conda create --name pytorch170_py3_7 python=3.7
conda activate pytorch170_py3_7
官网上面找与本机cuda对应的版本安装
# CUDA 10.1
conda install pytorch==1.7.0 torchvision==0.8.0 torchaudio==0.7.0 cudatoolkit=10.1 -c pytorch
# CPU Only
conda install pytorch==1.7.0 torchvision==0.8.0 cpuonly -c pytorch
python
import torch
print(torch.__version__) //查看pytorch版本
print(torch.version.cuda) //查看cuda版本
print(torch.cuda.is_available()) //验证cuda是否可用
在训练数据目录下新建 train 和 val 两个文件夹
在train文件夹下新建 各个分类文件夹。如：class1,class2,class3,class4
在val文件夹下同样如此
将不同分类的图片放到个子文件夹里面
#最终文件结构为
-数据集根目录:
----------------train:
----------------------class1
----------------------class2
----------------------class3
----------------------class4
----------------val:
----------------------class1
----------------------class2
----------------------class3
----------------------class4
from __future__ import print_function
from __future__ import division
import torch
import torch.nn as nn
import torch.optim as optim
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import os
import copy
#训练数据目录
data_dir = "./DataSets"
# 选择训练网络 [resnet, alexnet, vgg, squeezenet, densenet, inception]
model_name = "resnet"
#权重文件输出目录及名称
output_path="./resnet152.pth"
#学习率
lr_rate=0.001
# 种类数目
num_classes = 4
# Batch Size取决你电脑内存大小
batch_size = 8
# 训练次数
num_epochs = 500
# False时候更新所有参数，True时候只更新最后一层的参数
feature_extract = False
def train_model(model, dataloaders, criterion, optimizer, num_epochs=25, is_inception=False):
since = time.time()
val_acc_history = []
val_loss_history=[]
train_acc_history = []
train_loss_history=[]
best_model_wts = copy.deepcopy(model.state_dict())
best_acc = 0.0
for epoch in range(num_epochs):
print('Epoch {}/{}'.format(epoch, num_epochs - 1))
print('-' * 10)
# Each epoch has a training and validation phase
for phase in ['train', 'val']:
if phase == 'train':
model.train() # Set model to training mode
else:
model.eval() # Set model to evaluate mode
running_loss = 0.0
running_corrects = 0
# Iterate over data.
for inputs, labels in dataloaders[phase]:
inputs = inputs.to(device)
labels = labels.to(device)
# zero the parameter gradients
optimizer.zero_grad()
# forward
# track history if only in train
with torch.set_grad_enabled(phase == 'train'):
# Get model outputs and calculate loss
# Special case for inception because in training it has an auxiliary output. In train
# mode we calculate the loss by summing the final output and the auxiliary output
# but in testing we only consider the final output.
if is_inception and phase == 'train':
# From https://discuss.pytorch.org/t/how-to-optimize-inception-model-with-auxiliary-classifiers/7958
outputs, aux_outputs = model(inputs)
loss1 = criterion(outputs, labels)
loss2 = criterion(aux_outputs, labels)
loss = loss1 + 0.4*loss2
else:
outputs = model(inputs)
loss = criterion(outputs, labels)
_, preds = torch.max(outputs, 1)
# backward + optimize only if in training phase
if phase == 'train':
loss.backward()
optimizer.step()
# statistics
running_loss += loss.item() * inputs.size(0)
running_corrects += torch.sum(preds == labels.data)
epoch_loss = running_loss / len(dataloaders[phase].dataset)
epoch_acc = running_corrects.double() / len(dataloaders[phase].dataset)
print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))
# deep copy the model
if phase == 'val' and epoch_acc > best_acc:
best_acc = epoch_acc
best_model_wts = copy.deepcopy(model.state_dict())
if phase == 'train':
train_acc_history.append(epoch_acc)
train_loss_history.append(epoch_loss)
else:
val_acc_history.append(epoch_acc)
val_loss_history.append(epoch_loss)
print()
time_elapsed = time.time() - since
print('Training complete in {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))
print('Best val Acc: {:4f}'.format(best_acc))
# load best model weights
model.load_state_dict(best_model_wts)
return model, train_acc_history,train_loss_history,val_acc_history,val_loss_history
def set_parameter_requires_grad(model, feature_extracting):
if feature_extracting:
for param in model.parameters():
param.requires_grad = False
def initialize_model(model_name, num_classes, feature_extract, use_pretrained=True):
# Initialize these variables which will be set in this if statement. Each of these
# variables is model specific.
model_ft = None
input_size = 0
if model_name == "resnet":
""" Resnet152
"""
model_ft = models.resnet152(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, num_classes)
input_size = 480 #224
elif model_name == "alexnet":
""" Alexnet
"""
model_ft = models.alexnet(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
num_ftrs = model_ft.classifier[6].in_features
model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)
input_size = 224
elif model_name == "vgg":
""" VGG11_bn
"""
model_ft = models.vgg11_bn(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
num_ftrs = model_ft.classifier[6].in_features
model_ft.classifier[6] = nn.Linear(num_ftrs,num_classes)
input_size = 224
elif model_name == "squeezenet":
""" Squeezenet
"""
model_ft = models.squeezenet1_0(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
model_ft.classifier[1] = nn.Conv2d(512, num_classes, kernel_size=(1,1), stride=(1,1))
model_ft.num_classes = num_classes
input_size = 224
elif model_name == "densenet":
""" Densenet
"""
model_ft = models.densenet121(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
num_ftrs = model_ft.classifier.in_features
model_ft.classifier = nn.Linear(num_ftrs, num_classes)
input_size = 224
elif model_name == "inception":
""" Inception v3
Be careful, expects (299,299) sized images and has auxiliary output
"""
model_ft = models.inception_v3(pretrained=use_pretrained)
set_parameter_requires_grad(model_ft, feature_extract)
# Handle the auxilary net
num_ftrs = model_ft.AuxLogits.fc.in_features
model_ft.AuxLogits.fc = nn.Linear(num_ftrs, num_classes)
# Handle the primary net
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs,num_classes)
input_size = 299
else:
print("Invalid model name, exiting...")
exit()
return model_ft, input_size
if __name__ == '__main__':
print("PyTorch Version: ",torch.__version__)
print("Torchvision Version: ",torchvision.__version__)
# Initialize the model for this run
model_ft, input_size = initialize_model(model_name, num_classes, feature_extract, use_pretrained=True)
# Print the model we just instantiated
print(model_ft)
data_transforms = {
'train': transforms.Compose([
transforms.RandomResizedCrop(input_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
'val': transforms.Compose([
transforms.Resize(input_size),
transforms.CenterCrop(input_size),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
}
print("Initializing Datasets and Dataloaders...")
# Create training and validation datasets
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in ['train', 'val']}
# Create training and validation dataloaders
dataloaders_dict = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=batch_size, shuffle=True, num_workers=4) for x in ['train', 'val']}
# Detect if we have a GPU available
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# Send the model to GPU
model_ft = model_ft.to(device)
params_to_update = model_ft.parameters()
print("Params to learn:")
if feature_extract:
params_to_update = []
for name,param in model_ft.named_parameters():
if param.requires_grad == True:
params_to_update.append(param)
print("\t",name)
else:
for name,param in model_ft.named_parameters():
if param.requires_grad == True:
print("\t",name)
# Observe that all parameters are being optimized
optimizer_ft = optim.SGD(params_to_update, lr=lr_rate, momentum=0.9)
# Setup the loss fxn
criterion = nn.CrossEntropyLoss()
# Train and evaluate
model_ft, trainacc,trainloss,valacc,valloss = train_model(model_ft, dataloaders_dict, criterion, optimizer_ft, num_epochs=num_epochs, is_inception=(model_name=="inception"))
torch.save(model_ft.state_dict(), output_path)
plt.title("Acc&Loss")
plt.xlabel("Training Epochs")
plt.ylabel("Value")
plt.plot(range(1,num_epochs+1),trainacc,label="TrainAcc")
plt.plot(range(1,num_epochs+1),trainloss,label="TrainLoss")
plt.plot(range(1,num_epochs+1),valacc,label="ValAcc")
plt.plot(range(1,num_epochs+1),valloss,label="ValLoss")
plt.ylim((0,1.))
plt.xticks(np.arange(1, num_epochs+1, 1.0))
plt.legend()
plt.show()
python finetuning_torchvision_models_tutorial.py
# -*- coding: utf-8 -*-
#!/usr/bin/python
# -*- coding: UTF-8 -*-
import torchvision as tv
import torchvision.transforms as transforms
import torch
from PIL import Image
import torch.nn as nn
input_size = 480
names = ['class1', 'class2','class3','class4']
def pridict():
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model=tv.models.resnet152()
num_ftrs = model.fc.in_features
model.fc = nn.Linear(num_ftrs, 4) # 分类数量
model.load_state_dict(torch.load("resnet152.pth"))
model = model.to(device)
model.eval() # 预测模式
# 获取测试图片，并行相应的处理
img = Image.open('4.jpg')
transform = transforms.Compose([
transforms.Resize(input_size),
transforms.CenterCrop(input_size),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])
img = transform(img)
img = img.unsqueeze(0)
img = img.to(device)
with torch.no_grad():
py = model(img)
_, predicted = torch.max(py, 1) # 获取分类结果
classIndex_ = predicted[0]
print('预测结果', names[classIndex_])
if __name__ == '__main__':
pridict()
将模型转换为c++可用的模型
import torch
import torchvision
import torch.nn as nn
#model = torchvision.models.resnet50(pretrained=True)
model=torchvision.models.resnet152()
num_ftrs = model.fc.in_features
model.fc = nn.Linear(num_ftrs, 4) # make the change
model.load_state_dict(torch.load("resnet152.pth"))
model.eval()
example = torch.rand(1, 3, 480, 480)
traced_script_module = torch.jit.trace(model, example)
traced_script_module.save("resnet152.pt")