CodeRL
XMem
Our great sponsors
CodeRL | XMem | |
---|---|---|
4 | 11 | |
475 | 1,588 | |
1.9% | - | |
4.2 | 6.3 | |
7 months ago | about 1 month ago | |
Python | Python | |
BSD 3-clause "New" or "Revised" License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
CodeRL
-
[D] Most important AI Paper´s this year so far in my opinion + Proto AGI speculation at the end
CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning Paper: https://arxiv.org/pdf/2207.01780.pdf Github: https://github.com/salesforce/CodeRL
- AI Coding with CodeRL: Toward Mastering Program Synthesis with Deep RL
- [R] CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning
XMem
-
[D] Which open source models can replicate wonder dynamics's drag'n'drop cg characters?
Use Segmentation Model (SAM) combined with Inpainting model (E2FGVI) and Xmem to cut out the live action subject.
-
Track-Anything: a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything and XMem.
Nvm just found the occlusion video on https://github.com/hkchengrex/XMem holy shit
- XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
-
[D] Most important AI Paper´s this year so far in my opinion + Proto AGI speculation at the end
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model ( Added because of the Atkinson-Shiffrin Memory Model ) Paper: https://arxiv.org/abs/2207.07115 Github: https://github.com/hkchengrex/XMem
- [D] Most Popular AI Research July 2022 pt. 2 - Ranked Based On GitHub Stars
- Most Popular AI Research July 2022 pt. 2 - Ranked Based On GitHub Stars
-
I trained a neural net to watch Super Smash Bros
Yeah MiVOS would speed up your tagging a lot. I also was curious if you saw XMem which just came out. I found that worked really well too.
-
University of Illinois Researchers Develop XMem; A Long-Term Video Object Segmentation Architecture Inspired By Atkinson-Shiffrin Memory Model
Continue reading | Check out the paper and github link.
-
[R] Unicorn: 🦄 : Towards Grand Unification of Object Tracking(Video Demo)
Have you check XMem?
What are some alternatives?
flash-attention - Fast and memory-efficient exact attention
yolov7 - Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
RHO-Loss
flash-attention-jax - Implementation of Flash Attention in Jax
NAFNet - The state-of-the-art image restoration model without nonlinear activation functions.
EfficientZero - Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.
deeplab2 - DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a unified and state-of-the-art TensorFlow codebase for dense pixel labeling tasks.
msn - Masked Siamese Networks for Label-Efficient Learning (https://arxiv.org/abs/2204.07141)
Cream - This is a collection of our NAS and Vision Transformer work. [Moved to: https://github.com/microsoft/AutoML]
DeepSpeed - DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.