Accel
Accel copied to clipboard
SamvitJ
Fast, high accuracy video segmentation framework (CVPR 2019 oral)
The task of video semantic segmentation is to segment each frame of videos. But only several frames are labeled in the test set, the test performance in experiments is on...
README.md refers to [MXNet@(commit 62ecb60)](https://github.com/apache/incubator-mxnet/tree/62ecb60) version 0.9.3~0.9.5. But I had to use version 0.12.0 to run the code. It doesn't seem like DeformableConvolution is accessible from `mx.contrib.symbol`. I get this...
I want to make a comparison of the example you used to exam my own model. Could you please tell me the source of that? I mean, I have already...
Hi, great work! I just want to ask about the inference time. You report the inference time /per frame for baseline DL-18 and AL-18 and DFF. How to calculate this...
Why do the results of flownet need to be multiplied by 2.5?
