如何使用pytorch中的checkpoint模型文件来测试CIFAR-10数据集？

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: Traceback (most recent call last) in () 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'

I think I am not implementing this in right manner!!

Answer 1

Your error isn't from your checkpoint function. If we look at the traceback:

> 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'

The line that we're being told is breaking the line 43:

> ---> 43 model = SqueezeNext()

And the error is:

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

I'm assuming you're using this implementation of SqueezeNext, but whichever implementation you're using, you're not passing all the arguments needed to initialise the model. You'll want to change your code to something like:

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

If you're not using that implementation, you'll need to find the source code for the SqueezeNext model, and see what arguments the __init__ function requires. You can try this:

import inspect

inspect.signature(SqueezeNext.__init__)

Which should give you the signature.