Youngwoo Yoon

늦게 답변 드려 죄송합니다. VideoPose3D 프로젝트를 이용하여 3d pose 를 생성합니다. Pickle 파일이 바로 나오는 것은 아니고 결과 저장을 위한 코드를 작성하셔야 합니다. 3D Pose 부분을 제외하고 2D 포즈 사용으로...

네 저는 VideoPose3D 에서 사용하는 3D 포인트를 기준으로 하였습니다. 따라서 OpenPose 2D 데이터를 3D 로 변환하는 과정에서 포인트 수가 달라졌습니다. 만약 다른 관절 구조(포인트 수)를 쓰신다면 제스처 생성 모델에서 출력...

Hello, @younesbelkada I'm using the same version `0.15.0` of `accelerate`. I also got the correct result when I ran with `export CUDA_VISIBLE_DEVICES=0` Still wrong results with two GPUS `export CUDA_VISIBLE_DEVICES=0,1`

Thanks for the quick replies. This is the result and it still doesn't look good. ``` Hello, nice to meet you. How are!!!!!!!!!!!!!!!!!!!!!!! ``` My original test code with `export...

@younesbelkada, I got the same wrong result with PyTorch 1.13.1. ``` Hello, nice to meet you. How are noise retaliateousy retaliateousy retaliateousy retaliateousy retaliateousy retaliateousy retaliateousy retaliateousy retaliateousy retaliateousy retaliateousy...

I put the test scripts using cpu, gpu0, gpu1, and device_map=auto on a single python file to be sure. ``` from importlib.metadata import version import torch from transformers import AutoModelForCausalLM,...

I moved inputs to cuda:0 and cuda:1 but both gave the same wrong result. Below is the output when I moved inputs to cuda:0. ``` torch 1.13.1 transformers 4.25.1 accelerate...

It works well on another machine with two Quadro 6000 GPUs. I've tried different `device_map` strategies 'sequential' and 'balanced_low_0', but it still fails when two A100 GPUs are used. I...

I solved this problem by disabling ACS in BIOS. This document might be helpful to some of you. https://docs.nvidia.com/deeplearning/nccl/user-guide/docs/troubleshooting.html

I also failed `accelerate test` on a machine with two A100 (80GB) GPUs. Here is my output: ``` Running: accelerate-launch --config_file=None /home/user/anaconda3/envs/task_temp/lib/python3.10/site-packages/accelerate/test_utils/scripts/test_script.py stdout: **Initialization** stdout: Testing, testing. 1, 2, 3....