Phil Ferriere

Hi @rajat95 I believe you're correct. What we want is: ```python warped_im2[b, y, x, c] = im2[b, y + flow[b, y, x, 0], x + flow[b, y, x, 1], c]...

Per page 4 of NVidia's paper, section "Warping layer": > At the l-th level, we warp features of the second image *Im2* toward the first image *Im1* using the x2...

You're most welcome!

Hi @rockingromi I believe your concerns are addressed in [issue #26](https://github.com/NVlabs/PWC-Net/issues/26). If your question isn't completely answered there, would you consider deleting your comment here and re-open issue #26 instead?...

Hi again @frederick0329 , These are good tips! I'm still struggling a little bit coming up with a meaningful implementation/pseudo-code for a single stage SSD object detector. I'll try to...

Hi @frederick0329 ! All right... so, please bare with me as I try to capture why I'm failing to see a straight path to a working implementation for object detection...