精品人妻系列无码专区,97国产在线播放,亚洲欧美国产伦

主頁 > 知識庫 > PyTorch 遷移學習實踐(幾分鐘即可訓練好自己的模型)

PyTorch 遷移學習實踐(幾分鐘即可訓練好自己的模型)

前言

如果你認為深度學習非常的吃GPU，或者說非常的耗時間，訓練一個模型要非常久，但是你如果了解了遷移學習那你的模型可能只需要幾分鐘，而且準確率不比你自己訓練的模型準確率低，本節(jié)我們將會介紹兩種方法來實現(xiàn)遷移學習

遷移學習方法介紹

微調(diào)網(wǎng)絡的方法實現(xiàn)遷移學習，更改最后一層全連接，并且微調(diào)訓練網(wǎng)絡
將模型看成特征提取器，如果一個模型的預訓練模型非常的好，那完全就把前面的層看成特征提取器，凍結(jié)所有層并且更改最后一層，只訓練最后一層，這樣我們只訓練了最后一層，訓練會非常的快速

遷移基本步驟

數(shù)據(jù)的準備
選擇數(shù)據(jù)增廣的方式
選擇合適的模型
更換最后一層全連接
凍結(jié)層，開始訓練
選擇預測結(jié)果最好的模型保存

需要導入的包

import zipfile # 解壓文件
import torchvision
from torchvision import datasets, transforms, models
import torch
from torch.utils.data import DataLoader, Dataset
import os
import cv2
import numpy as np
import matplotlib.pyplot as plt
from PIL import Image
import copy

數(shù)據(jù)準備

本次實驗的數(shù)據(jù)到這里下載
首先按照上一章節(jié)講的數(shù)據(jù)讀取方法來準備數(shù)據(jù)

# 解壓數(shù)據(jù)到指定文件
def unzip(filename, dst_dir):
  z = zipfile.ZipFile(filename)
  z.extractall(dst_dir)
unzip('./data/hymenoptera_data.zip', './data/')
# 實現(xiàn)自己的Dataset方法，主要實現(xiàn)兩個方法__len__和__getitem__
class MyDataset(Dataset):
  def __init__(self, dirname, transform=None):
    super(MyDataset, self).__init__()
    self.classes = os.listdir(dirname)
    self.images = []
    self.transform = transform
    for i, classes in enumerate(self.classes):
      classes_path = os.path.join(dirname, classes)
      for image_name in os.listdir(classes_path):
        self.images.append((os.path.join(classes_path, image_name), i))
  def __len__(self):
    return len(self.images)
  def __getitem__(self, idx):
    image_name, classes = self.images[idx]
    image = Image.open(image_name)
    if self.transform:
      image = self.transform(image)
    return image, classes
  def get_claesses(self):
    return self.classes
# 分布實現(xiàn)訓練和預測的transform
train_transform = transforms.Compose([
  transforms.Grayscale(3),
  transforms.RandomResizedCrop(224), #隨機裁剪一個area然后再resize
  transforms.RandomHorizontalFlip(), #隨機水平翻轉(zhuǎn)
  transforms.Resize(size=(256, 256)),
  transforms.ToTensor(),
  transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])
val_transform = transforms.Compose([
  transforms.Grayscale(3),
  transforms.Resize(size=(256, 256)),
  transforms.CenterCrop(224),
  transforms.ToTensor(),
  transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])
# 分別實現(xiàn)loader
train_dataset = MyDataset('./data/hymenoptera_data/train/', train_transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=32)
val_dataset = MyDataset('./data/hymenoptera_data/val/', val_transform)
val_loader = DataLoader(val_dataset, shuffle=True, batch_size=32)

選擇預訓練的模型

這里我們選擇了resnet18在ImageNet 1000類上進行了預訓練的

model = models.resnet18(pretrained=True) # 使用預訓練

使用model.buffers查看網(wǎng)絡基本結(jié)構(gòu)

bound method Module.buffers of ResNet(
 (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
 (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
 (relu): ReLU(inplace=True)
 (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
 (layer1): Sequential(
  (0): BasicBlock(
   (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
   (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
   (relu): ReLU(inplace=True)
   (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
   (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  )
  (1): BasicBlock(
   (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
   (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
   (relu): ReLU(inplace=True)
   (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
   (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  )
 )
 (layer2): Sequential(
  (0): BasicBlock(
   (conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
   (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
   (relu): ReLU(inplace=True)
   (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
   (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
   (downsample): Sequential(
    (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
    (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
   )
  )
  (1): BasicBlock(
   (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
   (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
   (relu): ReLU(inplace=True)
   (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
   (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  )
 )
 (layer3): Sequential(
  (0): BasicBlock(
   (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
   (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
   (relu): ReLU(inplace=True)
   (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
   (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
   (downsample): Sequential(
    (0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
    (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
   )
  )
  (1): BasicBlock(
   (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
   (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
   (relu): ReLU(inplace=True)
   (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
   (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  )
 )
 (layer4): Sequential(
  (0): BasicBlock(
   (conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
   (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
   (relu): ReLU(inplace=True)
   (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
   (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
   (downsample): Sequential(
    (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
    (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
   )
  )
  (1): BasicBlock(
   (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
   (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
   (relu): ReLU(inplace=True)
   (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
   (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  )
 )
 (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
 (fc): Linear(in_features=512, out_features=1000, bias=True)
)>

我們現(xiàn)在需要做的就是將最后一層進行替換

only_train_fc = True
if only_train_fc:
  for param in model.parameters():
    param.requires_grad_(False)
fc_in_features = model.fc.in_features
model.fc = torch.nn.Linear(fc_in_features, 2, bias=True)

注釋:only_train_fc如果我們設置為True那么就只訓練最后的fc層
現(xiàn)在觀察一下可導的參數(shù)有那些（在只訓練最后一層的情況下）

for i in model.parameters():
  if i.requires_grad:
    print(i)

Parameter containing:
tensor([[ 0.0342, -0.0336, 0.0279, ..., -0.0428, 0.0421, 0.0366],
    [-0.0162, 0.0286, -0.0379, ..., -0.0203, -0.0016, -0.0440]],
    requires_grad=True)
Parameter containing:
tensor([-0.0120, -0.0086], requires_grad=True)

注釋:由于最后一層使用了bias因此我們會多加兩個參數(shù)

訓練主體的實現(xiàn)

epochs = 50
loss_fn = torch.nn.CrossEntropyLoss()
opt = torch.optim.SGD(lr=0.01, params=model.parameters())
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
# device = torch.device('cpu')
model.to(device)
opt_step = torch.optim.lr_scheduler.StepLR(opt, step_size=20, gamma=0.1)
max_acc = 0
epoch_acc = []
epoch_loss = []
for epoch in range(epochs):
  for type_id, loader in enumerate([train_loader, val_loader]):
    mean_loss = []
    mean_acc = []
    for images, labels in loader:
      if type_id == 0:
        # opt_step.step()
        model.train()
      else:
        model.eval()
      images = images.to(device)
      labels = labels.to(device).long()
      opt.zero_grad()
      with torch.set_grad_enabled(type_id==0):
        outputs = model(images)
        _, pre_labels = torch.max(outputs, 1)
        loss = loss_fn(outputs, labels)
      if type_id == 0:
        loss.backward()
        opt.step()
      acc = torch.sum(pre_labels==labels) / torch.tensor(labels.shape[0], dtype=torch.float32)    
      mean_loss.append(loss.cpu().detach().numpy())
      mean_acc.append(acc.cpu().detach().numpy())
    if type_id == 1:
      epoch_acc.append(np.mean(mean_acc))
      epoch_loss.append(np.mean(mean_loss))
      if max_acc  np.mean(mean_acc):
        max_acc = np.mean(mean_acc)
    print(type_id, np.mean(mean_loss),np.mean(mean_acc))
print(max_acc)

在使用cpu訓練的情況，也能快速得到較好的結(jié)果，這里訓練了50次，其實很快的就已經(jīng)得到了很好的結(jié)果了

總結(jié)

本節(jié)我們使用了預訓練模型，發(fā)現(xiàn)大概10個epoch就可以很快的得到較好的結(jié)果了，即使在使用cpu情況下訓練，這也是遷移學習為什么這么受歡迎的原因之一了，如果讀者有興趣可以自己試一試在不凍結(jié)層的情況下，使用方法一能否得到更好的結(jié)果

到此這篇關(guān)于PyTorch 遷移學習實踐(幾分鐘即可訓練好自己的模型)的文章就介紹到這了,更多相關(guān)PyTorch 遷移內(nèi)容請搜索腳本之家以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持腳本之家！

您可能感興趣的文章:

Pytorch模型遷移和遷移學習,導入部分模型參數(shù)的操作
PyTorch一小時掌握之遷移學習篇

標簽：股票西安日照白城安慶隨州天水錦州

巨人網(wǎng)絡通訊聲明：本文標題《PyTorch 遷移學習實踐(幾分鐘即可訓練好自己的模型)》，本文關(guān)鍵詞 PyTorch,遷移,學習,實踐,幾分鐘,；如發(fā)現(xiàn)本文內(nèi)容存在版權(quán)問題，煩請?zhí)峁┫嚓P(guān)信息告之我們，我們將及時溝通與處理。本站內(nèi)容系統(tǒng)采集于網(wǎng)絡，涉及言論、版權(quán)與本站無關(guān)。