Seonwook Park

Hi @chaeyoun, thanks for your interest in our research and in reproducing our results. I am not fully sure what you mean in your inquiry, but I think I can...

Hi @RichardoMrMu , I'm sorry that I completely missed this issue. I am not entirely sure which part you need help in, so I'd like to point you to: https://github.com/swook/EVE/blob/master/DATASET.md#hdf-file-format...

Hi, the transformation that you link to in ETH-XGaze is a transformation for warping the input image space to the final face patch space. Hence, this is different for every...

Thanks for opening this issue. I myself did not previously have the chance to train EVE on multiple GPUs... so am unaware of which parts make it incompatible for `nn.DataParallel`....

That's a good point. You could try compiling dlib manually instead of using the pip installed version: http://dlib.net/compile.html I recall that I was using such a version of the library....

Hi, I'm using Tensorflow 1.11.0 and cannot reproduce this issue (unfortunately it's cumbersome for me to switch TF versions...) would you mind trying 1.11? Thanks!

Thanks a lot

Sorry about the late response! It is indeed tricky to get things working in a different environment... The `module.` error you encountered occurs due to the original model being trained...

Please refer to my answer to your original question, viewable at #8

I am not 100% sure, but I imagine that you need to update https://github.com/NVlabs/few_shot_gaze/blob/master/demo/monitor.py#L28 (and its inverse) based on these values that you determined: ``` T = 285.23 100.70 159.83...