segaware
segaware copied to clipboard
aharley
Segmentation-Aware Convolutional Networks Using Local Attention Masks
I am trying to train VGG16 with my own data. I have cropped the images to 224x224. When I train with VGG16 as provided by Caffe model zoo (https://gist.github.com/ksimonyan/211839e770f7b538e2d8) I...
*** Check failure stack trace: *** @ 0x7fa08bf23daa (unknown) @ 0x7fa08bf23ce4 (unknown) @ 0x7fa08bf236e6 (unknown) @ 0x7fa08bf26687 (unknown) @ 0x7fa08c5791e1 caffe::SyncedMemory::~SyncedMemory() @ 0x7fa08c5c6fb2 boost::detail::sp_counted_impl_p::dispose() @ 0x40a52e boost::detail::sp_counted_base::release() @ 0x7fa08c5df1e5 caffe::Blob::~Blob()...
Could you please tell me what "TwoImageData" layer is used for, I can't find the code. Thanks!
Mainly change config file train and test in embs/vgg. Change TwoImageData to ImageSegData in config file to make them work with deeplab-v2
I have found that the code only contains the part for test and no code for training. Is the embedding network trained separately from deeplab network?