Demetris Marnerides

@domenpk @British_Airways Awesome, thanks!

@dmarnerides @British_Airways In the end we travelled, car seat with base counted as a car seat (well, noone checked really). We put it in a big car seat bag, it was tagged at check in counter and then we dropped it off at oversized baggage. No issues at either LHR or ZAG.

@British_Airways hi. Can you please clarify if we can bring a two part car seat (base+seat, only seat cannot be used) as toddler luggage? Website doesn't say, email support will not say, phone support either hangs up or has me waiting for hours.

@domenpk @British_Airways I have the exact same question. Have you travelled? Did the car seat + base eventually count as one of the two allowed items?

@British_Airways Thank you

@dabeaz @comabrewer Create a stub account.

Join our @GrandChallenge on #HDR #Imaging at @ieeeICIP !

Registration for the HDR Inverse Tone Mapping Grand Challenge is now open! The focus of this grand challenge is to transform lower range content into HDR via the process of Inverse Tone Mapping (ITM). Learn more here: hubs.ly/Q015MZc_0

Our very own Dr. Alessandro Artusi is an organizer for this year's #ICIP22 Inverse Tone Mapping Grand Challenge. For any researchers up to the challenge of creating a novel Inverse Tone Mapping operator, REGISTRATION is OPEN! Check it out here: #team" target="_blank" rel="nofollow noopener">vcg.isti.cnr.it/icip2022-itmo-…

Unsupervised HDR imaging – What can be learned from a single 8-bit video? deepai.org/publication/un… Paper by @frabante et al.

the @ieeeICIP 2022 #InverseToneMapping #GrandChallenge for #HDR has started. The #dataset is online: vcg.isti.cnr.it/icip2022-itmo-…

@dabeaz @dontusethiscode @llanga @robsmallshire @willmcgugan @raymondh I think they are meant for both. For humans it's to show intent (to others and to future self) and for the tools to check correctness (of the intent).

#Python success: I was finally able to make a type annotated pure python version of max(). All it took was a protocol bound to a typevar, a custom sentinel class, unions, overloads, isinstance checks, casts, repeated arguments, and the / and * notation. gist.github.com/rhettinger/beb…

Have you ever put a breve ˘ over a variable name, just so you could take its second derivative ¨ and end up with a tiny happy face ˘̈ ? Hand and Finch went there:

@iacopo_poli @jeremyphoward The other thing that I think should work is to use a byte tensor as the index (or Long but with numbered indices). I haven't really tried that but it works in PyTorch now so it should be fine in ATen.

@dmarnerides @jeremyphoward thank you! These are gonna be some funny loops to write :-)

if there is some ATen wizard in my contacts, I'd really love the help with this 🙂 discuss.pytorch.org/t/advanced-ind…

@iacopo_poli @jeremyphoward And then I think it's essentially just writing loops to access/set stuff in the order you want.

@iacopo_poli @jeremyphoward I think the main idea is to use accessors, e.g. for a 4 dimensional Tensor: auto x_acc = x.accessor<float, 4>(); and then get values like so: auto value = x_acc[i][j][k][l]; The API is not very stable atm though.

the true genius of classical pavlovian conditioning is that every time i hear “pavlov” i automatically think of a dog

@ApacheMXNet Neat. However you don't need to use Variables in PyTorch anymore.

#Pytorch user? Check out our 10 minutes conversion guide to #MXNet ! #DeepLearning #mxnet medium.com/apache-mxnet/m…