[深度應用]·實戰掌握PyTorch圖片分類簡明教程
[深度應用]·實戰掌握PyTorch圖片分類簡明教程
我的網站--> http://www.yansongsong.cn/python
項目GitHub地址--> https://github.com/xiaosongshine/image_classifier_PyTorch/git
1.引文
深度學習的比賽中，圖片分類是很常見的比賽，同時也是很難取得特別高名次的比賽，由於圖片分類已經被你們研究的很透徹，一些開源的網絡很容易取得高分。若是你們還掌握不了使用開源的網絡進行訓練，再慢慢去模型調優，很難取得較好的成績。github
咱們在[PyTorch小試牛刀]實戰六·準備本身的數據集用於訓練講解了如何製做本身的數據集用於訓練，這個教程在此基礎上，進行訓練與應用。數組
2.數據介紹
數據 下載地址bash
此次的實戰使用的數據是交通標誌數據集，共有62類交通標誌。其中訓練集數據有4572張照片（每一個類別大概七十個），測試數據集有2520張照片（每一個類別大概40個）。數據包含兩個子目錄分別train與test：網絡
爲何還須要測試數據集呢？這個測試數據集不會拿來訓練，是用來進行模型的評估與調優。app
train與test每一個文件夾裏又有62個子文件夾，每一個類別在同一個文件夾內：ide
我從中打開一個文件間，把裏面圖片展現出來：學習
其中每張照片都相似下面的例子，100*100*3的大小。100是照片的照片的長和寬，3是什麼呢？這實際上是照片的色彩通道數目，RGB。彩色照片存儲在計算機裏就是以三維數組的形式。咱們送入網絡的也是這些數組。測試
3.網絡構建
1.導入Python包，定義一些參數
import torch as t
import torchvision as tv
import os
import time
import numpy as np
from tqdm import tqdm
class DefaultConfigs(object):
data_dir = "./traffic-sign/"
data_list = ["train","test"]
lr = 0.001
epochs = 10
num_classes = 62
image_size = 224
batch_size = 40
channels = 3
gpu = "0"
train_len = 4572
test_len = 2520
use_gpu = t.cuda.is_available()
config = DefaultConfigs()
2.數據準備，採用PyTorch提供的讀取方式（具體內容參考[PyTorch小試牛刀]實戰六·準備本身的數據集用於訓練）
注意一點Train數據須要進行隨機裁剪，Test數據不要進行裁剪了
normalize = tv.transforms.Normalize(mean = [0.485, 0.456, 0.406],
std = [0.229, 0.224, 0.225]
)
transform = {
config.data_list[0]:tv.transforms.Compose(
[tv.transforms.Resize([224,224]),tv.transforms.CenterCrop([224,224]),
tv.transforms.ToTensor(),normalize]#tv.transforms.Resize 用於重設圖片大小
) ,
config.data_list[1]:tv.transforms.Compose(
[tv.transforms.Resize([224,224]),tv.transforms.ToTensor(),normalize]
)
}
datasets = {
x:tv.datasets.ImageFolder(root = os.path.join(config.data_dir,x),transform=transform[x])
for x in config.data_list
}
dataloader = {
x:t.utils.data.DataLoader(dataset= datasets[x],
batch_size=config.batch_size,
shuffle=True
)
for x in config.data_list
}
3.構建網絡模型（使用resnet18進行遷移學習，訓練參數爲最後一個全鏈接層 t.nn.Linear(512,num_classes)）
def get_model(num_classes):
model = tv.models.resnet18(pretrained=True)
for parma in model.parameters():
parma.requires_grad = False
model.fc = t.nn.Sequential(
t.nn.Dropout(p=0.3),
t.nn.Linear(512,num_classes)
)
return(model)
若是電腦硬件支持，能夠把下述代碼屏蔽，則訓練整個網絡，最終準確率會上升，訓練數據會變慢。
for parma in model.parameters():
parma.requires_grad = False
模型輸出
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)
(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)
(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)
(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)
(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)
(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)
(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)
(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)
(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)
(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): AvgPool2d(kernel_size=7, stride=1, padding=0)
(fc): Sequential(
(0): Dropout(p=0.3)
(1): Linear(in_features=512, out_features=62, bias=True)
)
)
4.訓練模型（支持自動GPU加速，GPU使用教程參考：[開發技巧]·PyTorch如何使用GPU加速）
def train(epochs):
model = get_model(config.num_classes)
print(model)
loss_f = t.nn.CrossEntropyLoss()
if(config.use_gpu):
model = model.cuda()
loss_f = loss_f.cuda()
opt = t.optim.Adam(model.fc.parameters(),lr = config.lr)
time_start = time.time()
for epoch in range(epochs):
train_loss = []
train_acc = []
test_loss = []
test_acc = []
model.train(True)
print("Epoch {}/{}".format(epoch+1,epochs))
for batch, datas in tqdm(enumerate(iter(dataloader["train"]))):
x,y = datas
if (config.use_gpu):
x,y = x.cuda(),y.cuda()
y_ = model(x)
#print(x.shape,y.shape,y_.shape)
_, pre_y_ = t.max(y_,1)
pre_y = y
#print(y_.shape)
loss = loss_f(y_,pre_y)
#print(y_.shape)
acc = t.sum(pre_y_ == pre_y)
loss.backward()
opt.step()
opt.zero_grad()
if(config.use_gpu):
loss = loss.cpu()
acc = acc.cpu()
train_loss.append(loss.data)
train_acc.append(acc)
#if((batch+1)%5 ==0):
time_end = time.time()
print("Batch {}, Train loss:{:.4f}, Train acc:{:.4f}, Time: {}"\
.format(batch+1,np.mean(train_loss)/config.batch_size,np.mean(train_acc)/config.batch_size,(time_end-time_start)))
time_start = time.time()
model.train(False)
for batch, datas in tqdm(enumerate(iter(dataloader["test"]))):
x,y = datas
if (config.use_gpu):
x,y = x.cuda(),y.cuda()
y_ = model(x)
#print(x.shape,y.shape,y_.shape)
_, pre_y_ = t.max(y_,1)
pre_y = y
#print(y_.shape)
loss = loss_f(y_,pre_y)
acc = t.sum(pre_y_ == pre_y)
if(config.use_gpu):
loss = loss.cpu()
acc = acc.cpu()
test_loss.append(loss.data)
test_acc.append(acc)
print("Batch {}, Test loss:{:.4f}, Test acc:{:.4f}".format(batch+1,np.mean(test_loss)/config.batch_size,np.mean(test_acc)/config.batch_size))
t.save(model,str(epoch+1)+"ttmodel.pkl")
if __name__ == "__main__":
train(config.epochs)
訓練結果以下：
def train(epochs):
model = get_model(config.num_classes)
print(model)
loss_f = t.nn.CrossEntropyLoss()
if(config.use_gpu):
model = model.cuda()
loss_f = loss_f.cuda()
opt = t.optim.Adam(model.fc.parameters(),lr = config.lr)
time_start = time.time()
for epoch in range(epochs):
train_loss = []
train_acc = []
test_loss = []
test_acc = []
model.train(True)
print("Epoch {}/{}".format(epoch+1,epochs))
for batch, datas in tqdm(enumerate(iter(dataloader["train"]))):
x,y = datas
if (config.use_gpu):
x,y = x.cuda(),y.cuda()
y_ = model(x)
#print(x.shape,y.shape,y_.shape)
_, pre_y_ = t.max(y_,1)
pre_y = y
#print(y_.shape)
loss = loss_f(y_,pre_y)
#print(y_.shape)
acc = t.sum(pre_y_ == pre_y)
loss.backward()
opt.step()
opt.zero_grad()
if(config.use_gpu):
loss = loss.cpu()
acc = acc.cpu()
train_loss.append(loss.data)
train_acc.append(acc)
#if((batch+1)%5 ==0):
time_end = time.time()
print("Batch {}, Train loss:{:.4f}, Train acc:{:.4f}, Time: {}"\
.format(batch+1,np.mean(train_loss)/config.batch_size,np.mean(train_acc)/config.batch_size,(time_end-time_start)))
time_start = time.time()
model.train(False)
for batch, datas in tqdm(enumerate(iter(dataloader["test"]))):
x,y = datas
if (config.use_gpu):
x,y = x.cuda(),y.cuda()
y_ = model(x)
#print(x.shape,y.shape,y_.shape)
_, pre_y_ = t.max(y_,1)
pre_y = y
#print(y_.shape)
loss = loss_f(y_,pre_y)
acc = t.sum(pre_y_ == pre_y)
if(config.use_gpu):
loss = loss.cpu()
acc = acc.cpu()
test_loss.append(loss.data)
test_acc.append(acc)
print("Batch {}, Test loss:{:.4f}, Test acc:{:.4f}".format(batch+1,np.mean(test_loss)/config.batch_size,np.mean(test_acc)/config.batch_size))
t.save(model,str(epoch+1)+"ttmodel.pkl")
if __name__ == "__main__":
train(config.epochs)
訓練10個Epoch，測試集準確率能夠到達0.86，已經達到不錯效果。經過修改參數，增長訓練，能夠達到更高的準確率。
相關文章
- 1. [深度應用]·實戰掌握Dlib人臉識別開發教程
- 2. pytorch實戰（一）簡單卷積網絡CIFAR10圖片分類
- 3. 【Pytorch實戰】CNN多分類 （MNIST圖片數據集分類）
- 4. Pytorch 深度學習實戰教程（五）：今天，你垃圾分類了嗎？
- 5. git簡單教程--10分鐘掌握
- 6. UML類圖簡明教程
- 7. 掌握深度學習，爲什麼要用 PyTorch、TensorFlow 框架？
- 8. PyTorch快速入門教程六(使用LSTM作圖片分類)
- 9. 視頻教程-深度學習-Pytorch項目實戰－垃圾分類-深度學習
- 10. tensorflow的簡單應用，圖片分類
- 更多相關文章...
- • XML 應用程序 - XML 教程
- • PHP imagecolorallocatealpha - 爲一幅圖像分配顏色和透明度 - PHP參考手冊
- • Github 簡明教程
- • Git五分鐘教程
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
最新文章
歡迎關注本站公眾號,獲取更多信息
相關文章