Svyatoslav Pchelintsev
Svyatoslav Pchelintsev
Hmm, that's strange... We have to have the same libraries. What CUDA version do you have? I hope @alcinos can help! Here is the necessary info: - the exact command...
Also, I tried to run fine-tuning in docker with CUDA 10.2 and CUDA 11.1. Again, it works on the CPU but I still get the same mistake on the GPU...
Oh, there is no error with python=3.7.10, torch=1.8.1, torchvision=0.9.1, CUDA=11.1, transformers=4.5.1! With the recommended python=3.8 it also works (I'm using python=3.8.12)
Same here with `jupyterlab=4.2.1` and `jupyter-server-resource-usage=1.0.2`. Are there any plans to fix this, @jtpio? By the way, the `tachometer` shows the CPU load. Moreover, it seems to correctly show the...
@hcscctv, did you run on a headless machine with GPU? I've followed https://github.com/soyeonm/FILM/tree/public/miscellaneous and https://github.com/soyeonm/FILM/blob/public/README.md#additional-preliminaries-to-use-alfred-scenes but I have ended up with `(EE) no screens found(EE)` Xorg error :(( Exactly the...
@hcscctv, could you please share your version of the GPU and the NVIDIA driver you're running on? I've been trying to solve `(EE) no screens found(EE)` but without success... I...
@uyeongkim, I was just looking around and encountered you question. I'm not sure about FILM's deterministic execution (I also wasn't able to reproduce the results), but AI2THOR itself is a...
@hcscctv, after many hours of trying It seems to me that if you don't have root access inside docker, then running Xorg server is impossible. What have I tried and...
Also, I want to mention some other strange places that I've encountered. Maybe someday they will be fixed. 1. What is the purpose of [this](https://github.com/soyeonm/FILM/blob/e27af241352320e79ed81221645f90e14f77cc8d/envs/utils/fmm_planner.py#L112) and [this](https://github.com/soyeonm/FILM/blob/e27af241352320e79ed81221645f90e14f77cc8d/alfred_utils/env/thor_env_code.py#L223) code? :) 2....
@soyeonm, thank you for your fast response! As for 5, should the README file be updated then? The command ``` mv Pretrained_Models_FILM/best_model_multi.pt models/semantic_policy/new_best_model.pt ``` should be ``` mv Pretrained_Models_FILM/new_best_model.pt models/semantic_policy/best_model_multi..pt...