error when I train the model

[czy-0326]

2021-02-23 22:06:27,598 INFO Start training
kitti_models/3DSSD_openPCDet(3DSSD)
epochs: 0it [00:00, ?it/s]
2021-02-23 22:06:28,232 INFO End training kitti_models/3DSSD_openPCDet(3DSSD)
When I run the command python train.py ,it doesnot work ,the problem is in line 3.

[czy-0326]

when I delete the ckpt folder,it can continue ,but I meet the new problem
2021-02-23 22:25:04,173 INFO Start training kitti_models/3DSSD_openPCDet(3DSSD)
epochs: 0%| | 0/80 [00:01<?, ?it/s]
Traceback (most recent call last): | 0/3712 [00:00<?, ?it/s]
File "train.py", line 198, in
main()
File "train.py", line 170, in main
merge_all_iters_to_one_epoch=args.merge_all_iters_to_one_epoch
File "/media/czy/新加卷/3DSSD-pytorch-openPCDet-main/tools/train_utils/train_utils.py", line 93, in train_model
dataloader_iter=dataloader_iter
File "/media/czy/新加卷/3DSSD-pytorch-openPCDet-main/tools/train_utils/train_utils.py", line 40, in train_one_epoch
loss.backward()
File "/home/czy/anaconda3/envs/3dssd/lib/python3.7/site-packages/torch/tensor.py", line 195, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/home/czy/anaconda3/envs/3dssd/lib/python3.7/site-packages/torch/autograd/init.py", line 99, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: Expected isFloatingType(grads[i].type().scalarType()) to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.)

[Mian0429]

when I delete the ckpt folder,it can continue ,but I meet the new problem
2021-02-23 22:25:04,173 INFO Start training kitti_models/3DSSD_openPCDet(3DSSD)
epochs: 0%| | 0/80 [00:01<?, ?it/s]
Traceback (most recent call last): | 0/3712 [00:00<?, ?it/s]
File "train.py", line 198, in
main()
File "train.py", line 170, in main
merge_all_iters_to_one_epoch=args.merge_all_iters_to_one_epoch
File "/media/czy/新加卷/3DSSD-pytorch-openPCDet-main/tools/train_utils/train_utils.py", line 93, in train_model
dataloader_iter=dataloader_iter
File "/media/czy/新加卷/3DSSD-pytorch-openPCDet-main/tools/train_utils/train_utils.py", line 40, in train_one_epoch
loss.backward()
File "/home/czy/anaconda3/envs/3dssd/lib/python3.7/site-packages/torch/tensor.py", line 195, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/home/czy/anaconda3/envs/3dssd/lib/python3.7/site-packages/torch/autograd/init.py", line 99, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: Expected isFloatingType(grads[i].type().scalarType()) to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.)

I met the same error as you when I train on cu101+pytorch1.4+python3.6, and it works when I use cu90+pytorch1.1+python3.6. I don't know why but it works.

[GYE19970220]

same error，any answers?

[3623687277]

same error，any answers?