I'm reviewing for www.acl2019.org and just got the papers. Looking at the titles, all fo them seem interesting to me.

It's time to read about hate speech. Any recommendations? Research papers, studies?

@socrates and Scholar Social in general.

Do you know a study which looks into why people share news on social media? What's people intent?

So far, I see that people might just share a news story they find important or give their opinion/comment. On a meta level, one can comment on the quality of a news outlet. Or even call out fake news and propaganda.

Are there studies that classify shared content similarly?

I've been dealing a lot with NFS recently, and the conclusion so far is to avoid it at all cost.

Tensorboard also looks amazing, all these models are trained at the same time!

This is uber cool, in one command I can see the training progress over all models!

It's so pleasing how well designed tools make life easy in unexpected situations. Now I'm redeploying my ML pipeline from a single machine to a cluster and it doesn't need to be modified.

It's surprisingly insightful to monitor system load by the UPS load. The setup on the left needs some tuning.

Every time the Google assistant asks me how it can help, I want to answer that it can't.

Dima boosted

mastodon wish: ability to mute individual toots.

Currently if I keep seeing the same thing boosted over and over again I have to mute the originator

I've started reading the text version of NPR text.npr.org Not surprisingly, I pay much more attention to the content, rather than to the visual packaging.

I've been heavily refactoring code of my machine learning project. Now I can just watch how GPUs are fully loaded, while the CPUs are not that much. Can't wait for first validation results. It's a slightly modified model which takes images of different sizes. I don't know yet wether it gives better results, but it definitely heats up the room.

I was sluggish this morning, but something is wrong if one is active at 6 in the morning. I was late to the pool for a swim practice, and fast people took over my usual lane, as a result, I felt like a gazelle chased by lions. Anyway, I survived it.

The one I had was too short, now I got a cable which is long enough to reach my home.

The morning started by putting a new Ethernet cable in my office.

The server crashed shortly after I left, so no great results.

vmtouch is a nice tool to cache file content into memory.

Then I relaised, that resising images on the fly might be the main reason of the slow down. This idea came to me on Friday afternoon. The end of the day was intense, but resizing images once and staving the sizes I need improved the speed. Still, the GPU is not 100% busy. Now I'm looking for Monday, to see the results!

At that point TemsorFlow was complaining that the CPU supports instructions that the binary was not built with. Before building TF from source, I decided to update cuda and other Nvidia software. After a dance following outdated tutorials, I got it done. Speed improved, but still, while CPUs were at 100%, GPUs were barely loaded.

When I moved my code to a much more powerful machine with lots of memory, cpus and gpus, I got a GPU enabled TemsorFlow binary. That speed up the things, but still CPU was a bottleneck.

Show more
3dots.lv Mastodon Instance

A beta setup of a Mastodon instance primary for family and friends.