Wenxiao Zhang comments

Results 6 comments of


                                            Wenxiao Zhang

RuntimeError: Dataset not found or incomplete. Please make sure all required folders for the specified "split" and "mode" are inside the "root" directory

The dataset structure should look like: cityscapes/ gtFine/ train/ val/ test/ leftImg8bit/ train/ val/ test/ You should first download the gtFine and leftImg8bit from cityscapse website, and then change the...

Can you explain why the results of PCAN are lower than PN_VLAD on U.S. and R.A. in Table 3.

Hi, @sagittahjz Sorry for later replying. I have not noticed this issue before. The reason I think is due to the datasets you used. If you look into the datasets,...

code

Hi, @xiaofeifeifeifeifei . Please refer to issue #3 .

code

Hi, @xiaofeifeifeifeifei This is a cuda lib missing error. Your current tensorflow needs cuda 10.0, please check if your cuda version is 10.0 first and if the cuda lib path...

code

@xiaofeifeifeifeifei Sorry for late replying. You can create a lmdb file with the following codes: https://github.com/wentaoyuan/pcn/blob/master/lmdb_writer.py This codes is writen by the author Wentao Yuan of PCN. Set the list_path...

Question for code

Hi @Lillian9707 , sorry for later replying. This seems an error due to the complied operator `tf_sampling_so`: `SFA/tf_ops/sampling/tf_sampling_so.so(ZNSt17_Function_handlerIFN10tensorflow6StatusEPNS0_15shape_inference16InferenceContextEEPS5_E9_M_invokeERKSt9_Any_dataOS4+0x20)` Check the .sh file in the operator file to confirm the settings...