It seems like out of memory about caffe_rtpose

[gineshidalgo99]

Hi, you need around 2GB of free memory on your GPU to run our code. You can check that with the bash command: nvidia-smi. Are you sure you are using the GPU with 12GB instead of the one of only 1GB?
Another thought is that you compiled without cuDNN. Without cuDNN, it requires more than 12GB of GPU memory. Let us know if any of this was your problem, thanks! Otherwise, re-open this issue please.

[lfxxxxx]

I have compiled rtpose-caffe with cuDNN. (I have set USE_CUDNN:=1), but still have this error

[lfx@gpu-com rtpose-caffe]$ .build_release/examples/rtpose/rtpose.bin --image_dir image/
F0407 10:27:17.102958 1129 syncedmem.cpp:64] Check failed: error == cudaSuccess (2 vs. 0) out of memory
*** Check failure stack trace: ***
@ 0x7efeaa736e6d (unknown)
@ 0x7efeaa738ced (unknown)
@ 0x7efeaa736a5c (unknown)
@ 0x7efeaa73963e (unknown)
@ 0x7efeb1905912 caffe::SyncedMemory::to_gpu()
@ 0x7efeb1904c79 caffe::SyncedMemory::gpu_data()
@ 0x7efeb177e762 caffe::Blob<>::gpu_data()
@ 0x7efeb197b9d3 caffe::CuDNNConvolutionLayer<>::Forward_gpu()
@ 0x7efeb18cdb8b caffe::Net<>::ForwardFromTo()
@ 0x40bcff warmup()
@ 0x411cbb processFrame()
@ 0x7efe9ed99dc5 start_thread
@ 0x7efe9eac873d __clone
Aborted (core dumped)

[gineshidalgo99]

I will answer in #37. Thanks