Bandhav Veluri

Hi @AtiqEmenent, Matlab resize performs anti-aliasing along with the interpolation, which gives very different results compared to cv2.resize. This was something I stumbled upon during the development as well. But...

@Justarrrrr Sorry for the confusion, it probably should've been 7 layers for key-frame extractor in total.

Hi @cartershoapshi, Yes, we plan to release a jupyter notebook demo! Btw, curious to learn about various use cases of this work! May I know your use case, and what...

A full training run took about 48 hours on a 4 V100 GPU machine. I think you could train for about 1-1.5 days to get good results, but not quite...

The training set had somewhere close to 64k videos. The exact link to the dataset is [this](http://data.csail.mit.edu/tofu/dataset/vimeo_septuplet.zip). No, we used batch size 8 with 4 GPUs. You could try 32...

It's single precision.. float32

> 1. The septuplet dataset consists of 91701 7-frame sequences with fixed resolution 448 x 256, extracted from 39k selected video clips from Vimeo-90k. The test set of it consists...

Hi, Refer to the footnote in page 6, in the following paper for REDS train and val sets: https://openaccess.thecvf.com/content/CVPR2021/papers/Chan_BasicVSR_The_Search_for_Essential_Components_in_Video_Super-Resolution_and_CVPR_2021_paper.pdf

Hi, Sorry for the late reply. Responses inline.. > 1. I want to confirm again that the validation set is REDSval4？ Yes. > 3. I want to know whether the...