hixiaye

@liyunsheng13 @AruniRC @PCJohn hi, I think that the gzipped tarball which can be obtained from http://maxwell.cs.umass.edu/self-train/dataset/bdd_HP18k.tar.gz includes all the pseudo-labels from detections and tracking. All I need to do is...

@PCJohn thanks for your reply There is a problem bothering me. I use bdd_HP18k.json and bdd_source_and_HP18k_distill100_track100.sh. However, the error occured: "00000f77c-62c2a288_00000067.jpg" not found. I checked the images in bdd_peds_HP18k, and...

Thank you very much for your clarification. It's greatly appreciated.

try to modify the make.sh, and add the following codes at the starting. (the website: https://blog.csdn.net/shang_jia/article/details/82929983 ) export CUDA_PATH=/usr/local/cuda/ export CXXFLAGS="-std=c++11" export CFLAGS="-std=c99" export PATH=/usr/local/cuda-8.0/bin${PATH:+:${PATH}} export CPATH=/usr/local/cuda-8.0/include${CPATH:+:${CPATH}} export LD_LIBRARY_PATH=/usr/local/cuda-8.0/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}

> For anyone who wants to use this dataloader, you can move `imdb.parse` to `collate_fn` and convert numpy array to tensor. Then the data processing part will run on multiple...

> Hi~ > > Look at this~ https://gist.github.com/jinyu121/02a505bb2547006ceb3fdbba3bee556c > > Works fine (certainly) to me Hi, I don't understand what the `move `imdb.parse` to `collate_fn` ` meaning. And where I...

hello, i get some trouble with this project. How to replace the "placeholder" with net.config? and how to create the ne.config? I'm confused about that, could you help me? thx

thx, i'll try that

the best net i got when searching phase is around 90%。after trainning for 300 epoch， i got 93 the densenet used for 300 epoch is deeper than the one you...

is you net for trainging the same with the net obtained by searching？ in the paper， the net for training is different with the net which is obtained by searching...