CaffeMex_v2
CaffeMex_v2 copied to clipboard
Easily deploy multi-GPU caffe on Windows or Linux
Caffe doesn't seem to be the most popular ML library today. Could you please release a keras, tensorflow or pytorch demo version of the COCO loss layer?
error C2995: “void caffe::Layer::Forward_gpu(const std::vector &,const std::vector &)”: 函数模板已经定义
Does this version of Caffe can reduce the occupied memory on singlecard?
Is the function "my_solver.snapshot('snapshot_path_and_name')" to save the "XXX.caffemodel.solverstate“ file? --then we try to recover the traing proicessing by using the function"caffe_solver.restore("XXX.caffemodel.solverstate") ,but there some errors: sgd_solver.cpp:316] Check failed: state.history_size() ==...
I build this version caffe on workstation with 4×1080TI, but I find that log.cpp, log.hpp and log.cu are missing.