neural-network - 使用暗网导出 YOLO v4 权重时出现 Segfault

Question

我在 nvidia jetson nano 上运行它，我能够理解为什么会出现这个错误。回溯显示最后调用的 fn 是 read_cfg()。

Reading symbols from darknet...done.
(gdb) r export yolov4-tiny-3l.cfg yolov4-tiny.weights layers
Starting program: /home/juno/Downloads/darknet/darknet export yolov4-tiny-3l.cfg yolov4- 
tiny.weights layers
[Thread debugging using libthread_db enabled]
Using host libthread_db library "/lib/aarch64-linux-gnu/libthread_db.so.1".
 DEBUG=1 
[New Thread 0x7fa52e93d0 (LWP 23005)]
 CUDA-version: 10020 (10020), GPU count: 1  
 OpenCV version: 4.1.1d

Thread 1 "darknet" received signal SIGSEGV, Segmentation fault.
0x00000055555f9510 in read_cfg ()
(gdb) bt
#0  0x00000055555f9510 in read_cfg ()
#1  0x00000055555f959c in parse_network_cfg_custom ()