Test net output #0: detection_eval = 0

[seandales]

Please use the caffe-users list for usage, installation, or modeling questions, or other requests for help. Do not post such requests to Issues. Doing so interferes with the development of Caffe.

Please read the guidelines for contributing before submitting this issue.

Issue summary

I0926 08:49:47.894820 22979 solver.cpp:294] Solving VGG_MELON_SSD_300x300_train I0926 08:49:47.894824 22979 solver.cpp:295] Learning Rate Policy: multistep I0926 08:49:47.894862 22979 blocking_queue.cpp:50] Data layer prefetch queue empty I0926 08:49:52.303377 22979 solver.cpp:332] Iteration 0, loss = 9.54588 I0926 08:49:52.303429 22979 solver.cpp:433] Iteration 0, Testing net (#0) I0926 08:49:52.309973 22979 net.cpp:693] Ignoring source layer mbox_loss I0926 09:01:38.221824 22979 solver.cpp:546] Test net output #0: detection_eval = 0 I0926 09:01:38.222069 22979 solver.cpp:337] Optimization Done. I0926 09:01:38.222079 22979 caffe.cpp:254] Optimization Done.

During the evaluation phase the detection_eval score is only 0. Please help

Steps to reproduce

If you are having difficulty building Caffe or training a model, please ask the caffe-users mailing list. If you are reporting a build error that seems to be due to a bug in Caffe, please attach your build configuration (either Makefile.config or CMakeCache.txt) and the output of the make (or cmake) command.

Your system configuration

Operating system: Ubuntu 16.04 Compiler: CUDA version (if applicable): CUDNN version (if applicable): BLAS: Python or MATLAB version (for pycaffe and matcaffe respectively): python 2.7