Closed xuyunlu1030 closed 7 years ago
I meet with exactly the same problem ... The error occurs when running
${CAFFE_DIR}/build/tools/extract_features \ ${trained_model} ${tmp_model} ${blob},label \ ${result_dir}/${subset}_features_lmdb,${result_dir}/${subset}_labels_lmdb \ ${num_iters} lmdb GPU 0
I got the same error terminate called after throwing an instance of 'boost::python::error_already_se
.
Have you solved it?
Yes, I have solved it since the error is the problem with input data path in your prototxt, please check it and see if it can help.
@xuyunlu1030 Could you share more details about that? Thank you.
@ljqcava ,replace 'root_folder': 'external/exp/datasets/${dataset}/'
with 'root_folder': ''
in models/spindlenet/spindlenet_test.prototxt
solved my problem.
When I run ./scripts/test.sh, it shows error "terminate called after throwing an instance of 'boost::python::error_already_set", it seems the problem with the initialization with the first layer, but I do not have any idea about the specific problem. Do you know what is the wrong with it?