Chao-Yuan Wu

Hi thanks for the questions. Unfortunately, it might take a bit longer, but I'll keep you updated if I have any updates. I'd also like to point out that H.264...

Hi, thanks for the question. What I meant was modifying `./ffmpeg/include/` and `-L./ffmpeg/lib/` For example, if you install ffmpeg in `/home/users/cywu/my_ffmpeg`, then you should modify them to be `/home/users/cywu/my_ffmpeg/include/` and...

Hi, thanks for the question. No, it's not in this repo, but it's modified from the example at the end of https://docs.opencv.org/3.4/d7/d8b/tutorial_py_lucas_kanade.html

You're very welcome! These are just pre-processing. We clip the MV images just like in two-stream networks, people clip the flow images. +128 and minimum/maximum is just shifting it to...

Hi, sorry I cannot quite see what's going on, and don't have a good explanation for this. Would it help if you add a dummy frame at the end to...

Hi @BarakBat , thanks for your question and sorry for the confusion. Once you install the data loader with data_loader/install.sh, you should be able to load "coviar" as a python...

Hi, The visualization is modified from the example at the end of https://docs.opencv.org/3.4/d7/d8b/tutorial_py_lucas_kanade.html

I used PyTorch 0.3.0.post4

Hi sorry for the late reply! Did you modify https://github.com/chaoyuaw/pytorch-coviar/blob/master/dataset.py#L20 accordingly? I thought the c file should be fine with a different GoP size.

Hi Thanks for your questions. I'm sorry for the delay, but it might take a bit longer. I'll let you know when I have a clearer plan. If you prefer...