HPL123 comments

Results 12 comments of


                                            HPL123

Could you tell me how to test this code?

Did you test success? and how did you test？

Could you tell me how to test this code?

I have tried the first way successfully,but the code can not get the correct results as the paper describes.

How to run train processing by data of OVP(open video project)

Did you test success? and how did you test？

How to extract video features and the number of seq_len?

Did you test success? and how did you test？

Expected object of type torch.DoubleTensor but found type torch.FloatTensor for argument #2 'weight'

@guanfuchen ，I uses ubuntu. But it is not solved

Expected object of type torch.DoubleTensor but found type torch.FloatTensor for argument #2 'weight'

@wting861006 ,did you solved this problem?

Expected object of type torch.DoubleTensor but found type torch.FloatTensor for argument #2 'weight'

@wting861006 ，Thanks，I solved it by deleting “image = image.astype(np.float)”

How to get im_h_y from im_h?

@yuanshuai220 ，Hi，I don't know why it needs so much memory when test and the train is normal. Have you ever had this problem? :: RuntimeError: cuda runtime error (2) :...

Question about discriminating the size of the network output

@Alxemade ,你好（我就说中文了哈），你在测试的时候碰到显存不够用的问题么？我训练时候正常，测试的时候就显示了下面这个问题 :: RuntimeError: cuda runtime error (2) : out of memory at /opt/conda/conda-bld/pytorch_1501969512886/work/pytorch-0.1.12/torch/lib/THC/generic/THCStorage.cu:66