search

princeton-vl / pose-hg-train

Training and experimentation code used for "Stacked Hourglass Networks for Human Pose Estimation"
Other
575 stars 185 forks source link

Error when running the pre-trained model #55

Open ShaminiKoravuna opened 5 years ago

ShaminiKoravuna commented 5 years ago

I was trying to generate the final predictions using the pre-trained model on nvidia-docker and I'm getting the following error:

# th main.lua -expID final-preds -finalPredictions -nEpochs 0 -loadModel /app/src/umich-stacked-hourglass.t7
Saving everything to: /root/pose-hg-train/exp/mpii/final-preds
Input is a tensor with dimensions: 3 x 256 x 256
Output is a table
Entry 1 is a tensor with dimensions: 16 x 64 x 64
Entry 2 is a tensor with dimensions: 16 x 64 x 64
Entry 3 is a tensor with dimensions: 16 x 64 x 64
Entry 4 is a tensor with dimensions: 16 x 64 x 64
Entry 5 is a tensor with dimensions: 16 x 64 x 64
Entry 6 is a tensor with dimensions: 16 x 64 x 64
Entry 7 is a tensor with dimensions: 16 x 64 x 64
Entry 8 is a tensor with dimensions: 16 x 64 x 64
# of training images: 25925
# of validation images: 2958
==> Loading model from: /app/src/umich-stacked-hourglass.t7
==> Converting model to CUDA
FATAL THREAD PANIC: (read) /root/torch/install/share/lua/5.1/torch/File.lua:343: unknown Torch class <pose.Dataset>
FATAL THREAD PANIC: (read) /root/torch/install/share/lua/5.1/torch/File.lua:343: unknown Torch class <pose.Dataset>
Segmentation fault (core dumped)

Can anyone help me out with this ?

Thanks in advance!!!