[Idea] Crowd-training of unreleased Flickr landscape model about spade HOT 40 OPEN

Hey everyone! We've finished training the model and it's available here https://drive.google.com/open?id=1QJr5HBv8PAjJuVNB9zf8EiA6IcIVCswa
Here's a video of it in action: https://twitter.com/genekogan/status/1136261959970709504

from spade.

As we mentioned in the GTC, we are making an online demo for everyone to play with the Flickr model (any mobile devices or desktops) and likely a standalone version for everyone with an NVIDIA GPU. Hopefully, it will not take too long.

from spade.

Not sure how much help I could be for actually training the network, but I would love to know if / when this happens! I made a pretty rudamentary web UI for this, and would love to be able to use the Flickr model on it. Source code and public site: http://www.smartsketch.xyz

from spade.

@noyoshi Training will take 1-2 weeks.

As of being of help, the guys and I can go two ways: pull together our own GPU resources, or buy AWS. If we settle on the latter, anyone could be of help by pledging money; most likely only one of us (the most experienced one) will actually train the model.

from spade.

That's a great idea! Count me in.

from spade.

And me.

from spade.

Also count me in.

from spade.

Telegram would be great. Same username as Github.

from spade.

Telegram, Discord, WhatsApp work well for me - emailed you my usernames in each of them. Btw, @Ares97, @Lokiiiiii, @aeti-in - you guys seem to be interested in this as well?

from spade.

I'm using WhatsApp, just sent an email to u, please check it out.

from spade.

I'm using telegram as well, identical with WhatsApp.

from spade.

@sidyakinian count me in as well, I just sent you an email

from spade.

We've accomplished Flickr datasets(41K) training last week.

from spade.

The official Flickr model is available as a web demo via https://www.nvidia.com/en-us/research/ai-playground/

Better models will likely come in the summer. Stay tuned.

from spade.

on what license such model would be?

from spade.

on what license such model would be?

@Ares97 Likely the same license that SPADE was released under

from spade.

Okay, looks like we have a few people. Let's form a group chat in some messenger to discuss the next steps. @code-de, @hologerry, and @banyet1, would you please email me or just comment here which few messengers among these you find convenient?

• Messenger
• WhatsApp
• iMessage
• Discord
• Telegram

We can then choose the messenger everyone picked and host the group chat there. My email is on my profile page.

@harsh2204, @wasd96040501, if you decide to join, you're welcome to email me too!

from spade.

@sidyakinian i am also interested in this. please include me!

from spade.

@sidyakinian i am also interested in this. please include me!

@genekogan Sure! Please remember to email me or comment some messengers so that you can join.

from spade.

@hologerry, @banyet1 So you guys picked different options, Telegram and WhatsApp, could one of you use the other messenger so that we can gather in one chat? Either of those two is fine with me and @code-de

from spade.

I assume there are no segmentation masks for this dataset available, right? So those will also have to be made (or inferred using another network)

from spade.

@aman-tiwari Yes, we'll have to create the dataset ourselves. Thankfully, SPADE researchers used DeepLabV2 for it, which works pretty quickly. We'll just use that or something similar.

from spade.

@mingyuliutw That's awesome! I've heard somewhere that it's going to be released in summer.

from spade.

It's maybe a dumb question, but what's the main reason, of the missing Flickr model? Is it it's sheer size or are there any licencing issues?

from spade.

Following

from spade.

@bitcoinmeetups Hi! Please email me your Telegram if you wanna join the chat

from spade.

It's awesome ! count me in as well

from spade.

Very interested. Count me in

from spade.

@banyet1 What are your plans now that the model is complete? Do you have any intention of making it available to others? I would love to test it out.

from spade.

@genekogan Great work!
Are there any plans to release the collected Flickr dataset?

from spade.

@genekogan Nice !!
Do you have any plans to release the dataset?

from spade.

from spade.

@mingyuliutw Is there a plan to release the actual model, not just the tool to play with it?

from spade.

@genekogan Thanks for your efforts, could the flickr dataset be shared with us?

from spade.

i'm not sure if releasing the dataset would violate the licenses of the actual photos as they belong to other people. if we can release it, i have no problem with that.

from spade.

from spade.

i'm not sure if releasing the dataset would violate the licenses of the actual photos as they belong to other people. if we can release it, i have no problem with that.

It is indeed a tough problem. What methods you used to extract the sematic layout of flickr images, you annotated some samples and trained the model on your own, or used existing model?

from spade.

What methods you used to extract the sematic layout of flickr images, you annotated some samples and trained the model on your own, or used existing model?

I always create my own datasets, either creating my labels or generating them from a 3D application but I know this a very specific scenario.

from spade.

@genekogan Flickr contains lots of photos which are licensed under the Creative Commons license. If you pick only these for training, I am pretty sure the trained model could be published under the same license again.

from spade.

@aviel08 @genekogan Is it permissible to share some sematic labels for the Flickr images along with the dataset/dataloader script, I just want to test the pretrained model, thanks.

from spade.