Hacker News new | past | comments | ask | show | jobs | submit login

Using Deep Learning models trained on static images is usually not a good idea. But one can simply extend the model to use 3D convolutions instead of 2D, use time as 3rd axis and then feed a sequence of images for training, getting much better results out of it without the wavy effects.



And have the amount of training data and time scale from n^2 to n^3... That's why nobody has achieved good results with this yet...


Oh yes, but that might be comparable to attention-based models for NLP, complexity-wise. Using C3D is quite common since 2015 actually:

http://vlg.cs.dartmouth.edu/c3d/

https://arxiv.org/pdf/1412.0767.pdf

Training a great model is expensive these days, FB routinely pays 6 figures per training run.




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: