densecap
densecap copied to clipboard
some errors when running train.lua
Hi, I have some error after (https://github.com/jcjohnson/densecap/issues):
libloadcaffe.so: undefined symbol: _ZN6google8protobuf8internal23empty_string_once_init_E
$ th train.lua -data_h5 output.HDF5 -data_json output.json -gpu 2
{
finetune_cnn_after : -1
weight_decay : 1e-06
optim_beta2 : 0.999
val_images_use : 1000
timing : false
optim_epsilon : 1e-08
test_num_proposals : 1000
input_encoding_size : 512
losses_log_every : 10
id : ""
gpu : 2
drop_prob : 0.5
data_json : "output.json"
clip_final_boxes : 1
sampler_batch_size : 256
rnn_size : 512
test_rpn_nms_thresh : 0.7
progress_dump_every : 100
optim_beta1 : 0.9
end_objectness_weight : 0.1
seed : 123
test_final_nms_thresh : 0.3
eval_first_iteration : 0
captioning_weight : 1
checkpoint_start_from : ""
sampler_high_thresh : 0.7
mid_objectness_weight : 0.1
data_h5 : "output.HDF5"
train_remove_outbounds_boxes : 1
sampler_low_thresh : 0.3
debug_max_train_images : -1
learning_rate : 1e-05
rpn_hidden_dim : 512
max_iters : -1
checkpoint_path : "checkpoint.t7"
save_checkpoint_every : 10000
end_box_reg_weight : 0.1
proposal_regions_h5 : ""
backend : "cudnn"
mid_box_reg_weight : 0.05
box_reg_decay : 5e-05
}
DataLoader loading json file: output.json
DataLoader loading h5 file: output.HDF5
reading box_to_img
reading boxes
reading image_heights
reading image_widths
reading img_to_first_box
reading img_to_last_box
reading labels
reading lengths
reading original_heights
reading original_widths
reading split
assigned 77396/5000/5000 images to train/val/test.
initialized DataLoader:
#images: 87396, #regions: 4062806, sequence max length: 15
initializing a DenseCap model from scratch...
/home/PPeiMi/torch/install/bin/luajit: /home/PPeiMi/torch/install/share/lua/5.1/trepl/init.lua:384: /home/PPeiMi/torch/install/share/lua/5.1/trepl/init.lua:384: /home/PPeiMi/torch/install/share/lua/5.1/loadcaffe/ffi.lua:10: /home/PPeiMi/torch/install/lib/lua/5.1/libloadcaffe.so: undefined symbol: _ZN6google8protobuf8internal23empty_string_once_init_E
stack traceback:
[C]: in function 'error'
/home/PPeiMi/torch/install/share/lua/5.1/trepl/init.lua:384: in function 'require'
./densecap/DenseCapModel.lua:21: in function '__init'
/home/PPeiMi/.luarocks/share/lua/5.1/torch/init.lua:91: in function </home/PPeiMi/.luarocks/share/lua/5.1/torch/init.lua:87>
[C]: in function 'DenseCapModel'
./models.lua:7: in function 'setup'
train.lua:48: in main chunk
[C]: in function 'dofile'
...eiMi/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:145: in main chunk
[C]: at 0x00405840
I can't find how to solve this...
There is some problem with your protobuf which is needed by loadcaffe; I'm not exactly sure how to solve this.
I had this error. I updated protobuf and it was fixed