RuntimeError: "nll_loss_forward_reduce_cuda_kernel_2d_index" not implemented for 'Int'

[oczzz15]

I was able to run train.py and save_features.py successfully, but encountered an issue when running test.py (using Python 3.10 and PyTorch 2.0). The error message is as follows:
Traceback (most recent call last):
File "D:\CloserLookFewShot-master\test.py", line 155, in
acc = feature_evaluation(cl_data_file, model, n_query=15, adaptation=params.adaptation, **few_shot_params)
File "D:\CloserLookFewShot-master\test.py", line 41, in feature_evaluation
scores = model.set_forward(z_all, is_feature=True)
File "D:\CloserLookFewShot-master\methods\baselinefinetune.py", line 15, in set_forward
return self.set_forward_adaptation(x,is_feature) # Baseline always do adaptation
File "D:\CloserLookFewShot-master\methods\baselinefinetune.py", line 48, in set_forward_adaptation
loss = loss_function(scores,y_batch)
File "C:\Users\tangs\miniconda3\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "C:\Users\tangs\miniconda3\lib\site-packages\torch\nn\modules\loss.py", line 1174, in forward
return F.cross_entropy(input, target, weight=self.weight,
File "C:\Users\tangs\miniconda3\lib\site-packages\torch\nn\functional.py", line 3029, in cross_entropy
return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
RuntimeError: "nll_loss_forward_reduce_cuda_kernel_2d_index" not implemented for 'Int'