hughplay / tvr Goto Github PK

Hi authors,
I am confused that why you use the same instruction for training and testing, like this:

# training
python core.py train config/event.ConcatResNet.yaml
# test only
python core.py train config/event.ConcatResNet.yaml

I want to kow whether it is the correct operation, and whether have the trained model for testing?

Could you please tell me the training cost for this project, i.e. how many GPUs, how long to finish the training process?

Hi authors,
Thanks for initial code, I want to konw are there any strict requirements for the Python dependent environment configuration of your model?