward(self, x):
    conv_out = self.conv1(x)
    res = conv_out.view(conv_out.size(0), -1)
    out = self.dense(res)
    return out

print("Method 2:")
model2 = Net2()
print(model2)


# Method 3 -------------------------------
class Net3(torch.nn.Module):
  def __init__(self):
    super(Net3, self).__init__()
    self.conv=torch.nn.Sequential()
    self.conv.add_module("conv1",torch.nn.Conv2d(3, 32, 3, 1, 1))
    self.conv.add_module("relu1",torch.nn.ReLU())
    self.conv.add_module("pool1",torch.nn.MaxPool2d(2))
    self.dense = torch.nn.Sequential()
    self.dense.add_module("dense1",torch.nn.Linear(32 * 3 * 3, 128))
    self.dense.add_module("relu2",torch.nn.ReLU())
    self.dense.add_module("dense2",torch.nn.Linear(128, 10))

  def forward(self, x):
    conv_out = self.conv1(x)
    res = conv_out.view(conv_out.size(0), -1)
    out = self.dense(res)
    return out

print("Method 3:")
model3 = Net3()
print(model3)



# Method 4 ------------------------------------------
class Net4(torch.nn.Module):
  def __init__(self):
    super(Net4, self).__init__()
    self.conv = torch.nn.Sequential(
      OrderedDict(
        [
          ("conv1", torch.nn.Conv2d(3, 32, 3, 1, 1)),
          ("relu1", torch.nn.ReLU()),
          ("pool", torch.nn.MaxPool2d(2))
        ]
      ))

    self.dense = torch.nn.Sequential(
      OrderedDict([
        ("dense1", torch.nn.Linear(32 * 3 * 3, 128)),
        ("relu2", torch.nn.ReLU()),
        ("dense2", torch.nn.Linear(128, 10))
      ])
    )

  def forward(self, x):
    conv_out = self.conv1(x)
    res = conv_out.view(conv_out.size(0), -1)
    out = self.dense(res)
    return out

print("Method 4:")
model4 = Net4()
print(model4)

以上就是本文的全部?jī)?nèi)容，希望對(duì)大家的學(xué)習(xí)有所幫助，也希望大家多多支持腳本之家。

您可能感興趣的文章: