CoinCheung

Hi, for the first question, the answer is yes. It is for rank-1. As for MARS dataset, I have to confess that I have no experience playing with that dataset,...

I met a core dumped error like this: ``` running build_ext building 'utils.cython_bbox' extension creating build creating build/temp.linux-x86_64-2.7 creating build/temp.linux-x86_64-2.7/utils x86_64-linux-gnu-gcc -pthread -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -fno-strict-aliasing -Wdate-time...

Do you have a conclusion on this? I found that model trained with PIL and eval with opencv have a low accuracy. It seems that the performance drop is brought...

Where could we download the pre-trained model for evaluation please?

@dschain 请问你的完整命令是啥啊，直接neo4j-admin import xxx.csv就完了吗，还是加了啥选项

@ClementPinard Thanks for replying !! As far as I know, cuda seems support dynamic allocated shared memory within a block, which is defined like `extern __shared__ scalar_t sdata[]`. Doesn't pytorch...

But I did have called the kernel function with shared memory sized assgined, I called it like this: ```cpp TestForward(); ``` I assigned 4k shared memory for each block in...

Thanks !!! It works now, but I have two more warnings: ``` /miniconda/envs/py36/lib/python3.6/site-packages/torch/include/torch/csrc/autograd/profiler.h(97): warning: attribute "__visibility__" does not apply here warning: specified alignment (4) is different from alignment (8) specified...

Hi guys, I got to know that yolo3 employs 9 anchors, but there are three layers used to generate yolo targets. Does this mean, each yolo target layer should have...

Hi, Here I have some anchor question please: If I did not misunderstand the paper, there is also a positive-negative mechanism in yolov3, but only when we compute confidence loss,...