Zhao (Dylan) Wang

Results 37 comments of Zhao (Dylan) Wang

Hi, from my prevous practice, the normalization value is not that important. But you can still try to use a specific normalization value to fit. If you have any findings,...

Hi @Yipinggggg Thanks for your interest! All of our downstream tasks take video sequences as the model input to model the temporal information. May I learn which part of code...

Hi, @tsaishien-chen Thanks for your reply! May I learn the exact approach you have used for splitting videos? And what is the estimated time for obtaining 2M sub-videos? Could you...

Hi, @jmorlana thanks for your interest! We obtain the segmentation for every of the input frames.

Hi @1170300714 thanks for your interest! As SUN-SEG is developed based on SUN, so we only need to process SUN-SEG. (The data in SUN and SUN-SEG is totally the same)

Hi @zkysss11235 thanks for your interest! I have not met such problem before. It looks like the compilation is not totally successful. May you refer to this https://github.com/pybind/pybind11/issues/3115 and try...

@10086ddd thanks for your interest! May I learn how you split the training and test sets?

@10086ddd what about the performance on the training dataset?

@10086ddd If the performance on the test set is 100%, this is not overfitting (I think). This indicates the high effectiveness and robustness of the model.