Open SuhZhang opened 2 years ago
I met the question for I use remote tool in VS Code. but finally I still met the same question as here when I used VNC. Please pay attention to the question through the link, and if anyone has solved the problem, please share any idea. This issue is closed.
I met the question for I use remote tool in VS Code. but finally I still met the same question as here when I used VNC. Please pay attention to the question through the link, and if anyone has solved the problem, please share any idea. This issue is closed.
I have solved the 'embed_dim', 'ape' & 'use_checkpoint' problem referring to here. But I meet the problem in this issue again. I would be appreciate if anyone could give me some suggestions.
I tried to reimplementation Swin-B on COCO, I just git the repository on Github and download the model file through the link in README. But when test the model by:
python tools/test.py configs/swin/cascade_mask_rcnn_swin_base_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_3x_coco.py checkpoint/cascade_mask_rcnn_swin_base_patch4_window7.pth --eval bbox segm
Firstly, I think maybe the memory of GPU is not enough, but when the process is running, I use command
nvidia-smi
:Seems that all things are right. I don't know what's wrong, hope someone could give me help!!! By the way, I have only modified the code in _./configs/base/datasets/cocoinstance.py and _configs/base/datasets/coco_instancesemantic.py, just the path of COCO dataset.
Here is my environment:
sys.platform: linux Python: 3.7.11 (default, Jul 27 2021, 14:32:16) [GCC 7.5.0] CUDA available: True GPU 0: GeForce GTX 1080 Ti CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 10.1, V10.1.243 GCC: gcc (Ubuntu 5.4.0-6ubuntu1~16.04.12) 5.4.0 20160609 PyTorch: 1.6.0 PyTorch compiling details: PyTorch built with:
TorchVision: 0.7.0 OpenCV: 4.5.3 MMCV: 1.3.14 MMCV Compiler: GCC 7.3 MMCV CUDA Compiler: 10.1 MMDetection: 2.11.0+6a979e2