Levin Jian

I am using Ubuntu 18.04, and encountered the same issue. I have it fixed by removing the `-march=native` from the CMAKE_CXX_FLAGS flag in CMakeList.txt file. I figured out this fix...

@980044579 , thanks for sharing your observations and experience. 1. With the great source codes in this project and the data provided, I was able to reproduce the author's result,...

Hi @980044579 , thanks a lot for your kind reply. I did the code changes too in yesterday and found the model can achieve 0.999 accuracy at 12th epoch. so...

@siddharthm83 , Based on Paul's great code implementations, I made some changes, and was able to make the training process work to some degree.   The SSD model is...

Sure @Zehaos . I listed the major changes I made in the Experimentation section of this [link](https://github.com/LevinJ/SSD_tensorflow_VOC)

There are quite a few areas which I could look into and figure out why the new detector has this performance gap with what is obervred in “Benenson etc., 2014...

Have made several attempts to fix this issue: 1. Adjust the timing of performing DCT by doing it after the shrinking, but this turns to worsen the situation. see here...

Hi @jiexiong2016 , I am also interested in exploring feature correspondence via deep learning on the basis of your great work/paper. Do you still have any plan to release the...

just completed hw2, it looks like I can't send new pull request without a prior pull request of mine being accepted first.