pytorch加载训练好的模型用来测试或者处理方式

import torchvision.models as models
resnet50 = models.resnet50(pretrained=True)

model =torchvision.models.resnet50(pretrained=False)

import torchvision.models as models
resnet18 = models.resnet18()
alexnet = models.alexnet()
squeezenet = models.squeezenet1_0()
densenet = models.densenet_161()

resnet.conv1 = nn.Conv2d(4, 64, kernel_size=7, stride=2, padding=3, bias=False)
resnet.fc = nn.Linear(2048, 21)

#加载model，model是自己定义好的模型
resnet50 = models.resnet50(pretrained=True) 
model =Net(...) 
#读取参数 
pretrained_dict =resnet50.state_dict() 
model_dict = model.state_dict() 
#将pretrained_dict里不属于model_dict的键剔除掉 
pretrained_dict =  {k: v for k, v in pretrained_dict.items() if k in model_dict} 
# 更新现有的model_dict 
model_dict.update(pretrained_dict) 
# 加载我们真正需要的state_dict
model.load_state_dict(model_dict)
# 加载我们真正需要的state_dict 
model.load_state_dict(model_dict)  

# 保存
torch.save(model_object, Path)
# 加载
model = torch.load(Path)

# ----------------保存模型参数--------------------------
torch.save(model.state_dict(), PATH)
#example
torch.save(resnet50.state_dict(),'ckp/model.pth')    
# ----------------加载模型参数--------------------------
model = ModelClass(*args, **kwargs) # 这是你后来设置的模型
model.load_state_dict(torch.load(PATH)) # 加载参数
#example
resnet=resnet50(pretrained=True)
resnet.load_state_dict(torch.load('ckp/model.pth'))

for epoch in range(start_epoch, nEpochs + 1):
        train(training_data_loader, optimizer, model, criterion, epoch)
        save_checkpoint(model, epoch)
def save_checkpoint(model, epoch):
    model_out_path = "checkpoint/" + "model_epoch_{}.pth".format(epoch)
    state = {"epoch": epoch ,"model": model}
    if not os.path.exists("checkpoint/"):
        os.makedirs("checkpoint/")
    torch.save(state, model_out_path)
    print("Checkpoint saved to {}".format(model_out_path))