szagoruyko / cvpr15deepcompare

Code and models for "Learning to Compare Image Patches via Convolutional Neural Networks"
http://imagine.enpc.fr/~zagoruys/deepcompare.html
Other
468 stars 169 forks source link

train error #33

Open sunbin1205 opened 6 years ago

sunbin1205 commented 6 years ago

Thank you for sharing the code. I made a mistake when I tried to run train. lua.

/home/zbw/torch/install/bin/lua: /home/zbw/torch/install/share/lua/5.2/torch/File.lua:375: unknown object stack traceback: [C]: in function 'error' /home/zbw/torch/install/share/lua/5.2/torch/File.lua:375: in function 'readObject' /home/zbw/torch/install/share/lua/5.2/torch/File.lua:409: in function 'load' train.lua:42: in function 'loadProvider' train.lua:54: in main chunk [C]: in function 'dofile' .../zbw/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk [C]: in ?

I used the create_dataset_file.py in the pytorch folder to convert the data to generate the data.npy file. This error occurs when i run the following command. train_set=notredame/data.npy test_set=yosemite/data.npy model=siam th train.lua

Does the model=sim represent the model parameter files that have been trained? Where does my operation go wrong? How can I solve this problem? Looking forward to your reply! Thank you very much!

sunbin1205 commented 6 years ago

Could it be lua's version problem? What version of lua do you use?