RuntimeError: "nll_loss_forward_reduce_cuda_kernel_2d_index" not implemented for 'Int'

[wxqyyds]

C:\Users\15727.conda\envs\pytorch\python.exe C:\Users\15727\Desktop\FixMatch-pytorch-master\train.py
03/08/2024 16:07:44 - WARNING - main - Process rank: -1, device: cuda:0, n_gpu: 1, distributed training: False, 16-bits training: False
03/08/2024 16:07:44 - INFO - main - {'gpu_id': 0, 'num_workers': 4, 'dataset': 'cifar10', 'num_labeled': 4000, 'expand_labels': False, 'arch': 'wideresnet', 'total_steps': 1048576, 'eval_step': 1024, 'start_epoch': 0, 'batch_size': 16, 'lr': 0.03, 'warmup': 0, 'wdecay': 0.0005, 'nesterov': True, 'use_ema': True, 'ema_decay': 0.999, 'mu': 7, 'lambda_u': 1, 'T': 1, 'threshold': 0.95, 'out': 'result', 'resume': '', 'seed': None, 'amp': False, 'opt_level': 'O1', 'local_rank': -1, 'no_progress': False, 'world_size': 1, 'n_gpu': 1, 'device': device(type='cuda', index=0)}
Files already downloaded and verified
03/08/2024 16:07:47 - INFO - models.wideresnet - Model: WideResNet 28x2
03/08/2024 16:07:47 - INFO - main - Total params: 1.47M
03/08/2024 16:07:47 - INFO - main - ***** Running training *****
03/08/2024 16:07:47 - INFO - main - Task = cifar10@4000
03/08/2024 16:07:47 - INFO - main - Num Epochs = 1024
03/08/2024 16:07:47 - INFO - main - Batch size per GPU = 16
03/08/2024 16:07:47 - INFO - main - Total train batch size = 16
03/08/2024 16:07:47 - INFO - main - Total optimization steps = 1048576
0%| | 0/1024 [00:00<?, ?it/s]Traceback (most recent call last):
File "C:\Users\15727\Desktop\FixMatch-pytorch-master\train.py", line 501, in
main()
File "C:\Users\15727\Desktop\FixMatch-pytorch-master\train.py", line 296, in main
train(args, labeled_trainloader, unlabeled_trainloader, test_loader,
File "C:\Users\15727\Desktop\FixMatch-pytorch-master\train.py", line 366, in train
Lx = F.cross_entropy(logits_x, targets_x, reduction='mean')
File "C:\Users\15727.conda\envs\pytorch\lib\site-packages\torch\nn\functional.py", line 3053, 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'
0%| | 0/1024 [00:25<?, ?it/s]