Questions about the training schedule about alphaction HOT 5 CLOSED

The released code has some slight difference compared to those hyper-parameters provided paper (we change the weight of the loss when we release the code). Currently, you could simply use the provided config file. If you want to use larger batch size, just adjust the learning rate following linear scaling rule and also scale the scheduler to train for the same number of epochs.

from alphaction.

Thanks for your reply! As I'm reproducing the results in Pytorch, I cannot directly use the config file provided for training. One question is how many epochs I should train for? I'm not sure how to convert the number of iterations in your config file to the number of epochs (one epoch refers to one scan of the whole dataset). Thanks.

from alphaction.

The training set includes about 200,000 video clips, so for the iteration number in the config file, epoch ~= 16*iteration_num/200000. I recommend you to reproduce the results following this codebase, since not all details are clearly clarified in the paper (e.g, the focal loss, the weight of each loss).

from alphaction.

Thanks for your reply!

from alphaction.

The training set includes about 200,000 video clips, so for the iteration number in the config file, epoch ~= 16*iteration_num/200000. I recommend you to reproduce the results following this codebase, since not all details are clearly clarified in the paper (e.g, the focal loss, the weight of each loss).

hi, I want to know that when evaluating the loss, why the weight of pose loss is 1.2 rather than 14.0?(the weight of object loss is 49.0 and the weight of person loss is 17.0). Thank you!

from alphaction.