shiro

The destruction method (https://github.com/sh1r0/caffe/blob/cmake_android/android/caffe_mobile.cpp#L82) should be exposed to jni layer. I'll fix it later, thanks.

I think it might be the permission issue, please refer to https://github.com/sh1r0/caffe-android-demo/issues/41#issuecomment-264628393, thanks.

I guess that you used some io lib format (say, lmdb in mnist example) as your data input which is not supported yet (please refer to [this](https://github.com/sh1r0/caffe-android-lib#support) and [this](https://github.com/sh1r0/caffe-android-lib/blob/master/scripts/build_caffe.sh#L58-L60)). BTW,...

@elife33 @DevilGragon Sorry, it's a known issue and I cannot find the root cause so far.

@DevilGragon You could do the conversion job on linux. By the way, I'm not sure if it's a good idea to train models on Android devices.

I would say that it's possible, but I'm not sure when. Currently, if you are interested in caffe w/ OpenCL support, you can refer to https://github.com/BVLC/caffe/pull/2610.

@naibaf7 :+1: But I took a look at your branch, and I found that the commits are too much to make the branch like a patch to be easily applied...

@naibaf7 Yes, I guess so. :stuck_out_tongue: I think a branch which is rebased to the latest master branch (https://github.com/BVLC/caffe/commit/03a84bf464dd47bcec9ac943f0229a758c627f05) should be enough for me to have some trials. Thanks.

@naibaf7 OK, that's fine. I tried to merge my branch onto yours for some trials in the early stage. To see my progress, you can take a look at [opencl_dev](https://github.com/sh1r0/caffe-android-lib/tree/opencl_dev)....

@naibaf7 Yes, it's really cool to have OpenCL works. Sorry, I'm not sure what the problem might be, as I just got a segmentation fault when specifying CPU as the...