You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
我在训练一个1080*1920尺寸大约5秒钟的视频,使用ffmpeg提取出约300张图片,同时使用SegmentAndTrackAnything提取出了遮罩。在执行train_multi过程中抛出错误:
RuntimeError: CUDA error: out of memory CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
我在训练一个1080*1920尺寸大约5秒钟的视频,使用ffmpeg提取出约300张图片,同时使用SegmentAndTrackAnything提取出了遮罩。在执行train_multi过程中抛出错误:
RuntimeError: CUDA error: out of memory
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with
TORCH_USE_CUDA_DSAto enable device-side assertions.
我的环境是windows下wsl2,分配了26g内存,显卡是4070ti 12g。
base.yaml
配置:img_wh: [1080, 1920]
canonical_wh: [1080, 1920]
lr: 0.001
bg_loss: 0.003
ref_idx: null # 0
N_xyz_w: [8,8]
flow_loss: 1
flow_step: -1
self_bg: True
deform_hash: True
vid_hash: True
num_steps: 10000
decay_step: [2500, 5000, 7500]
annealed_begin_step: 4000
annealed_step: 4000
save_model_iters: 2000
尝试将视频缩短,只提取出10张图片,但在train的过程仍然中断并抛出CUDA error: out of memory的错误,实在不理解为什么,是哪里配置错误了吗?跑测试用例没有问题。
The text was updated successfully, but these errors were encountered: