Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

the error when training with VOC2007 #186

Open
vananhlebarca opened this issue Jan 15, 2018 · 2 comments
Open

the error when training with VOC2007 #186

vananhlebarca opened this issue Jan 15, 2018 · 2 comments

Comments

@vananhlebarca
Copy link

Hi everyone,
I am using GPU Titan xp, cuda 6.5, Matlab 2014a and follow the instruction on https://github.com/ShaoqingRen/faster_rcnn
I ran experiments/script_faster_rcnn_demo.m successfully.
I have been trying to train with VOC 2007 and the error came out as follows:

fast_rcnn startup done
GPU 1: free memory 12251516928
Use GPU 1
Cleared 0 solvers and 1 stand-alone nets


stage one proposal


Error using CHECK (line 4)
invalid Net handle

Error in caffe.Net (line 38)
CHECK(is_valid_handle(hNet_net), 'invalid Net handle');

Error in caffe.Solver (line 33)
self.net = caffe.Net(self.attributes.hNet_net);

Error in caffe.get_solver (line 8)
solver = caffe.Solver(pSolver);

Error in caffe.Solver (line 21)
self = caffe.get_solver(varargin{:});

Error in proposal_train (line 49)
caffe_solver = caffe.Solver(opts.solver_def_file);

Error in Faster_RCNN_Train.do_proposal_train (line 7)
model_stage.output_model_file = proposal_train(conf, dataset.imdb_train, dataset.roidb_train, ...

Error in script_faster_rcnn_VOC2007_ZF (line 45)
model.stage1_rpn = Faster_RCNN_Train.do_proposal_train(conf_proposal, dataset, model.stage1_rpn, opts.do_val);

Did anyone came across with this error or any idea to fix it?
I am new in caffe.
Thanks a lot in advance.

@ggghh
Copy link

ggghh commented May 10, 2018

I have same problem! Have you solved it?

@qwertyDvo
Copy link

Have you solved it?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants