New code example on https://t.co/m6mT8SrKDD: image super-resolution, by Xingyu Longhttps://t.co/XAEpuBgPRf
— François Chollet (@fchollet) August 28, 2020
New code example on https://t.co/m6mT8SrKDD: image super-resolution, by Xingyu Longhttps://t.co/XAEpuBgPRf
— François Chollet (@fchollet) August 28, 2020
Oh wow, I had missed this! Really interesting open #recsys course by Google that goes all the way from basic content-based and matrix factorization to Deep Neural Nets (all of it with code on Colab!): https://t.co/jMY5u3OJBk
— Xavier Amatriain - BLM (@xamat) August 27, 2020
Check out these extensive notes and tips on Docker from @HamelHusain https://t.co/ULvaFqQ8Wd
— Jeremy Howard (@jeremyphoward) August 26, 2020
New tutorial!🚀
— Adrian Rosebrock (@PyImageSearch) August 24, 2020
OCR Handwriting Recognition with #OpenCV, #Keras, and #TensorFlow 2
- Full tutorial w/ #Python code
- Learn how to OCR handwriting
- Includes pre-trained modelhttps://t.co/8IILGyrupA 👍#DeepLearning #MachineLearning #ArtificialInteligence #AI #DataScience pic.twitter.com/gSRAwr3NRB
“How to build a real-time fraud detection pipeline using Faust and MLFlow” by Bogdan Cojocarhttps://t.co/szBGFGonG7 more real-time streaming analytics in python! MLflow/Kafka have @RAPIDSai integration, hopefully #Faust will add GPU support so this can be faster & cheaper.
— Joshua Patterson (@datametrician) August 22, 2020
100x Faster Machine Learning Model Ensembling with @rapidsai cuML and Scikit-Learn Meta-Estimators by Nick Becker https://t.co/GDr3KvsAlS
— Bojan Tunguz (@tunguz) August 18, 2020
A very simple Kaggle notebook that shows how to use KerasTuner to automatically find a high-performing model: https://t.co/LjXfpZJACw
— François Chollet (@fchollet) August 17, 2020
Includes finding the best image augmentation config as part of the parameter search (this is actually one of the most important things to tune) pic.twitter.com/pasgIGHVx5
Someone asked about converting #CSV to @ApacheParquet on the @RAPIDSai slack, and @rodaramburu of @blazingsql reminded us of this excellent blog https://t.co/0w68CrwL8k Even on a @NVIDIAGeForce 1060 we can convert nearly half a TB of data in 30 mins. 🔥🔥🔥 10x cost saving ftw!
— Joshua Patterson (@datametrician) August 17, 2020
Convert horses to zebras with this CycleGAN model by @A_K_Nain, now on https://t.co/m6mT8SrKDD:https://t.co/2KeopZUuJe
— François Chollet (@fchollet) August 17, 2020
Definitely the most concise and elegant implementation of CycleGAN I've seen anywhere -- around 350 lines end-to-end. Train on 8 GPUs by just adding 1 line. pic.twitter.com/ZgHg0TTaHC
This is a great way to learn how to preprocess your own data with 🤗Transformers before using Trainer or a classic PyTorch/Keras training loop! https://t.co/vud0r6nzIO
— Sylvain Gugger (@GuggerSylvain) August 17, 2020
Slides from my #rstatsnyc talk on the widyr package, for widening, operating, and then re-tidying a dataset
— David Robinson (@drob) August 15, 2020
Slides: https://t.co/Zz0b6pa0c3
Package 📦: https://t.co/1gjFrq6qQu pic.twitter.com/PBqXxUzBoY
Slides and code from my #rstatsnyc talk on "Forecasting ensembles using fable" now available at https://t.co/wB1GhYXqE0. #rstats #forecasting Thanks to @mitchoharawild for the packages. pic.twitter.com/GTpKLQxz0Y
— Rob J Hyndman (@robjhyndman) August 14, 2020