Deeplab is crashing

[dineshkh]

Hi, Can you please tell me what is the difference between fc_8 features and crf features. There are different trained models some has fc_8 in the test.prototxt some has crf.

I am using Deeplab to generate CRF features for my test images which I can use for my CRF. I have used ResNet-101 trained model with 1 image It got crashed by giving following output

I0524 07:20:19.491786 3885 net.cpp:816] Ignoring source layer label_shrink16_label_shrink16_0_split I0524 07:20:19.491788 3885 net.cpp:816] Ignoring source layer loss_res05 I0524 07:20:19.491793 3885 net.cpp:816] Ignoring source layer accuracyres05 I0524 07:20:19.500727 3885 caffe.cpp:252] Running for 1 iterations. F0524 07:20:19.748760 3885 blob.cpp:163] Check failed: data Check failure stack trace: @ 0x7f3d8340b5cd google::LogMessage::Fail() @ 0x7f3d8340d433 google::LogMessage::SendToLog() @ 0x7f3d8340b15b google::LogMessage::Flush() @ 0x7f3d8340de1e google::LogMessageFatal::~LogMessageFatal() @ 0x7f3d8398a15b caffe::Blob<>::mutable_cpu_data() @ 0x7f3d83800727 caffe::BatchNormLayer<>::Forward_cpu() @ 0x7f3d839348a3 caffe::Net<>::ForwardFromTo() @ 0x7f3d83934b17 caffe::Net<>::ForwardPrefilled() @ 0x4088c1 test() @ 0x407010 main @ 0x7f3d8269a830 __libc_start_main @ 0x4076c9 _start @ (nil) (unknown) Aborted (core dumped)

Please let me know if I am doing something wrong ?

Dinesh

[cslxiao]

@dineshkh Have you solve the problem? I met the same problem when run in cpu model. I guess it is a bug in the implement of cpu code.

[Jinming-Su]

@dineshkh @cslxiao I also met the same problem when I chose the CPU mode. My GPU is only 12GB and out of memory when I test the deeplab-resnet. How do you test deeplab-resnet?
I can train, but can't test.
Please help me.

[dineshkh]

Sorry for late reply. In file batch_norm_layer.cpp under /src/caffe/layers/ directory uncomment line no. 53. // xnorm.ReshapeLike(*bottom[0]);

Dinesh

[Jinming-Su]

Yes, it works.Thank you. @dineshkh