Numyard_DataScience (@numyard_ds) header
Numyard_DataScience (@numyard_ds) profile picture

Numyard_DataScience

@numyard_ds

Data Science Group that focuses on high quality data science programs, discussions and problem-solving

 Bangalore
numyard.com
Joined October 2019
  • Tweets129
  • Following145
  • Followers245
108Media
Photo by Numyard_DataScience (@numyard_ds)Photo by Numyard_DataScience (@numyard_ds)Photo by Numyard_DataScience (@numyard_ds)Photo by Numyard_DataScience (@numyard_ds)Photo by Numyard_DataScience (@numyard_ds)Photo by Numyard_DataScience (@numyard_ds)Photo by Numyard_DataScience (@numyard_ds)Photo by Numyard_DataScience (@numyard_ds)Photo by Numyard_DataScience (@numyard_ds)Photo by Numyard_DataScience (@numyard_ds)
Numyard_DataScience retweeted
Ketharinath Kamalanathan (@kknath) profile picture
Ketharinath Kamalanathan@kknath1 Jan 2019
Python 3 Beginners Cheat sheet #Python #algorithms #DataScience #DataScientists #programmer #programming #Coding #cheatsheet #data #DataAnalytics #fintech #MachineLearning #ML #Artificialintelligence #AI #DeepLearning #PredictiveAnalytics @antgrasso @kknath Pl retweet
Image from Ketharinath Kamalanathan (@kknath)
46
2
55
Numyard_DataScience retweeted
Andreas Kirsch 🇺🇦 (@BlackHC) profile picture
Andreas Kirsch 🇺🇦
@BlackHC9 Apr 2020
🔥 Has your PyTorch code ever crashed because it ran out-of-memory in CUDA, and you had to fiddle with batch sizes repeatedly? 🔥 What if we could just write code that adapted to the available memory instead of resorting to brittle hand-tuning? 🤯 👉 github.com/BlackHC/toma🤗
GitHub - BlackHC/toma: Helps you write algorithms in PyTorch that adapt to the available (CUDA)...

GitHub - BlackHC/toma: Helps you write algorithms in PyTorch that adapt to the available (CUDA)...

Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory - BlackHC/toma

github.com
9
56
6
255
Numyard_DataScience retweeted
Peter Beshai (@pbesh) profile picture
Peter Beshai@pbesh21 Dec 2019
Put together a little #dataviz proof of concept during a hack week at work last week. It's a 3D faceted search UI using #reactjs, #threejs, and react-three-fiber. 50,000 objects at 60 FPS in the browser is pretty sweet!!
42
409
55
2,273
Numyard_DataScience retweeted
Jeremy Howard (@jeremyphoward) profile picture
Jeremy Howard
@jeremyphoward11 Jan 2020
“Meet AdaMod: a new deep learning optimizer with memory” by Less Wright link.medium.com/CfAtYwooa3
Meet AdaMod: a new deep learning optimizer with memory

Meet AdaMod: a new deep learning optimizer with memory

AdaMod is a new deep learning optimizer that builds on Adam, but provides an automatic warmup heuristic and long term learning rate

lessw.medium.com
3
169
3
708
Numyard_DataScience retweeted
Towards Data Science (@TDataScience) profile picture
Towards Data Science
@TDataScience22 Dec 2019
Polynote: the new Jupyter? buff.ly/394N8Bh
12
2
51
Load more