http://simonwillison.net/2018-12-31T03:56:45+00:00Simon Willison2018-12-31T03:56:45+00:002018-12-31T03:56:45+00:00https://simonwillison.net/2018/Dec/31/the-friendship-that-made-google-huge/#atom-tag

<p><strong><a href="https://www.newyorker.com/magazine/2018/12/10/the-friendship-that-made-google-huge">The Friendship That Made Google Huge</a></strong></p> The New Yorker profiles Jeff Dean and Sanjay Ghemawat, Google’s first and only level 11 Senior Fellows. This is some of the best writing on complex software engineering topics (map-reduce, Tensor Flow and the like) aimed at a general audience that I’ve ever seen. Also a very compelling case study in pair programming. <p>Tags: <a href="https://simonwillison.net/tags/google">google</a>, <a href="https://simonwillison.net/tags/mapreduce">mapreduce</a>, <a href="https://simonwillison.net/tags/new-yorker">new-yorker</a>, <a href="https://simonwillison.net/tags/tensorflow">tensorflow</a></p>

2018-06-20T21:10:48+00:002018-06-20T21:10:48+00:00https://simonwillison.net/2018/Jun/20/teachable-machine-tensorflowjs/#atom-tag

<p><strong><a href="https://beta.observablehq.com/@nsthorat/how-to-build-a-teachable-machine-with-tensorflow-js">Notebook: How to build a Teachable Machine with TensorFlow.js</a></strong></p> This is a really cool Observable notebook. It explains how to build image classification that runs in the browser on top of Tensorflow.js, and includes interactive demos that hook into your webcam and let you hold up items and use them to train a classifier. Since it’s built on Observable every single underlying line of source code is available to browse as part of the essay. <p><small></small>Via <a href="https://twitter.com/nsthorat/status/10094961298919465172">@nsthorat</a></small></p> <p>Tags: <a href="https://simonwillison.net/tags/javascript">javascript</a>, <a href="https://simonwillison.net/tags/machine-learning">machine-learning</a>, <a href="https://simonwillison.net/tags/explorables">explorables</a>, <a href="https://simonwillison.net/tags/tensorflow">tensorflow</a>, <a href="https://simonwillison.net/tags/observable">observable</a></p>

2018-02-21T05:31:35+00:002018-02-21T05:31:35+00:00https://simonwillison.net/2018/Feb/21/pytorch/#atom-tag

<p><strong><a href="http://www.goldsborough.me/ml/ai/python/2018/02/04/20-17-20-a_promenade_of_pytorch/">A Promenade of PyTorch</a></strong></p> Useful overview of the PyTorch machine learning library from Facebook AI Research described as “a Python library enabling GPU-accelerated tensor computation”. Similar to TensorFlow, but where TensorFlow requires you to explicitly construct an execution graph PyTorch instead lets you write regular Python code (if statements, for loops etc) which PyTorch then uses to construct the execution graph for you. <p>Tags: <a href="https://simonwillison.net/tags/machine-learning">machine-learning</a>, <a href="https://simonwillison.net/tags/python">python</a>, <a href="https://simonwillison.net/tags/tensorflow">tensorflow</a>, <a href="https://simonwillison.net/tags/pytorch">pytorch</a></p>

2017-11-14T04:24:48+00:002017-11-14T04:24:48+00:00https://simonwillison.net/2017/Nov/14/how-to-train-your-own-object-detector/#atom-tag

<p><strong><a href="https://towardsdatascience.com/how-to-train-your-own-object-detector-with-tensorflows-object-detector-api-bec72ecfe1d9">How to train your own Object Detector with TensorFlow’s Object Detector API</a></strong></p> Dat Tran built a TensorFlow model that can detect raccoons! Impressive results, especially given it was only trained on 200 raccoon images from Google Image search. <p><small></small>Via <a href="https://github.com/datitran/raccoon_dataset">GitHub - datitran/raccoon_dataset: The dataset is used to train my own raccoon detector and I blogged about it on Medium</a></small></p> <p>Tags: <a href="https://simonwillison.net/tags/computer-vision">computer-vision</a>, <a href="https://simonwillison.net/tags/tensorflow">tensorflow</a>, <a href="https://simonwillison.net/tags/raccoons">raccoons</a></p>

2017-11-08T19:32:59+00:002017-11-08T19:32:59+00:00https://simonwillison.net/2017/Nov/8/eager-execution-tensorflow/#atom-tag

<p><strong><a href="https://developers.googleblog.com/2017/10/eager-execution-imperative-define-by.html">Eager Execution: An imperative, define-by-run interface to TensorFlow</a></strong></p> Lets you evaluate TensorFlow expressions interactively in Python without needing to constantly run tf.Session().run(variable). <p>Tags: <a href="https://simonwillison.net/tags/python">python</a>, <a href="https://simonwillison.net/tags/tensorflow">tensorflow</a></p>

2017-11-08T17:57:54+00:002017-11-08T17:57:54+00:00https://simonwillison.net/2017/Nov/8/tensorflow-101/#atom-tag

<p><strong><a href="https://mubaris.com/2017-10-21/tensorflow-101?utm_content=bufferc370a&amp;utm_medium=social&amp;utm_source=twitter.com&amp;utm_campaign=buffer">TensorFlow 101</a></strong></p> Concise, readable introduction to TensorFlow, with Python examples you can execute (and visualize) in Jupyter. <p>Tags: <a href="https://simonwillison.net/tags/python">python</a>, <a href="https://simonwillison.net/tags/tensorflow">tensorflow</a></p>