RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

[shizishen]

No description provided.

[87003697]

这是来自QQ邮箱的假期自动回复邮件。   您好，我最近正在休假中，无法亲自回复您的邮件。我将在假期结束后，尽快给您回复。

[shizishen]

when i run ucf101 by this commond
python main.py --root_path /media/lisaiwei/data/working_2023_2_27/Efficient-3DCNNs-master --video_path datasets/UCF101_JPG --annotation_path annotation_ucf101_self/ucf101_01.json --result_path results --dataset ucf101 --model_depth 50 --n_classes 101 --batch_size 8 --n_threads 4 --checkpoint 1
there is an error

run
train at epoch 1
Traceback (most recent call last):
File "main.py", line 152, in
train_logger, train_batch_logger)
File "/media/lisaiwei/data/working_2023_2_27/Efficient-3DCNNs-master/train.py", line 34, in train_epoch
prec1, prec5 = calculate_accuracy(outputs.data, targets.data, topk=(1,5))
File "/media/lisaiwei/data/working_2023_2_27/Efficient-3DCNNs-master/utils.py", line 67, in calculate_accuracy
correct_k = correct[:k].view(-1).float().sum(0)
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.