Anurag Ranjan

Hi, Thanks for pointing out the issues. I am sorry, I don't have the version info, but your graph looks good. The experiment is has a high variance, so we...

The relative error from 14 to 35 is about 250%. The adv_epe does not grow after approximately 30 epochs. We ran with many seeds, and terminated the experiment at epoch...

The first question is answered in the Analysis section of the paper, where we see some difference with random patches. But we did not train flownet with it. I haven't...

Oh, here you need to take care of the normalization of the patch properly. The raw saves of the patch are already normalized. The effect should be such that you...

Could you disable `--with-gt` flag. You don't need ground truths here. Also the function is available here - https://github.com/ClementPinard/SfmLearner-Pytorch/blob/master/data/kitti_raw_loader.py#L165-L182

We found that it barely affected results, it was within 1% or so. When you subtract the mean and divide by max, assuming all images have the same range [0,1],...

Okay, i think that's a valid issue. We did get around 14 EPE on unattacked FlownetC yes. We did at least 5-10 runs for each.

It should be fixed now. You would need to use a browser, and click on the link to download it. Let me know if there is any other problem.

I am pasting the md5sum of all the files. 7z x should work. You can also use the [7-zip extractor](https://www.7-zip.org/) manually. ``` 60d62b06ffb3ea04a4540a3f3e25af95 HumanFlowDataset.7z.001 add4e2a91219a23cdd503a905c78f556 HumanFlowDataset.7z.002 acdbff1ad8d0c312c8901c950858a69b HumanFlowDataset.7z.003 4ade0590a368ecedfbf2446d67770945 HumanFlowDataset.7z.004...