longjon/caffe

mnist examples not running and tests fail

Closed this issue · 1 comments

I have installed this FCN branch of caffe. There is no issue in make and make test but make runtest fails for some tests in SGDsolver. I commented those tests and rests are running.
Also, when I do examples/mnist/train_mnist_autoencoder_adagrad.sh, it gets hanged and doesn't proceed beyond
I0102 18:03:51.671083 3065 layer_factory.hpp:76] Creating layer data
I0102 18:03:51.671159 3065 net.cpp:111] Creating Layer data
I0102 18:03:51.671169 3065 net.cpp:434] data -> data
I have figured out where it is stopping. In net.cpp at line 153,
layers_[layer_id]->SetUp(bottom_vecs_[layer_id], top_vecs_[layer_id]);
is being executed which calls Setup in layer.hpp line 71
void SetUp(const vector<Blob>& bottom,
const vector<Blob
>& top)

In this function, I can't find it proceeding beyond line 75 which is
LayerSetUp(bottom, top);
Apparently LayerSetup is a virtual function, but I couldn't find it's implementation. When I comment this line, it breaks at the next line in Reshape..
F0102 18:12:52.731317 3652 split_layer.cpp:22] Check failed: count_ == top[i]->count() (0 vs. 1)

Also, I have a K40C GPU and CUDA-6.5 on which I am running the master branch caffe.

Closing since the future branch is now deprecated; the relevant functionality has been merged to master. For installation help on master see the caffe-users mailing list.

Check out the fcn.berkeleyvision.org repo for master editions of the reference networks, weights, and code for learning, inference, and scoring.