Automatic Model Compression (AutoMC) framework from Tencent: https://t.co/I2Z3hPBf0W
— Pete Warden (@petewarden) November 2, 2018
This looks like an awesome new way to optimize @TensorFlow models!
Automatic Model Compression (AutoMC) framework from Tencent: https://t.co/I2Z3hPBf0W
— Pete Warden (@petewarden) November 2, 2018
This looks like an awesome new way to optimize @TensorFlow models!
More gtable polish. There is now a pkgdown site if you want to learn more about it https://t.co/A7MTEDNeXd
— Thomas Lin Pedersen (@thomasp85) November 2, 2018
Just learned that there's a sklearn_porter package -- a tool to "transpile trained scikit-learn estimators to C, Java, JavaScript and others" Could come in handy for some https://t.co/Q4NFr3Txnl pic.twitter.com/hqnJKIOwKq
— Sebastian Raschka (@rasbt) November 1, 2018
Very pleased by the recent work done by @hug_nicolas to speed-up our pure Python + @numba_jit prototype implementation of gradient boosted trees: https://t.co/Ii6bAqmoRa The master branch is now competitive with LightGBM on the Higgs boson benchmark dataset.
— Olivier Grisel (@ogrisel) November 1, 2018
Neuron: an extension for @code that uses Jupyter to render nice-looking R #rstats and #Python output, without the downsides of developing code in a notebook https://t.co/ORDO3pqpI2 pic.twitter.com/ztnNwepLsp
— David Smith (@revodavid) October 31, 2018
There's a nice blog post today describing AdaNet, one project in our overall efforts in the AutoML research area, along with accompanying open source release and tutorial notebooks (see last paragraph of the blog post for links to these):https://t.co/mnfP2bGSao
— Jeff Dean (@JeffDean) October 30, 2018
Introducing ReviewNb, visual diffs for #Jupyter Notebooks on GitHub. It was fun building it, hope you like using it :D#DataScience #Python #VersionControlhttps://t.co/7lUdNx0hJE
— Amit Rathi (@amittrathi) October 30, 2018
Faster R-CNN and Mask R-CNN in PyTorch 1.0 https://t.co/p0dFhwbHf5 #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch
— PyTorch Best Practices (@PyTorchPractice) October 28, 2018
Update on the Pandas on Ray project (now "Modin"): https://t.co/TTFHKtrbhW Their read_csv function looks super impressive. Ok, it's on a 144-core node with 1Tb RAM, but great for these projects where we need quick results + have access to resources but no time to learn a new API pic.twitter.com/kk5bii1Hfo
— Sebastian Raschka (@rasbt) October 26, 2018
New release of fastprogress for fastai. Prettier and completely coded in HTML so it doesn't rely on widgets anymore which means an easier installation and compatibility with Colab ^^ pic.twitter.com/G003usVe79
— Sylvain Gugger (@GuggerSylvain) October 25, 2018
✂️ Got snippets? Keep 'em organized…
— Mara Averick (@dataandme) October 25, 2018
📦 "snippr: Manage, share, and install RStudio code snippets" by @drobhttps://t.co/G266TRbuSM #rstats
MaskRCNN-Benchmark:
— PyTorch (@PyTorch) October 24, 2018
- A fast, modular reference of {Mask,Faster}RCNN
- by @fvsmassa (PyTorch), optimized by Nvidia
- reusable components, pre-trained models
- optimized inference, live demo
Hope to see mmdetection and other great projects reuse the code!https://t.co/lryFWLxGwc pic.twitter.com/JiYZHHkQk7