LAION-5B: 5 billion image-text-pairs dataset (with the authors)

Channel:
Switzerland Yannic Kilcher
Subscribers:
291,000
Published on ● Video Link: https://www.youtube.com/watch?v=AIOE1l1W0Tw


Duration: 58:02
17,185 views
493

#laion #clip #dalle

LAION-5B is an open, free dataset consisting of over 5 billion image-text-pairs. Today's video is an interview with three of its creators. We dive into the mechanics and challenges of operating at such large scale, how to keep cost low, what new possibilities are enabled with open datasets like this, and how to best handle safety and legal concerns.

OUTLINE:
0:00 - Intro
1:30 - Start of Interview
2:30 - What is LAION?
11:10 - What are the effects of CLIP filtering?
16:40 - How big is this dataset?
19:05 - Does the text always come from the alt-property?
22:45 - What does it take to work at scale?
25:50 -When will we replicate DALL-E?
31:30 - The surprisingly efficient pipeline
35:20 - How do you cover the S3 costs?
40:30 - Addressing safety & legal concerns
55:15 - Where can people get started?

References:
LAION website: https://laion.ai/
LAION Discord: https://discord.com/invite/mVcgxMPD7e
LAION-5B: https://laion.ai/laion-5b-a-new-era-of-open-large-scale-multi-modal-datasets/
img2dataset tool: https://github.com/rom1504/img2dataset
LAION-400M: https://paperswithcode.com/dataset/laion-400m

Links:
TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick
YouTube: https://www.youtube.com/c/yannickilcher
Twitter: https://twitter.com/ykilcher
Discord: https://ykilcher.com/discord
BitChute: https://www.bitchute.com/channel/yannic-kilcher
LinkedIn: https://www.linkedin.com/in/ykilcher
BiliBili: https://space.bilibili.com/2017636191

If you want to support me, the best thing to do is to share out the content :)

If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this):
SubscribeStar: https://www.subscribestar.com/yannickilcher
Patreon: https://www.patreon.com/yannickilcher
Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq
Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2
Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m
Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n



Other Videos By Yannic Kilcher


2022-06-15Did Google's LaMDA chatbot just become sentient?
2022-06-03GPT-4chan: This is the worst AI ever
2022-06-01Did I crash the NFT market?
2022-05-13[ML News] DeepMind's Flamingo Image-Text model | Locked-Image Tuning | Jurassic X & MRKL
2022-05-10[ML News] Meta's OPT 175B language model | DALL-E Mega is training | TorToiSe TTS fakes my voice
2022-05-05This A.I. creates infinite NFTs
2022-05-02Author Interview: SayCan - Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
2022-04-30Do As I Can, Not As I Say: Grounding Language in Robotic Affordances (SayCan - Paper Explained)
2022-04-26Author Interview - ACCEL: Evolving Curricula with Regret-Based Environment Design
2022-04-25ACCEL: Evolving Curricula with Regret-Based Environment Design (Paper Review)
2022-04-22LAION-5B: 5 billion image-text-pairs dataset (with the authors)
2022-04-21Sparse Expert Models (Switch Transformers, GLAM, and more... w/ the Authors)
2022-04-17Author Interview - Transformer Memory as a Differentiable Search Index
2022-04-16Transformer Memory as a Differentiable Search Index (Machine Learning Research Paper Explained)
2022-04-10[ML News] Google's 540B PaLM Language Model & OpenAI's DALL-E 2 Text-to-Image Revolution
2022-04-06DALL-E 2 by OpenAI is out! Live Reaction
2022-04-04The Weird and Wonderful World of AI Art (w/ Author Jack Morris)
2022-04-02Author Interview - Improving Intrinsic Exploration with Language Abstractions
2022-04-01Improving Intrinsic Exploration with Language Abstractions (Machine Learning Paper Explained)
2022-03-30[ML News] GPT-3 learns to edit | Google Pathways | Make-A-Scene | CLIP meets GamePhysics | DouBlind
2022-03-29Author Interview - Memory-assisted prompt editing to improve GPT-3 after deployment