zhuhan1236/mmd-caffe

[DEPRECATED] Please move to https://github.com/thuml/transfer-caffe

mmd-caffe's Issues

Run time error

I have successfully complied the project. But run time error appears when I start training with the command：
build/tools/caffe.bin train -solver models/icml/amazon_to_webcam_common_setting/solver.prototxt -weights models/bvlc_reference_caffenet.caffemodel -gpu 0

I0915 14:21:56.463819 27231 mmd_layer.cu:69] before mmd diff 5.76657
I0915 14:21:56.468710 27231 mmd_layer.cu:107] bandwidth 3.65977e-05
I0915 14:21:56.476428 27231 mmd_layer.cu:464] after mmd diff sum 7.71586
I0915 14:21:56.476439 27231 mmd_layer.cu:465] ------
I0915 14:21:56.486502 27231 solver.cpp:189] Iteration 8, loss = 2.62049
I0915 14:21:56.486516 27231 solver.cpp:465] Iteration 8, lr = 0.001
F0915 14:21:56.619989 27231 math_functions.cu:125] Check failed: status == CUBLAS_STATUS_SUCCESS (11 vs. 0) CUBLAS_STATUS_MAPPING_ERROR
*** Check failure stack trace: ***
@ 0x7f95c82e25cd google::LogMessage::Fail()
@ 0x7f95c82e4433 google::LogMessage::SendToLog()
@ 0x7f95c82e215b google::LogMessage::Flush()
@ 0x7f95c82e4e1e google::LogMessageFatal::~LogMessageFatal()
@ 0x7f95c87579de caffe::caffe_gpu_asum<>()
@ 0x7f95c8792329 caffe::SoftmaxWithLossLayer<>::Forward_gpu()
@ 0x7f95c8742712 caffe::Net<>::ForwardFromTo()
@ 0x7f95c8742907 caffe::Net<>::ForwardPrefilled()
@ 0x7f95c8731042 caffe::Solver<>::Step()
@ 0x7f95c8731b64 caffe::Solver<>::Solve()
@ 0x407e99 train()
@ 0x405be8 main
@ 0x7f95c7775830 __libc_start_main
@ 0x406109 _start
@ (nil) (unknown)
Aborted (core dumped)

Loss is NAN...

Hi,
When i am running you code for amazon to webcam I getting the fc7MMD and fc8 MMD loss value equal to NAN.. Could you please where I am wrong???

single-step debug

When I uncomment the code DEBUG=1 in file "Makefile.config", there is no problem compiling. However, it returns an error when runing, saying:
Expr:-CGAL_IA_MUL(-1.1,10.1)!=CGAL_IA_MUL(1.1,10.1)
Explanation:Wrong rounding: did you forget the -frounding-math option if you use GCC (or -f-model strict for Intel)
I cannot find a solution and can you give me some advices? Thank you.

Aborted at 1478502296 (unix time) try "date -d @1478502296" if you are using GNU date ***

Hi,zhuhan.When I added your implemention of MMD to the lastest caffe version,I met the following error:
*** Aborted at 1478502296 (unix time) try "date -d @1478502296" if you are using GNU date *** PC: @ 0x7f645ee615a6 caffe::Blob<>::Reshape() *** SIGSEGV (@0x0) received by PID 21540 (TID 0x7f645f8b9a40) from PID 0; stack trace: *** @ 0x7f645d7d5cb0 (unknown) @ 0x7f645ee615a6 caffe::Blob<>::Reshape() @ 0x7f645edf645a caffe::Net<>::ForwardFromTo() @ 0x7f645edf67f7 caffe::Net<>::Forward() @ 0x7f645ee52807 caffe::Solver<>::Step() @ 0x7f645ee530c9 caffe::Solver<>::Solve() @ 0x4094ab train() @ 0x4068ac main @ 0x7f645d7c0f45 (unknown) @ 0x40711b (unknown) @ 0x0 (unknown) Segmentation fault (core dumped)
It works well before the program run if(now_iter_>=iter_of_epoch) ,..,blablabla command.
Could you tell me what happens?
Thanks in advance.