>>723
ログ出力してなかったから改めて試行、0.6.2、rfdetr-v5

05:11:19 AM ERROR [blend-encode] thread crashed
Traceback (most recent call last):
File "jasna\pipeline_threads.py", line 301, in blend_encode_loop
File "jasna\pipeline_threads.py", line 90, in decode_detect_loop
File "jasna\pipeline_processing.py", line 129, in process_frame_batch
File "jasna\mosaic\rfdetr.py", line 131, in __call__
File "jasna\mosaic\rfdetr.py", line 85, in _preprocess
torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 380.00 MiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Of the allocated memory 712.48 MiB is allocated by PyTorch, and 453.52 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://docs.pytorch.org/docs/stable/notes/cuda.html#optimizing-memory-usage-with-pytorch-cuda-alloc-conf)

NVIDIA GeForce RTX-4060 Laptop GPU 8.00GB
GeForce 591.4 WHQL DCH-[r591_66]