Creating lmdb dataset in google colab

[iammobina]

Hi everyone,
i followed the instruction on how to train a new model,but I didn't understand well how should I create my own database and run the following command ? can somebody explain this to me?

python train.py --adadelta --trainRoot {train_path} --valRoot {val_path} --cuda

1)what should I replace with {train_path} and {val_path}?
2)th main_train.lua ../models/foo_model/ in google colab raise an error which is "/bin/bash: th: command not found"
can you help me?

[itsbvk]

for 2 -- I think you will have to prefix it with ! . That is if you want to run a linux terminal command on any jupyter notebook ( valid for colab since colab is a jupyter notebook) you prefix it with !. For example to run the ls command , you run !ls