Closed wanxinjun closed 2 years ago
sys.platform: linux Python: 3.7.11 (default, Jul 27 2021, 14:32:16) [GCC 7.5.0] CUDA available: True GPU 0,1,2,3: GeForce GTX 1080 CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 9.0, V9.0.176 GCC: gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-28) PyTorch: 1.5.1 PyTorch compiling details: PyTorch built with:
TorchVision: 0.6.0a0+35d732a OpenCV: 4.5.3 MMCV: 1.2.0 MMCV Compiler: GCC 7.3 MMCV CUDA Compiler: 10.1 MMSegmentation: 0.7.0+e3674fe
The script demo/image_demo.py
is from mmsegmentation. Our code currently does not support inference on a single image.
I will delete these scripts since they are misleading.
Thanks for your error report and we appreciate it a lot.
What command or script did you run? python demo/image_demo.py demo/demo.png configs/bpr/hrnet48_256.py checkpoints/hrnet48_256-cbf4922c.pth
Please run
python mmseg/utils/collect_env.py
to collect necessary environment infomation and paste it here. TorchVision: 0.6.0a0+35d732a OpenCV: 4.5.3 MMCV: 1.2.0 MMCV Compiler: GCC 7.3 MMCV CUDA Compiler: 10.1 MMSegmentation: 0.7.0+e3674feError traceback
If applicable, paste the error trackback here.
Traceback (most recent call last): File "demo/image_demo.py", line 29, in
main()
File "demo/image_demo.py", line 23, in main
result = inference_segmentor(model, args.img)
File "/home/wanxinjun/anaconda3/envs/BPR/lib/python3.7/site-packages/mmsegmentation-0.7.0-py3.7.egg/mmseg/apis/inference.py", line 86, in inference_segmentor
data = test_pipeline(data)
File "/home/wanxinjun/anaconda3/envs/BPR/lib/python3.7/site-packages/mmsegmentation-0.7.0-py3.7.egg/mmseg/datasets/pipelines/compose.py", line 40, in call
data = t(data)
File "/home/wanxinjun/anaconda3/envs/BPR/lib/python3.7/site-packages/mmsegmentation-0.7.0-py3.7.egg/mmseg/datasets/pipelines/loading.py", line 125, in call
filename = results['ann_info']['seg_map']
KeyError: 'ann_info'
If you have already identified the reason, you can provide the information here. If you are willing to create a PR to fix it, please also leave a comment here and that would be much appreciated!