retinanet nvidia
2020.01.12 16:28
_C.so: undefined symbol: _ZN2cv8fastFreeEPv
it is because the opencv library is not well linked. Please extend the library in setup.py as follows:
libraries=['nvinfer', 'nvinfer_plugin', 'nvonnxparser', 'opencv_core', 'opencv_highgui', 'opencv_imgproc', 'opencv_imgcodecs'])
changing devtoolset-8/root/usr/include/c++/8/bits/basic_string.tcc:1067 from this:
__p->_M_set_sharable();
to this seems to fix the compiler error:
(*__p)._M_set_sharable();
__p->_M_set_sharable();
to this seems to fix the compiler error:
(*__p)._M_set_sharable();
댓글 3
-
WHRIA
2020.01.12 16:29
-
WHRIA
2020.01.12 18:22
retinanet train model_mydataset.pth --backbone ResNet50FPN \ --fine-tune retinanet_rn50fpn.pth \ --classes 20 --iters 10000 --val-iters 1000 --lr 0.0005 \ --resize 512 --jitter 480 640 --images /voc/JPEGImages/ \ --annotations /voc/pascal_train2012.json --val-annotations /voc/pascal_val2012.json -
WHRIA
2020.01.12 18:22
retinanet train retinanet_rn50fpn.pth --backbone ResNet50FPN \ --images /coco/images/train2017/ --annotations /coco/annotations/instances_train2017.json \ --val-images /coco/images/val2017/ --val-annotations /coco/annotations/instances_val2017.json
| 번호 | 제목 | 글쓴이 | 날짜 | 조회 수 |
|---|---|---|---|---|
| 1624 | batch normalize | WHRIA | 2020.02.06 | 44 |
| 1623 | exif remove | WHRIA | 2020.01.28 | 34 |
| 1622 | nvidia docker | WHRIA | 2020.01.15 | 42 |
| 1621 | lvm 축소 확장 [4] | WHRIA | 2020.01.13 | 57 |
| 1620 | xml json pascal [4] | WHRIA | 2020.01.12 | 64 |
| 1619 | nvidia caffe | WHRIA | 2020.01.12 | 46 |
| » | retinanet nvidia [3] | WHRIA | 2020.01.12 | 68 |
| 1617 | lvm [2] | WHRIA | 2020.01.09 | 39 |
| 1616 | usb 3.1 + DP | WHRIA | 2020.01.07 | 167 |
| 1615 | raid 6 rebuild | WHRIA | 2020.01.07 | 35 |
| 1614 | add extra raid disk | WHRIA | 2020.01.05 | 80 |
| 1613 | 참고 또 참고 | WHRIA | 2020.01.03 | 69 |
| 1612 | R graph | WHRIA | 2019.12.29 | 228 |
| 1611 | melanoma awareness [1] | WHRIA | 2019.12.27 | 45 |
| 1610 | 윈도우 raid ahci 전환 | WHRIA | 2019.12.26 | 37 |
https://developer.download.nvidia.com/compute/redist/nvidia-dali