DI-star
Kornia
DI-star | Kornia | |
---|---|---|
9 | 11 | |
1,162 | 9,395 | |
1.2% | 1.8% | |
3.3 | 9.4 | |
10 months ago | 4 days ago | |
Python | Python | |
Apache License 2.0 | Apache License 2.0 |
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.
DI-star
-
Better AI ?
There is an AI/bot scene for SC2, I don't have many links but you can start by looking here: https://github.com/opendilab/DI-star https://www.youtube.com/watch?v=fvQF-24IpXs (Harstem and uThermal both have more videos vs different bots).
- [ENG] 2022 GSL S3 Code S RO.20 Group B
-
Any idea about DI-star ? It's an AI model could beat top human players in StarCraft II!
Looks like a simplified AlphaStar using LSTM RNN instead of Pointer Transformer, much heavier supervised imitation learning, Zerg vs Zerg only (with simplified build order module), and a much smaller AlphaStar League: https://github.com/opendilab/DI-star/blob/main/docs/guidance_to_small_scale_training.md
For more information,plz visit out GitHub page:https://github.com/opendilab/DI-star
- Any idea about DI-star?An AI model could beat top human players in StarCraftII
- A large-scale game AI distributed training platform developed for StarCraftII
-
Why can't we make a perfect AI for Starcraft through evolution
First of all, let's discuss what the level of AI is now. If the "level" refers to the capability of competing, the current AI has been very closed to the top human player in some types of games, like chess, Texas Poker, and Mahjong of CARDS, DOTA2 of MOBA, as well as StarCraft2 of RTS. As for other games, if we have enough human resources and computing performance, we also can get similar results. If the "level" has other meanings, like AI agents having human behavior, intelligent NPC can be designed specifically for different people so that they can have different gaming experience. These are all at the stage of issue-defining and exploring new technology solutions. Although traditional game AI is mostly based on hard code, it still has much prior knowledge. In recent years, some hot ML-related techs have performed well in competitiveness while in other fields, they haven't found the perfect entry point. If we expand the conclusions above in detail, the design of game AI can be divided into two parts: issue defining and issue solving. For those competitive issues which have already got complete definitions, their core issue is to explore the optimal strategy based on the evaluation standard, like ladder points. Traditional solutions can deal with less complex scenarios, like chess and Gobang. While machine learning related techs, including deep learning and reinforcement learning, they can perform very well in much more complex games, like StarCraft II. {For this you can try it in DI-star: this project is a reimplementation (with a few improvements) of Alphastar (Only Zerg vs Zerg) based on OpenDILab.}
- Show HN: Come and fight professional AI in StarCraftII
- DI-Star (Starcraft 2 AI, Continuation of AlphaStar)
Kornia
-
[News] Kornia 0.6.6: ParametrizedLine API, load_image support for Apple Windows Developer, integration demos with Hugging Face and many more.
👉 https://github.com/kornia/kornia/releases/tag/v0.6.6
- [P] Kornia: Differential Computer Vision
- Kornia: Differential Computer Vision
-
Hacker News top posts: May 10, 2022
Kornia: Differential Computer Vision\ (3 comments)
- Preprocessing for NN on GPU
-
Top 5 Python libraries for Computer vision
Kornia - Kornia is a differentiable computer vision library for PyTorch. It consists of a set of routines and differentiable modules to solve generic computer vision problems. At its core, the package uses PyTorch as its main backend both for efficiency and to take advantage of the reverse-mode auto-differentiation to define and compute the gradient of complex functions.
-
[D] CPU choice for machine learning server (Epyc vs. Threadripper)
Between "not being sure yet" about GPU operations in pre-processing and choosing high-end CPUs, I think you are overthinking the wrong alternative. Besides DALI, check whether you are using codecs besides nvidia/torchvision-supported jpeg and png, and if other GPU CV libraries meet your needs: torchvision kornia
-
[P] Using PyTorch + NumPy? A bug that plagues thousands of open-source ML projects.
Use kornia.augmentation where this problem is solved doing the augmentations in batch outside the dataloader. https://github.com/kornia/kornia
What are some alternatives?
pytorch-lightning - The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate. [Moved to: https://github.com/PyTorchLightning/pytorch-lightning]
OpenCV - Open Source Computer Vision Library
RobustVideoMatting - Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
Face Recognition - The world's simplest facial recognition api for Python and the command line
thinc - 🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
EasyOCR - Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
pytorch-lightning - Build high-performance AI models with PyTorch Lightning (organized PyTorch). Deploy models with Lightning Apps (organized Python to build end-to-end ML systems). [Moved to: https://github.com/Lightning-AI/lightning]
SimpleCV - The Open Source Framework for Machine Vision
polyaxon - MLOps Tools For Managing & Orchestrating The Machine Learning LifeCycle
multi-object-tracker - Multi-object trackers in Python
Stanza - Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages
gaps - A Genetic Algorithm-Based Solver for Jigsaw Puzzles :cyclone: