Pretrained EfficientNet, MixNet, MobileNetV3, MNASNet A1 and B1, FBNet, Single-Path NAS https://t.co/1cCSJGrNrN #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch
— PyTorch Best Practices (@PyTorchPractice) November 3, 2019
Pretrained EfficientNet, MixNet, MobileNetV3, MNASNet A1 and B1, FBNet, Single-Path NAS https://t.co/1cCSJGrNrN #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch
— PyTorch Best Practices (@PyTorchPractice) November 3, 2019
NanigoNet — Language detector for code-mixed input supporting 150+19 human+programming languages
— ML Review (@ml_review) November 3, 2019
By @mhagiwarahttps://t.co/ftJ2bavQEj pic.twitter.com/iatPqVRT28
I'm really happy w/ caching in https://t.co/14p1S1Pup6. Have expensive preprocessing in your pipeline?
— Josh Gordon (@random_forests) November 2, 2019
ds = tf.data.Dataset.list_files('images/*')
ds = ds.map(load_and_preprocess)
A cache lets you pay for that just once. The speedup is dramatic, and takes one LOC.
Example:
A really convenient way of using Fairness Indicators in your machine learning pipeline: https://t.co/1L0o8KqNyN https://t.co/GZXWZBYXJf pic.twitter.com/HYgQiA1JAG
— hardmaru 😷 (@hardmaru) November 2, 2019
Multi-GPU PageRank performs over 50x faster than @ApacheSpark at similar cost, and can scale to 300GB datasets on @nvidia #DGX2 using @rapidsai cuGraph and @dask_dev. https://t.co/SaZzQcI7Lf
— RAPIDS AI (@rapidsai) November 1, 2019
Keras Tuner is now out of beta! v1 is out on PyPI.https://t.co/riqnIr4auA
— François Chollet (@fchollet) October 31, 2019
Fully-featured, scalable, easy-to-use hyperparameter tuning for Keras & beyond. pic.twitter.com/zUDISXPdBw
Launched yesterday: hosted, shareable TensorBoard dashboards https://t.co/Sv9hnuP1p2
— François Chollet (@fchollet) October 31, 2019
I've open-sourced a Facebook Ad Library scraper for FB's political ads via the official API! This scraper gathers and cleans the data in a way to make it very easy to perform analysis on it! (unfortunately you still need to be approved for the API) https://t.co/67aRTW1ydV
— Max Woolf (@minimaxir) October 31, 2019
See a new example combining Dask and PyTorch for scalable batch prediction.https://t.co/9aB6cU2f5A
— Dask (@dask_dev) October 31, 2019
let me please share with you a full docker setup for serving a @fastai model. The repository includes:
— Radek Osmulski (@radekosmulski) October 31, 2019
✅jupyter NB for training and saving the model
✅starlette endpoint performing inference
✅rails frontend
all < 40 lines of code (excl HTML + train)https://t.co/AMCWLxbCWd pic.twitter.com/0d9n33brVA
State-of-the-Art Natural Language Processing in TensorFlow 2.0
— TensorFlow (@TensorFlow) October 30, 2019
Discover how you can use the @HuggingFace Transformers library with TensorFlow to fine-tune a Transformer model.
Read the blog ↓https://t.co/fhhTLXonuL
TensorTrade - An open source reinforcement learning framework for training, evaluating, and deploying robust trading agents. https://t.co/40Xpd4OC7X #python pic.twitter.com/Bufkg119NS
— Python Weekly (@PythonWeekly) October 29, 2019