Open Rango-Zhang-Hang opened 1 year ago
I meet this error too!,Have you resolved?
I meet this error too!,Have you resolved?
Sadly no, have u?
have you solve this problem?
我也一样报错
把fp16注释掉,我也遇见了一样的问题,加入fp16 = dict(loss_scale='dynamic'),虽然没有这个问题,但是训练过程中,grad_norm: nan
I am having the same problem...
Thank you for this great work! I followed the instructions and used the nuscenesv1.0 full dataset. But when I run the training code, as I tried multiple times, it always has this error at around epoch 1 [14000/20000]. I was using the provided '.pkl' files to train, so I wonder if anyone also met this problem. I read online that the reason is the inconsistency between the label and the output, but this error appeared during the training process, not at the very first beginning. Thus it is very wired to me.
I attached the report: