This media is not supported in your browser
VIEW IN TELEGRAM
๐ฎ SAM-PT: Segment Anything + Tracking ๐ฎ
โญ๏ธ SAM-PT is the first method to utilize sparse point propagation for Video Object Segmentation (VOS).
๐ Review https://t.ly/QLMG
๐ Paper arxiv.org/pdf/2307.01197.pdf
๐ Project www.vis.xyz/pub/sam-pt/
๐ Code github.com/SysCV/sam-pt
https://t.iss.one/DataScienceT
โญ๏ธ SAM-PT is the first method to utilize sparse point propagation for Video Object Segmentation (VOS).
๐ Review https://t.ly/QLMG
๐ Paper arxiv.org/pdf/2307.01197.pdf
๐ Project www.vis.xyz/pub/sam-pt/
๐ Code github.com/SysCV/sam-pt
https://t.iss.one/DataScienceT
โคโ๐ฅ1โค1๐1
๐ธThe Drunkardโs Odometry: Estimating Camera Motion in Deforming Scenes
๐ฅ Github: https://github.com/UZ-SLAMLab/DrunkardsOdometry
โฉ Paper: https://arxiv.org/pdf/2306.16917v1.pdf
๐จ Dataset: https://paperswithcode.com/dataset/drunkard-s-dataset
https://t.iss.one/DataScienceT
๐ฅ Github: https://github.com/UZ-SLAMLab/DrunkardsOdometry
โฉ Paper: https://arxiv.org/pdf/2306.16917v1.pdf
๐จ Dataset: https://paperswithcode.com/dataset/drunkard-s-dataset
https://t.iss.one/DataScienceT
โคโ๐ฅ2
This media is not supported in your browser
VIEW IN TELEGRAM
๐ช Making a web app generator with open ML models
๐ฅ Github: https://github.com/huggingface/blog/blob/main/text-to-webapp.md
๐ HuggingFace: https://huggingface.co/blog/text-to-webapp
๐Demo: https://huggingface.co/spaces/jbilcke-hf/webapp-factory-wizardcoder
https://t.iss.one/DataScienceT
๐ฅ Github: https://github.com/huggingface/blog/blob/main/text-to-webapp.md
๐ HuggingFace: https://huggingface.co/blog/text-to-webapp
๐Demo: https://huggingface.co/spaces/jbilcke-hf/webapp-factory-wizardcoder
https://t.iss.one/DataScienceT
โคโ๐ฅ3๐2
๐คณFiltered-Guided Diffusion
๐ฅ Github: https://github.com/jaclyngu/filteredguideddiffusion
โฉ Paper: https://arxiv.org/pdf/2306.17141v1.pdf
๐จ Dataset: https://paperswithcode.com/dataset/afhq
https://t.iss.one/DataScienceT
๐ฅ Github: https://github.com/jaclyngu/filteredguideddiffusion
โฉ Paper: https://arxiv.org/pdf/2306.17141v1.pdf
๐จ Dataset: https://paperswithcode.com/dataset/afhq
https://t.iss.one/DataScienceT
โคโ๐ฅ1โค1๐1
This media is not supported in your browser
VIEW IN TELEGRAM
๐ชฉ DISCO: Human Dance Generation
โญ๏ธ NTU (+ #Microsoft) unveils DISCO: a big step towards the Human Dance Generation.
๐ Review https://t.ly/cNGX
๐ Paper arxiv.org/pdf/2307.00040.pdf
๐Project: disco-dance.github.io/
๐ Code github.com/Wangt-CN/DisCo
https://t.iss.one/DataScienceT
โญ๏ธ NTU (+ #Microsoft) unveils DISCO: a big step towards the Human Dance Generation.
๐ Review https://t.ly/cNGX
๐ Paper arxiv.org/pdf/2307.00040.pdf
๐Project: disco-dance.github.io/
๐ Code github.com/Wangt-CN/DisCo
https://t.iss.one/DataScienceT
๐3โค1
Building an Image Recognition API using Flask.
Step 1: Set up the project environment
1. Create a new directory for your project and navigate to it.
2. Create a virtual environment (optional but recommended):
(Image 1.)
3. Install the necessary libraries (image 2.)
Step 2: Create a Flask Web Application
Create a new file called app.py in the project directory (image 3.)
Step 3: Launch the Flask Application
Save the changes and run the Flask application (image 4.)
Step 4: Test the API
Your API is now up and running and you can send images to /predict via HTTP POST requests.
You can use tools such as curl or Postman to test the API.
โข An example of using curl (image 5.)
โข An example using Python queries (image 6.)
https://t.iss.one/DataScienceT
Step 1: Set up the project environment
1. Create a new directory for your project and navigate to it.
2. Create a virtual environment (optional but recommended):
(Image 1.)
3. Install the necessary libraries (image 2.)
Step 2: Create a Flask Web Application
Create a new file called app.py in the project directory (image 3.)
Step 3: Launch the Flask Application
Save the changes and run the Flask application (image 4.)
Step 4: Test the API
Your API is now up and running and you can send images to /predict via HTTP POST requests.
You can use tools such as curl or Postman to test the API.
โข An example of using curl (image 5.)
โข An example using Python queries (image 6.)
https://t.iss.one/DataScienceT
โคโ๐ฅ2๐2๐1
This media is not supported in your browser
VIEW IN TELEGRAM
๐ Hierarchical Open-vocabulary Universal Image Segmentation
Decoupled text-image fusion mechanism and representation learning modules for both "things" and "stuff".
๐ฅ Github: https://github.com/berkeley-hipie/hipie
๐ Paper: https://arxiv.org/abs/2307.00764v1
๐Project: https://people.eecs.berkeley.edu/~xdwang/projects/HIPIE/
๐ Dataset: https://paperswithcode.com/dataset/pascal-panoptic-parts
https://t.iss.one/DataScienceT
Decoupled text-image fusion mechanism and representation learning modules for both "things" and "stuff".
๐ฅ Github: https://github.com/berkeley-hipie/hipie
๐ Paper: https://arxiv.org/abs/2307.00764v1
๐Project: https://people.eecs.berkeley.edu/~xdwang/projects/HIPIE/
๐ Dataset: https://paperswithcode.com/dataset/pascal-panoptic-parts
https://t.iss.one/DataScienceT
โคโ๐ฅ1
๐Foundation Model for Endoscopy Video Analysis
๐ฅ Github: https://github.com/med-air/endo-fm
โฉ Paper: https://arxiv.org/pdf/2306.16741v1.pdf
๐จ Dataset: https://paperswithcode.com/dataset/kumc
https://t.iss.one/DataScienceT
๐ฅ Github: https://github.com/med-air/endo-fm
โฉ Paper: https://arxiv.org/pdf/2306.16741v1.pdf
๐จ Dataset: https://paperswithcode.com/dataset/kumc
https://t.iss.one/DataScienceT
โคโ๐ฅ3
We launched a special bot some time ago to download all scientific, software and mathematics books The bot contains more than thirty million books, and new books are downloaded first, In addition to the possibility of downloading all articles and scientific papers for free
To request a subscription: talk to @Hussein_Sheikho
To request a subscription: talk to @Hussein_Sheikho
โค3๐3
This media is not supported in your browser
VIEW IN TELEGRAM
๐จ Making ML-powered web games with Transformers.js
The goal of this tutorial is to show you how easy it is to make your own ML-powered web game.
๐ฅ Github: https://github.com/xenova/doodle-dash
๐ค Hugging face: https://huggingface.co/blog/ml-web-games
โญ๏ธ Code: https://github.com/xenova/doodle-dash
๐Demo: https://huggingface.co/spaces/Xenova/doodle-dash
๐ Dataset: https://huggingface.co/datasets/Xenova/quickdraw-small
https://t.iss.one/DataScienceT
The goal of this tutorial is to show you how easy it is to make your own ML-powered web game.
๐ฅ Github: https://github.com/xenova/doodle-dash
๐ค Hugging face: https://huggingface.co/blog/ml-web-games
โญ๏ธ Code: https://github.com/xenova/doodle-dash
๐Demo: https://huggingface.co/spaces/Xenova/doodle-dash
๐ Dataset: https://huggingface.co/datasets/Xenova/quickdraw-small
https://t.iss.one/DataScienceT
โค1๐1
๐ฆ Focused Transformer: Contrastive Training for Context Scaling
LongLLaMA, a large language model capable of handling long contexts of 256k tokens or even more.
๐ฅ Github: https://github.com/cstankonrad/long_llama
๐ Paper: https://arxiv.org/abs/2307.03170v1
๐ฅ Colab: https://colab.research.google.com/github/CStanKonrad/long_llama/blob/main/long_llama_colab.ipynb
๐ Dataset: https://paperswithcode.com/dataset/pg-19
https://t.iss.one/DataScienceT
LongLLaMA, a large language model capable of handling long contexts of 256k tokens or even more.
๐ฅ Github: https://github.com/cstankonrad/long_llama
๐ Paper: https://arxiv.org/abs/2307.03170v1
๐ฅ Colab: https://colab.research.google.com/github/CStanKonrad/long_llama/blob/main/long_llama_colab.ipynb
๐ Dataset: https://paperswithcode.com/dataset/pg-19
https://t.iss.one/DataScienceT
๐3โค1โคโ๐ฅ1
This media is not supported in your browser
VIEW IN TELEGRAM
ContainerGym: A Real-World Reinforcement Learning Benchmark for Resource Allocation โป๏ธ
๐ฅ Github: https://github.com/pendu/containergym
โฉ Paper: https://arxiv.org/pdf/2307.02991v1.pdf
๐จ Dataset: https://paperswithcode.com/dataset/openai-gym
https://t.iss.one/DataScienceT
๐ฅ Github: https://github.com/pendu/containergym
โฉ Paper: https://arxiv.org/pdf/2307.02991v1.pdf
๐จ Dataset: https://paperswithcode.com/dataset/openai-gym
https://t.iss.one/DataScienceT
๐1
๐ฅ Chat Downloader
A simple tool used to retrieve chat messages from livestreams, videos, clips and past broadcasts.
- YouTube.com
- Zoom.us
- Facebook.com
- Twitch.tv
๐ฅ Github
๐ Docs
https://t.iss.one/DataScienceT
A simple tool used to retrieve chat messages from livestreams, videos, clips and past broadcasts.
- YouTube.com
- Zoom.us
- Facebook.com
- Twitch.tv
$ pip install chat-downloader
Using:
# termimal
$ chat_downloader https://www.youtube.com/watch?v=video_link --output chat.json
# Python script
from chat_downloader import ChatDownloader
url = 'https://www.youtube.com/watch?v=video_link'
chat = ChatDownloader().get_chat(url)
for message in chat:
chat.print_formatted(message)
๐ฅ Github
๐ Docs
https://t.iss.one/DataScienceT
โค5๐2
๐ฅ Tkinter Designer
An easy and fast way to create a Python GUI ๐
๐ฅ Github
https://t.iss.one/DataScienceT
An easy and fast way to create a Python GUI ๐
๐ฅ Github
https://t.iss.one/DataScienceT
๐6โค2
Benchmarking Test-Time Adaptation against Distribution Shifts in Image Classification
๐ฅ Github: https://github.com/yuyongcan/benchmark-tta
โฉ Paper: https://arxiv.org/pdf/2307.03133v1.pdf
๐จ Dataset: https://paperswithcode.com/dataset/imagenet
https://t.iss.one/DataScienceT
๐ฅ Github: https://github.com/yuyongcan/benchmark-tta
โฉ Paper: https://arxiv.org/pdf/2307.03133v1.pdf
๐จ Dataset: https://paperswithcode.com/dataset/imagenet
https://t.iss.one/DataScienceT
โค2๐2