Due to device limitations, I use only 2 GPUs (Tesla K80), each 12GB with 4 Batch-Size.
After the first round of train and evaluation, it stops with this error.
RuntimeError: CUDA error: the launch timed out and was terminated
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.
Hi, I am trying to run an experiment with COCO-additional using this yaml configuration file: https://github.com/facebookresearch/unbiased-teacher/blob/main/configs/coco_additional/faster_rcnn_R_50_FPN_focal_cross_coco_unsupW2.yaml
Due to device limitations, I use only 2 GPUs (Tesla K80), each 12GB with 4 Batch-Size.
After the first round of train and evaluation, it stops with this error.