Angel G.

Thanks, the lines were: ``` if os.name != "nt" and platform.machine() != "s390x": from tensorflow.contrib import cloud ``` then it worked but uh/oh tflow said my GPU is bad -...

@bryanlyon Since you cite ZFS, it has something else which could help in your case: ECC code / redundancy built-in. So if we had this in securefs, in theory you...

I looked for the XDE desktop for which the xde-ctools are (LOL) but finally realized that it is a common name. Talking about usability, are the xde-ctools callable from sth....

@lmobot I tried ` python demo/restoration_video_demo.py configs/basicvsr_plusplus_reds4.py chkpts/basicvsr_plusplus_reds4.pth data/demo_000 results/demo_000` and it Worked !! Note: I had to patch 'demo/restoration_video_demo.py' with the following code: ``` import sys sys.path.append(os.path.join(os.path.dirname(os.path.realpath(__file__)), os.pardir)) #...

Thank you guys for working on this. I'm grateful to the original authors as well. The kernel coding is a bit of black art for me.... yet this code works...

> Could you explain more on how you implemented face alignment? Yes, I can post the code. It is integrated well within a copy of your validate_on_LFW.py script. I used...

So far: - I have cleaned/aligned VGG2 and tried training on CPU but it will take months to complete. Also the aligner didn't perform too well so I used MTCNN...

That's good news ! I'll check your faster triplet code, your solution is a bit different than mine, yet still using dictionaries. For the hobbyist in me, the newer GPUs...

I didn't manage to download the whole Glint360k (no seed) so I'm on my modified/filtered/aligned version of Vgg2. It seems they (Glint360k authors) **merged** whatever face DB they found, so...

I still explore what could be achieved with the old version on filtered VGG2 and ResNet34 with constrained GPU memory. Had to reduce the batch size to 144 with 16...