Eugene Zatepyakin
Eugene Zatepyakin
Hello, i was testing MIH matching 500 query codes of length 293 Bits to 10K-20K in database. my setup for parameter "m" (number of hash tables) is 19 to 14....
i think you can try to use recently introduced **Normalised Pixel Difference** features instead of existing. You can read more here: http://www.cbsr.ia.ac.cn/users/scliao/papers/Liao-PAMI15-NPD.pdf I'm currently doing some tests using NPD for...
Hi, i was wondering if you did any tests to measure how it performs against well known detectors, such as OpenCV VJ etc. would be great to see some numbers...
Hi Phil! I was wondering if HTM part can be used in/for auto-regressive scenario? Full proposed arch in the paper has 3 blocks: 1. Self Att - this can be...
Hi Phil! thanks for coding this, i was wondering if the implementation is suitable for autoregressive generation since it seems to share sequence info all to all, or am I...
Is it necessary for the Pools to be static? https://github.com/ALSchwalm/lfpAlloc/blob/master/lfpAlloc/PoolDispatcher.hpp#L35 MSVC do not support thread_local with types that have non trivial destructors/constructors. the other way we can implement TLS manually...
I think we can get away with having learnable null-latents in case we dont have prefix initially
Hi! I was wondering if this is intentional to use online network for target quantiles? https://github.com/BY571/FQF-and-Extensions/blob/9c25cb3ab9144bbc5dbcb9d737fc0937c8e3a685/agent.py#L205
Hi! was reviewing some code parts of your implementation (great as usual!) and noticed that you dont alter gradient computation for models when its not required. for example computing losses...
Hey! looks like there is a mess in tensors arrangements in few place here: https://github.com/lucidrains/tranception-pytorch/blob/610ebf21c4cf3b7f0d560c89610051c7242527a0/tranception_pytorch/tranception_pytorch.py#L140 does not make sense to go to 'b h n d' last dim is channels...