这篇“pytorch怎么实现加载保存查看checkpoint文件”文章的知识点大部分人都不太理解,所以小编给大家总结了以下内容,内容详细,步骤清晰,具有一定的借鉴价值,希望大家阅读完这篇文章能有所收获,下面我们一起来看看这篇“pytorch怎么实现加载保存查看checkpoint文件”文章吧。
# 方式一:保存加载整个state_dict(推荐) # 保存 torch.save(model.state_dict(), PATH) # 加载 model.load_state_dict(torch.load(PATH)) # 测试时不启用 BatchNormalization 和 Dropout model.eval()
# 方式二:保存加载整个模型 # 保存 torch.save(model, PATH) # 加载 model = torch.load(PATH) model.eval()
# 方式三:保存用于继续训练的checkpoint或者多个模型 # 保存 torch.save({ 'epoch': epoch, 'model_state_dict': model.state_dict(), ... }, PATH) # 加载 checkpoint = torch.load(PATH) start_epoch=checkpoint['epoch'] model.load_state_dict(checkpoint['model_state_dict']) # 测试时 model.eval() # 或者训练时 model.train()
# GPU上保存,CPU上加载 # 保存 torch.save(model.state_dict(), PATH) # 加载 device = torch.device('cpu') model.load_state_dict(torch.load(PATH, map_location=device)) # 如果是多gpu保存,需要去除关键字中的module,见第4部分
# GPU上保存,GPU上加载 # 保存 torch.save(model.state_dict(), PATH) # 加载 device = torch.device("cuda") model.load_state_dict(torch.load(PATH)) model.to(device)
# CPU上保存,GPU上加载 # 保存 torch.save(model.state_dict(), PATH) # 加载 device = torch.device("cuda") # 选择希望使用的GPU model.load_state_dict(torch.load(PATH, map_location="cuda:0")) model.to(device)
# 打印模型的 state_dict print("Model's state_dict:") for param_tensor in model.state_dict(): print(param_tensor, "\t", model.state_dict()[param_tensor].size())
多gpu
报错为KeyError: ‘unexpected key “module.conv1.weight” in state_dict’
原因:当使用多gpu时,会使用torch.nn.DataParallel,所以checkpoint中有module字样
#解决1:加载时将module去掉 # 创建一个不包含`module.`的新OrderedDict from collections import OrderedDict new_state_dict = OrderedDict() for k, v in state_dict.items(): name = k[7:] # 去掉 `module.` new_state_dict[name] = v # 加载参数 model.load_state_dict(new_state_dict)
# 解决2:保存checkpoint时不保存module torch.save(model.module.state_dict(), PATH)
'''本文件用于举例说明pytorch保存和加载文件的方法''' import torch as torch import torchvision as tv import torch.nn as nn import torch.optim as optim import torch.nn.functional as F import torchvision.transforms as transforms import os # 参数声明 batch_size = 32 epochs = 10 WORKERS = 0 # dataloder线程数 test_flag = False # 测试标志,True时加载保存好的模型进行测试 ROOT = '/home/pxt/pytorch/cifar' # MNIST数据集保存路径 log_dir = '/home/pxt/pytorch/logs/cifar_model.pth' # 模型保存路径 # 加载MNIST数据集 transform = tv.transforms.Compose([ transforms.ToTensor(), transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])]) train_data = tv.datasets.CIFAR10(root=ROOT, train=True, download=True, transform=transform) test_data = tv.datasets.CIFAR10(root=ROOT, train=False, download=False, transform=transform) train_load = torch.utils.data.DataLoader(train_data, batch_size=batch_size, shuffle=True, num_workers=WORKERS) test_load = torch.utils.data.DataLoader(test_data, batch_size=batch_size, shuffle=False, num_workers=WORKERS) # 构造模型 class Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(3, 64, 3, padding=1) self.conv2 = nn.Conv2d(64, 128, 3, padding=1) self.conv3 = nn.Conv2d(128, 256, 3, padding=1) self.conv4 = nn.Conv2d(256, 256, 3, padding=1) self.pool = nn.MaxPool2d(2, 2) self.fc1 = nn.Linear(256 * 8 * 8, 1024) self.fc2 = nn.Linear(1024, 256) self.fc3 = nn.Linear(256, 10) def forward(self, x): x = F.relu(self.conv1(x)) x = self.pool(F.relu(self.conv2(x))) x = F.relu(self.conv3(x)) x = self.pool(F.relu(self.conv4(x))) x = x.view(-1, x.size()[1] * x.size()[2] * x.size()[3]) x = F.relu(self.fc1(x)) x = F.relu(self.fc2(x)) x = self.fc3(x) return x model = Net().cpu() criterion = nn.CrossEntropyLoss() optimizer = optim.SGD(model.parameters(), lr=0.01) # 模型训练 def train(model, train_loader, epoch): model.train() train_loss = 0 for i, data in enumerate(train_loader, 0): x, y = data x = x.cpu() y = y.cpu() optimizer.zero_grad() y_hat = model(x) loss = criterion(y_hat, y) loss.backward() optimizer.step() train_loss += loss print('正在进行第{}个epoch中的第{}次循环'.format(epoch,i)) loss_mean = train_loss / (i + 1) print('Train Epoch: {}\t Loss: {:.6f}'.format(epoch, loss_mean.item())) # 模型测试 def test(model, test_loader): model.eval() test_loss = 0 correct = 0 with torch.no_grad(): for i, data in enumerate(test_loader, 0): x, y = data x = x.cpu() y = y.cpu() optimizer.zero_grad() y_hat = model(x) test_loss += criterion(y_hat, y).item() pred = y_hat.max(1, keepdim=True)[1] correct += pred.eq(y.view_as(pred)).sum().item() test_loss /= (i + 1) print('Test set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format( test_loss, correct, len(test_data), 100. * correct / len(test_data))) def main(): # 如果test_flag=True,则加载已保存的模型并进行测试,测试以后不进行此模块以后的步骤 if test_flag: # 加载保存的模型直接进行测试机验证 checkpoint = torch.load(log_dir) model.load_state_dict(checkpoint['model']) optimizer.load_state_dict(checkpoint['optimizer']) start_epoch = checkpoint['epoch'] test(model, test_load) return # 如果有保存的模型,则加载模型,并在其基础上继续训练 if os.path.exists(log_dir): checkpoint = torch.load(log_dir) model.load_state_dict(checkpoint['model']) optimizer.load_state_dict(checkpoint['optimizer']) start_epoch = checkpoint['epoch'] print('加载 epoch {} 成功!'.format(start_epoch)) else: start_epoch = 0 print('无保存了的模型,将从头开始训练!') for epoch in range(start_epoch+1, epochs): train(model, train_load, epoch) test(model, test_load) # 保存模型 state = {'model':model.state_dict(), 'optimizer':optimizer.state_dict(), 'epoch':epoch} torch.save(state, log_dir) if __name__ == '__main__': main()
以上就是关于“pytorch怎么实现加载保存查看checkpoint文件”这篇文章的内容,相信大家都有了一定的了解,希望小编分享的内容对大家有帮助,若想了解更多相关的知识内容,请关注亿速云行业资讯频道。
免责声明:本站发布的内容(图片、视频和文字)以原创、转载和分享为主,文章观点不代表本网站立场,如果涉及侵权请联系站长邮箱:is@yisu.com进行举报,并提供相关证据,一经查实,将立刻删除涉嫌侵权内容。