はてなブックマーク

https://blog.tensorflow.org/2022/09/announcing-tensorflow-official-build-collaborators.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgwYbl0yCfhpq9TY7E-8Pnn1c3a8dm_K5z7JPm56Hz3RpzQ2spN4rIkiTQiZzSEF8ZgS6wjtpplVuBmyHbk7CCXi843sO7jl5DpxIaT4Jt5pSTLsAVWB7LFaPDjCYjuUDEJqC2uInko31ft2ap-uKt5PjQ0LM6TTrX7-phltjU4GYxpwqan-4rws9t0/s1600/tensorflow-content-moderation-using-machine-learning-a-d

https://blog.tensorflow.org/2022/05/whats-new-in-tensorflow-29.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgYIMKKNGUkhWyF3gL1qLpn7cQ3iQu5GleP-36OHbTJwn90YdRUk8vGTefc9ctjwPcJhyBbFlprd581nDsWEKfMAeAo9xuX8zKfxti8Fvl2f2v69Qmvt695cCJY1dfVPbMIlfWqMFKMEyBCgIaRLXypYCrHlob-OiAb0mvVbhmBEt65-agfmRWDMuaI/s1600/image1.png May 18, 2022 — Posted by Goldie Gadde and Douglas Yarrington for the

https://blog.tensorflow.org/2022/04/video-classification-on-edge-devices.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiZEUGTtz5pQ1Oz86fmupeAjEoXcDZ9Ar4I4F5YhL6aNJbyAbz-AIJl9LRb-mzQ4Yh80VgEUM1HFhQaLWHeArM39HlOAwuVxHQw4lczTLqP0sSVloprJTx-blhannqi5tnsJksAQv7PpRQqj5IwgUdoxcrMpDjBNiwUJ32ljMMSPl9djYefKqpmnhWF/s1600/image3.gif April 14, 2022 — Posted by Dan Kondratyuk, Liangzhe Yuan, G

Posted by Sibon Li, Jan Pfeifer and Bryan Perozzi and Douglas Yarrington Today, we are excited to release TensorFlow Graph Neural Networks (GNNs), a library designed to make it easy to work with graph structured data using TensorFlow. We have used an earlier version of this library in production at Google in a variety of contexts (for example, spam and anomaly detection, traffic estimation, YouTub

https://blog.tensorflow.org/2021/08/3d-pose-detection-with-mediapipe-blazepose-ghum-tfjs.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEju5BNMgQYeE9f8fTIExf2qW4JTveDA2sfk5HmAQOZamLVBOPUKcVKkObW_6TfgTTr08usiwi4y1gvVhQfrkAzOhQeuHRa41IN9MvfIOXGqPIsbqsFAxL1USY3o21xOSvhyphenhyphenYHGSaXe8mbA/s0/TF+image+2.gif August 30, 2021 — Posted by Ivan Grishchenko, Valentin Bazarevsky, Eduard Gab

At Google I/O this year, we are excited to announce several product updates that simplify training and deployment of object detection models on mobile devices: On-device ML learning pathway: a step-by-step tutorial on how to train and deploy a custom object detection model on mobile devices with no machine learning expertise required. EfficientDet-Lite: a state-of-the-art object detection model ar

While our training example only contains two training features (cur_page and session_index), additional features from Google Analytics can be easily added to create a richer dataset and used for training to create a more powerful model. To do so, extend the following code: def ga_session_to_tensorflow_examples(session): examples = [] for i in range(len(session)-1): features = {‘cur_page’: [session

Posted by Mathieu Guillame-Bert, Sebastian Bruch, Josh Gordon, Jan Pfeifer We are happy to open source TensorFlow Decision Forests (TF-DF). TF-DF is a collection of production-ready state-of-the-art algorithms for training, serving and interpreting decision forest models (including random forests and gradient boosted trees). You can now use these models for classification, regression and ranking t

https://blog.tensorflow.org/2021/05/next-generation-pose-detection-with-movenet-and-tensorflowjs.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj234Pcu7Tprg7dTlqiHbcAejxBjrre4hR94tVXevyCQ0jd4EKQ5dQiV25-uuq1Z-ad2QWEdXzdieUZ2JwetwbGIyUl3JDpARqHec5Jw_HVDzgFt8jC14pAW_wpz77sZig1k3AymPnTgR8/s0/three_pane_aligned+%25281%2529.gif May 17, 2021 — Posted by Ronny Votel and Na Li, Google Rese

https://blog.tensorflow.org/2020/11/accelerating-tensorflow-performance-on-mac.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhfOeoWyPa5DuJPkPW26BcXEp1vlex_t0aJDFLzQeBGHZhxNkEs4MTD7sDvqwAQIW6OpjkykNjbBv8l0Q68pE5sVQawOfsAhA2MRNPDlnB1ivcY1Yvg2ETmVlfKyabPLeoyUPwepEWY6sI/s0/image1.jpg November 18, 2020 — Posted by Pankaj Kanwar and Fred Alcober With TensorFlow 2, best-in-class trainin

https://blog.tensorflow.org/2020/09/introducing-tensorflow-recommenders.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhRP3srVMnqWpCBVIQWg5esg0J_w-u0ZRuIGtmJRLukKIgN4r5fVmnCloV-4zR6dAITFG4cRg6xb2z1V7MXGlG8FJ5PSgPFzSSCE23IiSmLEzczykvX2Dodl08IKuDooGacNBB3v0Hz1hc/s0/TF+Recommenders+06.gif September 23, 2020 — Posted by Maciej Kula and James Chen, Google BrainFrom recommending movies

https://blog.tensorflow.org/2020/09/supercharging-tensorflowjs-webassembly.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj124OoLW469DhvyugpJkaL3YgvWO2lXUMpyY5fN_Tr6H7AzgpHSOVJGDkoAkaKq59sXdSwau4cvmMM-M06Jton1Ost721G3DF5enoHt31l9BdpeK2URcx5KoAVBSVZykp1OsJv9H-0bSk/s1600/table1.png September 02, 2020 — Posted by Ann Yuan and Marat Dukhan, Software Engineers at Google In March we int

https://blog.tensorflow.org/2020/08/introducing-tensorflow-coder-tool.html August 26, 2020 — Posted by Kensen Shi, Google Research When manipulating tensors, one must keep track of multiple dimensions, tensor shape and DType compatibility, and of course mathematical correctness. Additionally, there are hundreds of TensorFlow operations, and finding the right ones to use can be a challenge. Instead

A guest post by Rising Odegua, Independent Researcher; Stephen Oni, Data Science Nigeria Danfo.js is an open-source JavaScript library that provides high-performance, intuitive, and easy-to-use data structures for manipulating and processing structured data. Danfo.js is heavily inspired by the Python Pandas library and provides a similar interface/API. This means that users familiar with the Panda

https://blog.tensorflow.org/2020/07/pixelopolis-self-driving-car-demo-tensorflow-lite.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhs4gaxC1c-8T8Ei8rgaCqf6BoyUQRfPllTIcLCnkECygff-sSAHYUfJBu4Z4ZGtSwksvzRki32WFGSYiFPtlv19oacze5SpcU9c4spZF8a2KMU3hzT2LD7G3TwDglWqHj6JFEFZSdZbGo/s1600/106.gif July 13, 2020 — Posted by Miguel de Andrés-Clavera, Product Manager, Google PI In this post, I

https://blog.tensorflow.org/2020/07/tensorflow-2-meets-object-detection-api.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhKis9ECId8eIwn_p0SVMBt3a1vfvKOcOZXy6zK0fWoyzXnzQTguKc2CV__6oI1Pwg22NjWsErpDKqjwQdzjilvmqwWkXPj2ncglphh6mAhpoZ_QXQiDwxnwo-GjKEP0fEOb3uBlNlh9sc/s1600/tensorflow2objectdetection.png July 10, 2020 — Posted by Vivek Rathod and Jonathan Huang, Google Research At the

https://blog.tensorflow.org/2020/03/higher-accuracy-on-vision-models-with-efficientnet-lite.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjkW-QEUi2BQR3pO85B6XNSiw3DplipNxCzRUQx7RAY8jrpR6oWB22B8WUYtYZq5LR2H41PtbIjNzCK27qD3_OdrctcHSwA41YyhT7lglc69Zlx2ZKtPN7UbegeqeZvujd3iQggemU3QjE/s1600/figure1a.png March 16, 2020 — Posted by Renjie Liu, Software Engineer In May 2019, Google releas

https://blog.tensorflow.org/2020/04/tfrt-new-tensorflow-runtime.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhjEwP7k7mM3L8q4tIwqNJSYw4TpNiNYr15ctGvyXozJD_cZW5-0YDCSg-dPMwN0jJeXoVN6xohn8M0jdnUprk-p6qWJrOY10-YX3CuokeJkhB5GQcOMtv_E4k5PBjyk3gfXz1fnZzKnVo/s1600/tfrtroleingraph.png April 29, 2020 — Posted by Eric Johnson, TFRT Product Manager and Mingsheng Hong, TFRT Tech Lead/Manager

https://blog.tensorflow.org/2020/03/introducing-model-garden-for-tensorflow-2.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj6B548lJmA18SnsjhUT9rGoal-UoV7Afij6c2cY2nUhC0nGUZI6wfx2CMXjIYxJ0RX-8NBxgF0rqviDjkvyyQvH9qP5D2dwP6CIxzb084NxcbAHvGz5dxjM1gEPwHGr-PgwATBZZyNHD0/s1600/TF_FullColor_Icon.jpg March 31, 2020 — Posted by Jaeyoun Kim, Technical Program Manager, and Jing Li, Software

https://blog.tensorflow.org/2020/03/introducing-webassembly-backend-for-tensorflow-js.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgxevQQFk1NSA6XTKwp0_HoQ_7qE7Q1ErFbnx3Mzu2P0WQq3H71BW0AFFtdRrFYjjbcTjkNw4gAdjnXTjuU-7Ar0IO6O4XF2dCdma4GiCH5SRagaQ-5OHTz35etWJbmZpxzJu1HSRkV49Q/s1600/Screen+Shot+2020年03月10日+at+12.22.51+PM.png March 11, 2020 — Posted by Daniel Smilkov, Nikhil Thorat, an

https://blog.tensorflow.org/2020/03/part-1-fast-scalable-and-accurate-nlp-tensorflow-deploying-bert.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhWJ2AwUPtnioab3hD6MxsgPzNCLWuy3B_HGH99oqrMSPBvg0Kx9E_xXP8P5TeGpnOsppDacTE1ajQuTzkTPyqZfyFWIzduupu3-UHTncTb1dckkge8t-wYgpDEZHAYnhKkRPUZLjsb7Kg/s1600/figure1.png March 11, 2020 — Posted by Guest author Hannes Hapke, Senior Machine Learnin

Posted by Ann Yuan and Andrey Vakunov, Software Engineers at Google Today we’re excited to release two new packages: facemesh and handpose for tracking key landmarks on faces and hands respectively. This release has been a collaborative effort between the MediaPipe and TensorFlow.js teams within Google Research. Try the demos live in your browserThe facemesh package finds facial boundaries and lan

Guest post by Jeff Houghton, Chief Operating Officer - Modiface Inc. ModiFace has been creating artificial intelligence tech for the beauty industry for over a decade and began working on AR experiences before "Augmented Reality" was a household term. As smartphones hit the market, ModiFace quickly took advantage of the platform to switch from a virtual try on for a 2D image, to a virtual try on f

Posted by Marina Munkhoeva, PhD student at Skolkovo Institute of Science and Technology and AI Resident at Alphabet's X, Chase Roberts, Research Engineer at Alphabet's X, and Stefan Leichenauer, Research Scientist at Alphabet's X Introduction In this post, we’re going to talk about TensorNetwork, and how it can be used to supercharge a feed-forward neural network in TensorFlow. TensorNetwork is an

Posted by Yannick Assogba, Software Engineer, Google Research, Brain team We are pleased to announce that TensorFlow.js for React Native is now available for general use. We would like to thank everyone who gave us feedback, bug reports, and contributions during the alpha release and invite the broader community of React Native developers to try it out! What is React Native?JavaScript runs on a wi

https://blog.tensorflow.org/2020/01/hyperparameter-tuning-with-keras-tuner.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEj0alAj351oTuthCR4_0WQem2uZnPOwrXNI9x1i-eIcaubTlY8WxKjWEKvUftTnJg4Ov3XUgHgDjhmxjdJLxnkX6hhtlagu_fQfTZtNFTu9dfvvoZf8_IMHDiVIya2XpDS0U4DqLx9tGKO9/s1600/pasted+image+0.png January 29, 2020 — Posted by Tom O’Malley The success of a machine learning project is often

https://blog.tensorflow.org/2020/01/run-tensorflow-savedmodel-in-nodejs-directly-without-conversion.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjhkuOR0EpRpuVC5Ru1ioLJxqsm_2hcg9LDpi7xboxOta-Fy-O0gg07ETjq8fXlp6l8CUqwZsIkb7K-NdCywcCxDQoNkr7QqZYzvLmbHDiMHOJlj54whlKq_jBEj0ZR47gGFuJQDRloukc/s1600/gpu+model.png January 14, 2020 — Posted by Kangyi Zhang, Sandeep Gupta, and Brijesh Kris

https://blog.tensorflow.org/2020/01/ecovacs-robotics-ai-robotic-vacuum.html https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgfyDn1JM2pmWd22uHjq6UECnpseNMnI4E2e-FblWpJbdYSAqjUdC2DAIQYyfYIdIQ48wvKJWIiV9rwbtOCs5ielu0DnAyCjZiuDhBosIts2D7mT5dnujRDAy-kl6kRgh_DJJj9wvcqlDM/s1600/fig1.gif January 07, 2020 — A guest post by Liang Bao, Chengqi Lv, from Ecovacs Robotics AI Department. Translated by