TypeWriter4017

I found one of the reasons for this error is that the compiler can't find the 'cpu.py'. In particular, because the name of package is the same as the name...

A simple solution is that we can copy the files in packeage ` enconding` to project dir `encoding`. The comands are as follows. ``` cp /home/user/.conda/envs/Pytorch-Encoding/lib/python3.6/site-packages/torch_encoding-1.2.2b20210908-py3.6-linux-x86_64.egg/encoding/cpu.py /home/user/PyTorch-Encoding/encoding/ cp /home/user/.conda/envs/Pytorch-Encoding/lib/python3.6/site-packages/torch_encoding-1.2.2b20210908-py3.6-linux-x86_64.egg/encoding/cpu.cpython-36m-x86_64-linux-gnu.so /home/user/PyTorch-Encoding/encoding/...

> > > > i got it > > > > > > > > > 如果问题解决了，可以分享一下经验。谢谢！ > > > > > > 可能有两个原因： > > pytorch 版本的问题 > >...

> Hi, I have modified your code to train an EfficientNet-SSD. After the first 10,000 iterations (loss converged to 7), I picked up the model and evaluated it on COCO2017....

@zzy0428 I met the same problem. Do you have any solution? This is part of the error log. `Error executing job with overrides: ['dataset.category=tv', 'dataloader.batch_size=24', 'dataloader.num_workers=8', 'run.vis_before_training=True', 'run.val_before_training=True', 'run.name=train__hydrant__ebs_24'] Traceback...