search

philipperemy / yolo-9000

YOLO9000: Better, Faster, Stronger - Real-Time Object Detection. 9000 classes!
Apache License 2.0
1.18k stars 309 forks source link

Process finished with exit code 139 (interrupted by signal 11: SIGSEGV) #50

Closed ghost closed 2 years ago

ghost commented 2 years ago

Your code doesn't work properly

When I call python/darknet.py with Working directory as darknet (which contains the python subdirectory which in turn contains the darknet.py file), the code runs fine. When I do the same but with working directory as the parent directory of darknet or a parent of that, I get the above error. Full error log:

layer     filters    size              input                output
    0 conv     32  3 x 3 / 1   544 x 544 x   3   ->   544 x 544 x  32  0.511 BFLOPs
    1 max          2 x 2 / 2   544 x 544 x  32   ->   272 x 272 x  32
    2 conv     64  3 x 3 / 1   272 x 272 x  32   ->   272 x 272 x  64  2.727 BFLOPs
    3 max          2 x 2 / 2   272 x 272 x  64   ->   136 x 136 x  64
    4 conv    128  3 x 3 / 1   136 x 136 x  64   ->   136 x 136 x 128  2.727 BFLOPs
    5 conv     64  1 x 1 / 1   136 x 136 x 128   ->   136 x 136 x  64  0.303 BFLOPs
    6 conv    128  3 x 3 / 1   136 x 136 x  64   ->   136 x 136 x 128  2.727 BFLOPs
    7 max          2 x 2 / 2   136 x 136 x 128   ->    68 x  68 x 128
    8 conv    256  3 x 3 / 1    68 x  68 x 128   ->    68 x  68 x 256  2.727 BFLOPs
    9 conv    128  1 x 1 / 1    68 x  68 x 256   ->    68 x  68 x 128  0.303 BFLOPs
   10 conv    256  3 x 3 / 1    68 x  68 x 128   ->    68 x  68 x 256  2.727 BFLOPs
   11 max          2 x 2 / 2    68 x  68 x 256   ->    34 x  34 x 256
   12 conv    512  3 x 3 / 1    34 x  34 x 256   ->    34 x  34 x 512  2.727 BFLOPs
   13 conv    256  1 x 1 / 1    34 x  34 x 512   ->    34 x  34 x 256  0.303 BFLOPs
   14 conv    512  3 x 3 / 1    34 x  34 x 256   ->    34 x  34 x 512  2.727 BFLOPs
   15 conv    256  1 x 1 / 1    34 x  34 x 512   ->    34 x  34 x 256  0.303 BFLOPs
   16 conv    512  3 x 3 / 1    34 x  34 x 256   ->    34 x  34 x 512  2.727 BFLOPs
   17 max          2 x 2 / 2    34 x  34 x 512   ->    17 x  17 x 512
   18 conv   1024  3 x 3 / 1    17 x  17 x 512   ->    17 x  17 x1024  2.727 BFLOPs
   19 conv    512  1 x 1 / 1    17 x  17 x1024   ->    17 x  17 x 512  0.303 BFLOPs
   20 conv   1024  3 x 3 / 1    17 x  17 x 512   ->    17 x  17 x1024  2.727 BFLOPs
   21 conv    512  1 x 1 / 1    17 x  17 x1024   ->    17 x  17 x 512  0.303 BFLOPs
   22 conv   1024  3 x 3 / 1    17 x  17 x 512   ->    17 x  17 x1024  2.727 BFLOPs
   23 conv  28269  1 x 1 / 1    17 x  17 x1024   ->    17 x  17 x28269  16.732 BFLOPs
   24 detection
mask_scale: Using default '1.000000'

Process finished with exit code 139 (interrupted by signal 11: SIGSEGV)
ghost commented 2 years ago

I solved the problem by adding the darknet folder (which contains everything from this repo) to my Python path

philipperemy commented 2 years ago

Good to know! Using the PYTHONPATH variable?