Mahzad Khoshlessan

@timmeinhardt No. I just wanted to mention what case I am running. I see. If I want to get one single output from the transformer decoder, what would be the...

@timmeinhardt Where are the auxiliary losses defined? I did not find them in the paper?

Does that mean the transformer has losses besides the ones that are introduced in the paper?

@Arthur151 Yes I had the same understanding. Do you have any resolution? How can I avoid this error? How did you guys avoid it when using data parallel?

@Arthur151 Thanks! It works with this solution!

@fanninpm So this is not an existing feature right now? Is there a workaround to get my package running?

@Arthur151 It doesnot seem to be related to `torch.utils.bottleneck`. When I run `(/z/home/mahzad-khosh/env/romp2) mahzad-khosh@prism:/z/home/mahzad-khosh/ROMP/romp$ python -m torch.utils.bottleneck train.py --configs_yml='configs/v1_hrnet_3dpw_ft.yml'` I get the following error. It has to do with the...

@vivi90 Python version is `3.8.13`, Operating system `Ubuntu 20.04.3 LTS`, Here is the output of the `pip freeze`: ``` absl-py==1.0.0 addict==2.4.0 aiohttp==3.8.1 aiosignal==1.2.0 anyio==3.5.0 argon2-cffi==21.3.0 argon2-cffi-bindings==21.2.0 asttokens==2.0.5 async-timeout==4.0.2 attrs==21.4.0 autobahn==22.4.2...

Hi @Arthur151, I have a question for you. If I want to evaluate the performance of the pre-trained backbones `pretrain_hrnet.pkl` and `pretrain_resnet.pkl` what would be the best way given that...

@Arthur151 I did try romp.train. Even with that I get the error. Here is what I get: ``` ***************************************** /z/home/mahzad-khosh/env/romp/bin/python: can't open file 'romp.train': [Errno 2] No such file or...