WuQiang
WuQiang
@Felix-neko . Did you do this? Common issues: You may need to set an LD_LIBRARY_PATH before you start MATLAB. If you see a message like "Invalid MEX-file '/path/to/rcnn/external/caffe/matlab/caffe/caffe.mexa64': libmkl_rt.so: cannot...
I have a problem .when I ran rcnn_demo('ILSVRC13',0), ``` Welcome to the ILSVRC13 demo Running in CPU mode (To run in GPU mode, call rcnn_demo(demo_choice, 1) instead) Press any key...
I have trained the nets several time and always got worse a liitle than your model's result . Just because of the network initialization?
If I get more data and finetune the models . Maybe I can get better results, because I have get a better network initialization.
@luoyetx yes,I used my trained 23 models.But two models(1_EN,1_NM) was not be used. I used my 21 models to repace your models under webapp/v0.0.6 and test it. I used my...
@luoyetx I can't open your pdf. So if it is possible,please send it to my email ([email protected]).Thanks!
@luoyetx no, it is ok.
@luoyetx I have another question. Caffe with different version will get different train.hd5. Why?
This wrong result may be caused by caffe with diffrent version. You can upload your caffe to github.
I used bootstrap.sh to train it and i got 23 models