Closed Alexwong-1024 closed 10 months ago
I'm using the official example scripts/configs for the officially supported tasks/models/datasets.
master branch https://github.com/open-mmlab/mmrotate
The environment you require.
] 0/30974, elapsed: 0s, ETA:/root/miniconda3/lib/python3.8/site-packages/mmdet/models/dense_heads/anchor_head.py:123: UserWarning: DeprecationWarning: anchor_generator is deprecated, please use "prior_generator" instead
warnings.warn('DeprecationWarning: anchor_generator is deprecated, ' [>>>>>>>>>>>>>>>>>>>>>>>] 30974/30974, 17.6 task/s, elapsed: 1757s, ETA: 0s
Merge detected results of patch for whole image evaluating... 00002 00106 00335 00602 00187 00081 00421 00213 00798 00547 00576 00651 00251 00457 00330 00138 00735 00782 00264 00070 00146 00362 00657 00465 00399 00738
python tools/test.py /SODA-mmrotate/configs/sodaa-benchmarks/oriented_rcnn_r50_fpn_1x.py --checkpoint /SODA-mmrotate/work_dirs/oriented-rcnn-r50/epoch_1.pth --eval mAP
There is a lag when performing the assessment, it stays stuck in place, looking forward to your response author.
The dataset is the SODA-A
From our past testing experiences, it seems that the issue is tied to the hardware environment. Try to turn off the multi-processing during merging the results by set nproc for merge with 0
nproc
Prerequisite
Task
I'm using the official example scripts/configs for the officially supported tasks/models/datasets.
Branch
master branch https://github.com/open-mmlab/mmrotate
Environment
The environment you require.
Reproduces the problem - code sample
warnings.warn('DeprecationWarning: anchor_generator is deprecated, ' [>>>>>>>>>>>>>>>>>>>>>>>] 30974/30974, 17.6 task/s, elapsed: 1757s, ETA: 0s
Reproduces the problem - command or script
python tools/test.py /SODA-mmrotate/configs/sodaa-benchmarks/oriented_rcnn_r50_fpn_1x.py --checkpoint /SODA-mmrotate/work_dirs/oriented-rcnn-r50/epoch_1.pth --eval mAP
Reproduces the problem - error message
warnings.warn('DeprecationWarning: anchor_generator is deprecated, ' [>>>>>>>>>>>>>>>>>>>>>>>] 30974/30974, 17.6 task/s, elapsed: 1757s, ETA: 0s
There is a lag when performing the assessment, it stays stuck in place, looking forward to your response author.
Additional information
The dataset is the SODA-A