Classifying Handwritten Digits with TF.Learn - Machine Learning Recipes #7

312 437
33.2
Следующее
Популярные
77 дней – 3 3260:25
The 2-cut cake challenge
107 дней – 1 6690:59
Build with Gemini Nano on Android
Опубликовано 16 августа 2016, 20:31
Last time we wrote an image classifier using TensorFlow for Poets. This time, we’ll write a basic one using TF.Learn. To make it easier for you to try this out, I wrote a Jupyter Notebook for this episode -- goo.gl/NNlMNu -- and I’ll start with a quick screencast of installing TensorFlow using Docker, and serving the notebook. This is a great way to get all the dependencies installed and properly configured. I've linked some additional notebooks below you can try out, too. Next, I’ll start introducing a linear classifier. My goal here is just to get us started. I’d like to spend a lot more time on this next episode, if there’s interest? I have a couple alternate ways of introducing them that I think would be helpful (and I put some exceptional links below for you to check out to learn more, esp. Colah's blog and CS231n - wow!). Finally, I’ll show you how to reproduce those nifty images of weights from TensorFlow.org's Basic MNIST’s tutorial.

Jupyter Notebook: goo.gl/NNlMNu

Docker images: goo.gl/8fmqVW

MNIST tutorial: goo.gl/GQ3t7n

Visualizing MNIST: goo.gl/ROcwpR (this blog is outstanding)

More notebooks: goo.gl/GgLIh7

More about linear classifiers: goo.gl/u2f2NE

Much more about linear classifiers: goo.gl/au1PdG (this course is outstanding, highly recommended)

More TF.Learn examples: goo.gl/szki63

Thanks for watching, and have fun! For updates on new episodes, you can find me on Twitter at www.twitter.com/random_forests
автотехномузыкадетское