VideoObjectSearch

Results 6 comments of VideoObjectSearch

how to detect video?

Sorry for delayed reply. Currently ALFNet is running on images. When applied on videos, you can run it frame by frame. To perform detection on video, you can refer to...

tensorflow.python.framework.errors_impl.InternalError: cudaGetDevice() failed. Status: CUDA driver version is insufficient for CUDA runtime version

Sorry for delayed reply. Maybe the problem lies in that the version of your tensorflow is unmatched with the version of CUDA. You can refer to https://www.tensorflow.org/install/gpu

run train.py occur error

@yongqiangzhang1 @zhangxydlut @MADONOKOUKI @pnnnnnnn Please try this compiled document [utils.zip](https://github.com/liuwei16/ALFNet/files/2424399/utils.zip)

run train.py occur error

@yongqiangzhang1 You can have a try. [nms.zip](https://github.com/liuwei16/ALFNet/files/2426261/nms.zip)

The MR is not as good as that in the paper.

@Chen94yue Sorry for delayed reply. Did you decrease the learning rate and load the trained weights to continue training?

The MR is not as good as that in the paper.

@rintiunse Sorry for delayed reply. Did you make sure that your tensorflow is running on GPU? I just re-run the exact experiments 4 times. It approximately took 126~132 seconds on...