Floating point exception (core dumped) when run tools/demo.py

[PapaMadeleine2022]

hello, I have trained a model in my own dataset. and then I run ./tools/demo.py to test some images, but it shows error:

I0226 17:06:05.172631 122245 net.cpp:816] Ignoring source layer rpn-data
I0226 17:06:05.172633 122245 net.cpp:816] Ignoring source layer rpn_loss_cls
I0226 17:06:05.172636 122245 net.cpp:816] Ignoring source layer rpn_loss_bbox
I0226 17:06:05.172641 122245 net.cpp:816] Ignoring source layer roi-data
I0226 17:06:05.270239 122245 net.cpp:816] Ignoring source layer loss_cls
I0226 17:06:05.270261 122245 net.cpp:816] Ignoring source layer loss_bbox


Loaded network /xxx/py-faster-rcnn/output/faster_rcnn_end2end/voc_2007_trainval/vgg16_faster_rcnn_iter_xxxxx.caffemodel
Floating point exception (core dumped)

how to solve this problem? can anyone give some advises? thank you very much~~

[LucasMahieu]

I got the same issue when using a min_size to big according to my frame input size.

Reducing the min_size to 1 (in my example) solved the problem

[JFishLover]

can you give more details please? I have some trouble in understanding your answer, thx @LucasMahieu

[JFishLover]

do you know how to solve it now? I have the same trouble now, please help me if you know how to do it, thanks @IvyGongoogle