moyencourt
moyencourt
Same question for me, it would be very convenient to have this option
It would be great... It looks like @aerostitch is the maintainer of the package for ubuntu.
If you install via `sudo apt-get install gnome-shell-pomodoro`on ubuntu 20.04, so the official repository ( https://packages.ubuntu.com/focal/gnome-shell-pomodoro ) it installs version 0.16 which is bit outdated. I tried to install directly...
Thanks. Will the update code be running with pytorch 1.0? I am getting into a few problems to run it since some features are deprecated (e.g. volatile variables, `.data[0]`, etc.)
I am also having an error with the FW step: `sol, min_norm = MinNormSolver.find_min_norm_element([grads[t] for t in tasks]) ` ``` ----> 1 sol, min_norm = MinNormSolver.find_min_norm_element([grads[t] for t in tasks])...
I think I have managed to make it work with pytorch 1.0, but I still need to check the results and train it fully. @r0456230 I haven't done much other...
@YoungGer you need to compute a mean image (per pixel) using all training images (or just a few to get an approximation) of the Cityscapes's disparity dataset.
Same here, I can only reach about ~78.9%, not 80.0% as claimed in the paper. Worrying as their baseline is 78.51%.
I agree, it would be great to be able to delete them to declutter the UI. I want to go to my project without having to look for the right...
Yes! Thank you!