Hanrong Ye
Hanrong Ye
./include/caffe/util/cudnn.hpp: In function ‘void caffe::cudnn::setConvolutionDesc(cudnnConvolutionStruct**, cudnnTensorDescriptor_t, cudnnFilterDescriptor_t, int, int, int, int)’: ./include/caffe/util/cudnn.hpp:105:70: error: too few arguments to function ‘cudnnStatus_t cudnnSetConvolution2dDescriptor(cudnnConvolutionDescriptor_t, int, int, int, int, int, int, cudnnConvolutionMode_t, cudnnDataType_t)’ pad_h, pad_w,...
As shown in the Equ. 8 of the paper, it seems that the hand mask loss function is not differentiable. Could you please provide some hints or codes on the...
Hi team, Thank you so much for your impressive work! It is a huge contribution to the open-source community. What are the hyper-parameters used in training the VC 2 model?...
https://github.com/xieenze/Trans2Seg/blob/a1591849ced066d32171a25cec01a25fcacccf2b/segmentron/modules/transformer.py#L92 Maybe here you want to swap dim 1 (num_heads) and dim 2 (num_class) before reshaping? Or it is my misunderstanding? Thank you very much.
I ran `egoexo -o /mnt/datasets/egoexo_data` and some files cannot be downloaded, it shows this error message after I ran the command again: ``` Expected size of downloaded files is 4175.8...