Yu-Wu
Yu-Wu
@JurrivhLeon It is not that easy to find the data since I have left my previous affiliation, where I stored the data. But it should be easy for you to...
@NaehaSharif Hi, Thanks for your interests on our DNOC paper. From the provided logs, I found it might blame the Pickle module (https://stackoverflow.com/questions/44144584/typeerror-cant-pickle-thread-lock-objects)
@NaehaSharif Please give me some time to solve this issue. It seems it only happens on Windows.
@NaehaSharif I tried a lot, but I could not reproduce the error. In addition, I checked my code and found that I never use ''Pickle'' in reading data. It seems...
@tuannguyen1999xxx You may try this link. https://drive.google.com/file/d/1qIadJTpY3Wpvsubui2c4jIQTUhAWA1-y/view?usp=drive_open
Sorry that we do not have these data, either.
@a-flying-crow Thanks for the interest on our paper. - Are the parameters in the code are the same as those used in the result of your paper? I did not...
@catherine-qian Sorry that due to the company policy, code is available upon request. Please send me email ([email protected]).
Hi, For the first question, yes. For the second one, 16 frames out of the tracklet are input into the network during training. But for inference, we input all frames...
Because we do not have tooooo much GPU memory for training. The largest tracklet has more than 1,000 frames, which needs 60x times GPU memory cost.