train.lua in cpu mode complains about a nil value

[imanthos]

Hello,

After running the th train.lua -gpu -1 command it shows the following output:

loading network weights from .. VGG_ILSVRC_16_layers.caffemodel
Couldn't load /home/sentinel/5G - Project/densecap/data/models/vgg-16/VGG_ILSVRC_16_layers.caffemodel
/home/sentinel/torch/install/bin/luajit: ./densecap/net_utils.lua:100: attempt to index local 'net' (a nil value)
_stack traceback:
./densecap/net_utils.lua:100: in function 'subsequence'
./densecap/DenseCapModel.lua:73: in function '_init'
/home/sentinel/torch/install/share/lua/5.1/torch/init.lua:91: in function </home/sentinel/torch/install/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'
...inel/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00406670

Also running the same command with some flags more:
th train.lua -gpu -1 -backend nn -checkpoint_start_from data/models/densecap/model_id1-501-1448236541.t7_cpu.t7, and another model breaks with the same cause:

/home/sentinel/torch/install/bin/luajit: ./models.lua:11: attempt to index local 'model' (a nil value)
stack traceback:
./models.lua:11: in function 'setup'
train.lua:48: in main chunk
[C]: in function 'dofile'
...inel/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00406670

Is this a dependency issue or something I am missing?

Also sharing the rest of the output in case it is helpful:
{
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 : -1
drop_prob : 0.5
data_json : "data/VG-regions-dicts.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 : "data/VG-regions.h5"
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 : "nn"
mid_box_reg_weight : 0.05
box_reg_decay : 5e-05
}

Thank you.

[csnemes2]

just donwload http://www.robots.ox.ac.uk/%7Evgg/software/very_deep/caffe/VGG_ILSVRC_16_layers.caffemodel to the proper folder, namely: Project/densecap/data/models/vgg-16/VGG_ILSVRC_16_layers.caffemodel