xika1234

Results 4 comments of xika1234

AttributeError: 'Shared2FCBBoxHead' object has no attribute 'use_sigmoid'

TorchVision: 0.10.0+cu102 OpenCV: 4.9.0 MMCV: 1.7.1 MMCV Compiler: GCC 7.3 MMCV CUDA Compiler: 10.2 MMDetection: 2.28.1+

Training stuck after index is created when training from checkpoint

i met the same problem, did you solve it?

training stuck problem

It's a memory leak issue, and after the reference is established,the memory usage keeps increasing until it crashes

AttributeError: 'Shared2FCBBoxHead' object has no attribute 'use_sigmoid'

TorchVision: 0.10.0+cu102 OpenCV: 4.9.0 MMCV: 1.7.1 MMCV Compiler: GCC 7.3 MMCV CUDA Compiler: 10.2 MMDetection: 2.28.1+