推理无法进行

[Lin-0324]

Prerequisite

• [X] I have searched Issues and Discussions but cannot get the expected help.
• [X] I have read the FAQ documentation but cannot get the expected help.
• [X] The bug has not been fixed in the latest version (master) or latest version (3.x).

Task

I'm using the official example scripts/configs for the officially supported tasks/models/datasets.

Branch

master branch https://github.com/open-mmlab/mmdetection

Environment

Python 3.8, PyTorch 1.13 and mmdet 2.26.0

Reproduces the problem - code sample

python tools/test.py configs/sodad-benchmarks/autoassign_r50_1x.py work_dirs/autoassign_r50_1x/epoch_1.pth

Reproduces the problem - command or script

python tools/test.py configs/sodad-benchmarks/autoassign_r50_1x.py work_dirs/autoassign_r50_1x/epoch_1.pth

Reproduces the problem - error message

[>>>>>>>>>>>>>>>>>>>>>>>] 109126/109126, 8.8 task/s, elapsed: 12385s, ETA: 0s

Merge detected results of patch for whole image evaluating...

当使用RetinaNet和Faster R-CNN这种anchor-based时，能够正常推理。但是使用FCOS或autoassign这种anchor-free检测器时，就会卡在这个合并步骤，无法下一步推理。

Additional information

No response

[shaunyuan22]

检查下子图有没有正常预测的检测框

[Lin-0324]

将12轮训练后的ckpt进行测试可视化是有正常预测的检测框和分类。