Original Traceback (most recent call last): File "/opt/conda/lib/python3.7/site-packages/torch/nn/parallel/parallel_apply.py", line 61, in _worker output = module(*input, **kwargs) File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/EMS-YOLO/g1-resnet/models/yolo.py", line 131, in forward input[i] = x RuntimeError: expand(torch.cuda.FloatTensor{[8, 5, 3, 320, 320]}, size=[8, 5, 3, 320]): the number of sizes provided (4) must be greater or equal to the number of dimensions in the tensor (5)

[JonYuanHao]

I have create gen1_data by replace train_g1 import dataset_g1T to import give_g1_data, and i have got train.txt and val.txt，but when i run: python train_g1.py，the pre-trained weights is best.pt, cfg file is models/resnet34.yaml.

[sumingming123]

Have you solved this problem? I also encountered the same problem.