Question

model = SqueezeNext()
model = model.to(device)

def load_checkpoint(model, optimizer, losslogger, filename='SqNxt_23_1x_Cifar.ckpt'):
# Note: Input model & optimizer should be pre-defined.  This routine only updates their states.
start_epoch = 0
if os.path.isfile(filename):
    print("=> loading checkpoint '{}'".format(filename))
    checkpoint = torch.load(filename)
    start_epoch = checkpoint['epoch']
    model.load_state_dict(checkpoint['state_dict'])
    optimizer.load_state_dict(checkpoint['optimizer'])
    losslogger = checkpoint['losslogger']
    print("=> loaded checkpoint '{}' (epoch {})"
              .format(filename, checkpoint['epoch']))
else:
    print("=> no checkpoint found at '{}'".format(filename))


return model, optimizer, start_epoch, losslogger

model, optimizer, start_epoch, losslogger = load_checkpoint(model, optimizer, losslogger)

TypeError：回溯（最近一次通话最近）在（）中 41 test_loader = torch.utils.data.DataLoader（test_dataset，batch_size = 80，num_workers = 8，shuffle = False） 42 ---> 43模型= SqueezeNext（） 44型号= model.to（设备） 45 def load_checkpoint（模型，优化器，损失记录器，文件名='SqNxt_23_1x_Cifar.ckpt'）：TypeError： init （）missing 3 必需的位置参数：“ width_x”，“ blocks”和“ num_classes”

我认为我没有以正确的方式实现这一目标！

Answer 1

您的错误不是来自检查点函数。如果我们回溯一下：

> TypeError: Traceback (most recent call last)
> <ipython-input-51-94c8be648862> in <module>()
>      41 test_loader   = torch.utils.data.DataLoader(test_dataset, batch_size=80, num_workers=8, shuffle=False)
>      42 
> ---> 43 model = SqueezeNext()
>      44 model = model.to(device)
>      45 def load_checkpoint(model, optimizer, losslogger, filename='SqNxt_23_1x_Cifar.ckpt'): TypeError: __init__() missing 3
> required positional arguments: 'width_x', 'blocks', and 'num_classes'

我们被告知的行打破了第43行：

> ---> 43 model = SqueezeNext()

错误是：

> required positional arguments: 'width_x', 'blocks', and 'num_classes'

我假设您正在使用SqueezeNext的this implementation，但是无论使用哪种实现，都不会传递初始化模型所需的所有参数。您需要将代码更改为以下内容：

model = SqueezeNext(width_x=1.0, blocks=[6, 6, 8, 1], num_classes=10)

如果不使用该实现，则需要找到SqueezeNext模型的源代码，并查看__init__函数需要哪些参数。您可以尝试以下方法：

import inspect

inspect.signature(SqueezeNext.__init__)

应该给您签名。

如何在pytorch中使用检查点模型文件来测试CIFAR-10数据集？

1 个答案: