SMY1999 Samuel Young comments

Results 14 comments of


                                            SMY1999 Samuel Young

Training problem :

I meet similar problem： Traceback (most recent call last): File "train.py", line 170, in loss=optNet(outs,sample_pix_num,ratio,frame_ids,debug_root) File "/home/smy/anaconda3/envs/SelfRecon/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/smy/anaconda3/projects/SelfRecon/model/network.py", line 494, in forward...

Training problem :

> I meet similar problem： Traceback (most recent call last): File "train.py", line 170, in loss=optNet(outs,sample_pix_num,ratio,frame_ids,debug_root) File "/home/smy/anaconda3/envs/SelfRecon/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/smy/anaconda3/projects/SelfRecon/model/network.py", line 494, in...

CUDA out of memory

[zhihu](https://zhuanlan.zhihu.com/p/581606031) `import os os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "max_split_size_mb:128"`

when reading checkpoint file tensorflow.python.framework.errors_impl.OutOfRangeError

看了大家的讨论，原因应该是解压的时候，ckpt文件损坏了，换一个系统来解压，就好了。