(on cpu mode, i've trained models,use 100 pictures、500 iteration,it took much time ,but i can get the model finally)。
I tried to train my ssd model on gpu , use VOC dataset(i use your script files to get the lmdb files),
but it failed,here is the message:
sgd_solver.cpp:106] Iteration 13100,lr = 0.001
math_functions.cpp:250] Check failed: a <= b <0 vs -1.19209e-007>
* Check failure stack trace *.
i don't know how to deal with it ,can you give me some advice?
Thank you!
(on cpu mode, i've trained models,use 100 pictures、500 iteration,it took much time ,but i can get the model finally)。 I tried to train my ssd model on gpu , use VOC dataset(i use your script files to get the lmdb files), but it failed,here is the message: sgd_solver.cpp:106] Iteration 13100,lr = 0.001 math_functions.cpp:250] Check failed: a <= b <0 vs -1.19209e-007> * Check failure stack trace *.
i don't know how to deal with it ,can you give me some advice? Thank you!