Want to use a non-fastai architecture and take advantage of all fastai's transfer learning goodness? Here's lot of examples to show you how easy it is! https://t.co/AG7M8kQKZL
— Jeremy Howard (@jeremyphoward) January 28, 2019
Want to use a non-fastai architecture and take advantage of all fastai's transfer learning goodness? Here's lot of examples to show you how easy it is! https://t.co/AG7M8kQKZL
— Jeremy Howard (@jeremyphoward) January 28, 2019
JupyText – Jupyter notebooks as Markdown documents, Julia, Python or R scripts
— ML Review (@ml_review) January 27, 2019
By @marcwouts
– use your favourite IDE & code refactoring
– clear and meaningfull diffs inside VCShttps://t.co/OZqF17MEf9
This telegram chatbot can notify every events from your deep learning training processes with just a dedicated callback in Keras / TF. This seems to be very useful since nowadays many training take several days. https://t.co/veJMJHDaEH pic.twitter.com/SJMUYlHwHz
— 정지훈 Jihoon Jeong (@hiconcep) January 26, 2019
PyTorch is now installed by default on Google Colaboratory.
— PyTorch (@PyTorch) January 25, 2019
Go ahead and `import torch`, `import torchvision`, `import torchtext` pic.twitter.com/PISPoegATV
TFDV (https://t.co/Lv4n5Hnnfw) is a super handy tool to quickly analyze a new dataset, discover its schema automagically, detect outliers & train/test discrepancies, monitor that inputs remain consistent in production, and more.
— Aurélien Geron (@aureliengeron) January 25, 2019
Try it out using Colab: https://t.co/OfigtqSFOe
1/ Excited to share something I've been working on for a while now. Troubleshooting Deep Neural Networks: a decision tree for debugging your model and improving performance. https://t.co/EeGxZ2SKz4
— Josh Tobin (@josh_tobin_) January 25, 2019
it depends: A dialog about dependencies
— Jim Hester (@jimhester_) January 25, 2019
My talk about dependencies in #rstats given at #rstudioconf 2019
video 📹: https://t.co/q6Je94JFkS
slides 📽️: https://t.co/7uUF1H0drK
package 📦: https://t.co/RtdcQByMMJ pic.twitter.com/qBDw5M7FX5
loguru: Python Logging Made (Stupidly) Simple https://t.co/NZRvOElDAT
— PyCoder’s Weekly (@pycoders) January 24, 2019
Fast #Python item counting in little RAM: new #Bounter release with stability & documentation fixes 🛠https://t.co/qibC8A4Bjl
— Gensim (@gensim_py) January 24, 2019
TorchSeg - Fast, modular reference implementation and easy training of Semantic Segmentation algorithms in PyTorch. https://t.co/qg81kjkux6
— Python Trending (@pythontrending) January 23, 2019
The future package is one of the most interesting packages to hit the #rstats universe and I use it all the time. Worth a look. (Also discussed on recent @NSSDeviations) https://t.co/bW6pjg41ww
— Roger D. Peng (@rdpeng) January 21, 2019
If you want to spend some time exploring a UMAP embedding of images (like MNIST) @GrantCuster put together a nice tool: https://t.co/IF9V5u3Fn9
— Leland McInnes (@leland_mcinnes) January 18, 2019