Closed LiWentomng closed 2 years ago
Additional information:
The script tools/analysis_tools/benchmark.py
to FPS can run well on other models, like Mask R-CNN
and SOLO
.
The tools/analysis_tools/benchmark.py
need to be refined.
The above error can be resolved by
replacing
cfg.model.pretrained = None
(line 64)
to
if 'pretrained' in cfg.model:
cfg.model.pretrained = None
elif 'init_cfg' in cfg.model.backbone:
cfg.model.backbone.init_cfg = None
Prerequisite
🐞 Describe the bug
When I try the script of the below to get the FPS
python -m torch.distributed.launch --nproc_per_node=1 --master_port=29500 tools/analysis_tools/benchmark.py configs/mask2former/mask2former_r50_lsj_8x2_50e_coco.py work_dirs/mask2former/iter_737500.pth --launcher pytorch
I encounter the below erro:
However, I run the
test.py
as below, it can work well without this error.python tools/test.py configs/mask2former/mask2former_r50_lsj_8x2_50e_coco.py work_dirs/mask2former/iter_737500.pth --eval segm
Look forward to the reply. Thanks!
Environment
sys.platform: linux Python: 3.7.13 (default, Mar 29 2022, 02:18:16) [GCC 7.5.0] CUDA available: True GPU 0,1,2,3,4,5,6,7: Tesla V100-SXM2-32GB CUDA_HOME: /usr/local/cuda-11.4 NVCC: Cuda compilation tools, release 11.4, V11.4.152 GCC: gcc (Ubuntu 5.4.0-6ubuntu1~16.04.12) 5.4.0 20160609 PyTorch: 1.7.1+cu101 PyTorch compiling details: PyTorch built with:
TorchVision: 0.8.2+cu101 OpenCV: 4.6.0 MMCV: 1.5.0 MMCV Compiler: GCC 7.3 MMCV CUDA Compiler: 10.1 MMDetection: 2.25.0+
Additional information
No response