when train on hmdb split1,the val accuracy is about 70%, but test accuracy is only about 60%。i use 2 segments and each segment sample 16 frames sequentially in training.when in testing,i sample 25 frames at equal intervals。 Is there a problem with the way I sample?
each segment sample 16 frames I don't think this is the way we use TSN in the paper. For your own experiments, you are responsible for tuning the learning parameters.
when train on hmdb split1,the val accuracy is about 70%, but test accuracy is only about 60%。i use 2 segments and each segment sample 16 frames sequentially in training.when in testing,i sample 25 frames at equal intervals。 Is there a problem with the way I sample?