search

ShaoqingRen / SPP_net

SPP_net : Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
363 stars 236 forks source link

The script_spp_voc.m met some error for prototxt version #18

Open wistone opened 9 years ago

wistone commented 9 years ago

Hi, Shaoqing

I download the SPP package and the corresponding caffe package a few days ago. Now I have some problem in running Script_spp_voc.m

If I use the original pascal_finetune_fc_spm_solver.prototxt, the matlab crashed with an error message of

WARNING: Logging before InitGoogleLogging() is written to STDERR I1123 15:46:26.743105 9641 common.cpp:222] Compute Capability 3.5, set cuda_num_threads = 1024 libprotobuf ERROR google/protobuf/text_format.cc:172] Error parsing text-format caffe.NetParameter: 17:23: Message type "caffe.V0LayerParameter" has no field named "inner_product_param". F1123 15:46:30.807468 9641 upgrade_proto.cpp:627] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: pascal_finetune_fc_spm_train.prototxt

If I changed to the other prototxt pascal_finetune_fc_spm_solver_new.prototxt, the matlab also crashed. Either or not I changed the prototxt following the 5th post.

So which one is the right version for training the VOC using current caffe version? Could you help solve it?

Thanks.

ShaoqingRen commented 9 years ago

Hi wistone,

If you are using the caffe.mex from fetch_caffe_mex_5_5.m, then the model from fetch_model_data.m and pascal_finetune_fc_spm_train.prototxt should be used.

If you are using the caffe.mex compiled from https://github.com/ShaoqingRen/caffe, then the model from OneDriver(https://onedrive.live.com/download?resid=4006CBB8476FF777!9723&authkey=!APTWXLD_P7UN6P0&ithint=file%2czip) and pascal_finetune_fc_spm_solver_new.prototxt should be used.

Best, Shaoqing