TensorStore for High-Performance, Scalable Array Storage
http://ai.googleblog.com/2022/09/tensorstore-for-high-performance.html
@tensorflowblog
http://ai.googleblog.com/2022/09/tensorstore-for-high-performance.html
@tensorflowblog
blog.research.google
TensorStore for High-Performance, Scalable Array Storage
https://blog.tensorflow.org/2022/09/bridging-communities-tensorflow-federated-tff-and-openmined.html
@tensorflowblog
@tensorflowblog
blog.tensorflow.org
Bridging communities: TensorFlow Federated (TFF) and OpenMined
we’re excited to announce the collaboration between TFF and OpenMined - an OSS community dedicated to development of privacy-preserving technologies.
Crossmodal-3600 — Multilingual Reference Captions for Geographically Diverse Images
http://ai.googleblog.com/2022/10/crossmodal-3600-multilingual-reference.html
@tensorflowblog
http://ai.googleblog.com/2022/10/crossmodal-3600-multilingual-reference.html
@tensorflowblog
blog.research.google
Crossmodal-3600 — Multilingual Reference Captions for Geographically Diverse Images
UL2 20B: An Open Source Unified Language Learner
http://ai.googleblog.com/2022/10/ul2-20b-open-source-unified-language.html
@tensorflowblog
http://ai.googleblog.com/2022/10/ul2-20b-open-source-unified-language.html
@tensorflowblog
research.google
UL2 20B: An Open Source Unified Language Learner
Posted by Yi Tay and Mostafa Dehghani, Research Scientists, Google Research, Brain Team Building models that understand and generate natural langua...
Table Tennis: A Research Platform for Agile Robotics
http://ai.googleblog.com/2022/10/table-tennis-research-platform-for.html
@tensorflowblog
http://ai.googleblog.com/2022/10/table-tennis-research-platform-for.html
@tensorflowblog
blog.research.google
Table Tennis: A Research Platform for Agile Robotics
Do Modern ImageNet Classifiers Accurately Predict Perceptual Similarity?
http://ai.googleblog.com/2022/10/do-modern-imagenet-classifiers.html
@tensorflowblog
http://ai.googleblog.com/2022/10/do-modern-imagenet-classifiers.html
@tensorflowblog
blog.research.google
Do Modern ImageNet Classifiers Accurately Predict Perceptual Similarity?
MUSIQ: Assessing Image Aesthetic and Technical Quality with Multi-scale Transformers
http://ai.googleblog.com/2022/10/musiq-assessing-image-aesthetic-and.html
@tensorflowblog
http://ai.googleblog.com/2022/10/musiq-assessing-image-aesthetic-and.html
@tensorflowblog
blog.research.google
MUSIQ: Assessing Image Aesthetic and Technical Quality with Multi-scale Transformers
https://blog.tensorflow.org/2022/10/integrating-arm-virtual-hardware-with-tensorflow-lite-micro-continuous-integration-infrastructure.html
@tensorflowblog
@tensorflowblog
blog.tensorflow.org
Integrating Arm Virtual Hardware with the TensorFlow Lite Micro Continuous Integration Infrastructure
Arm is making embedded ML more accessible with Arm Virtual Hardware (AVH). AVH offers a platform to test TFLM models without needing physical hardware
https://blog.tensorflow.org/2022/10/accelerating-tensorflow-on-intel-data-center-gpu-flex-series.html
@tensorflowblog
@tensorflowblog
blog.tensorflow.org
Accelerating TensorFlow on Intel Data Center GPU Flex Series
Intel and Google co-architected the TensorFlow PluggableDevice mechanism to enable TensorFlow models on Data Center GPU Flex Series.
Remote physiotherapy at scale with IncludeHealth - Made with TensorFlow.js
https://www.youtube.com/watch?v=HcstcWAk2a4&ab_channel=TensorFlow
@tensorflowblog
https://www.youtube.com/watch?v=HcstcWAk2a4&ab_channel=TensorFlow
@tensorflowblog
YouTube
Remote physiotherapy at scale with IncludeHealth - Made with TensorFlow.js
Meet Ryan Eder, Founder and CEO of IncludeHealth, who’s changing the medical industry by making it more accessible using Web ML and TensorFlow.js by delivering an AI-powered platform directly to patients for at-home physical therapy treatments using a regular…
I tried building an ML Cancer Segmentation API in 15 Minutes
https://www.youtube.com/watch?v=aMldpZF6GBU&ab_channel=NicholasRenotte
@tensorflowblog
https://www.youtube.com/watch?v=aMldpZF6GBU&ab_channel=NicholasRenotte
@tensorflowblog
YouTube
I tried building an ML Cancer Segmentation API in 15 Minutes
Was originally meant to be satellite segmentation but 🤷 I think this is cooler anyway.
In this episode we're going to try to build AND deploy a machine learning Cancer Segmentation API using Python, Tensorflow, FastAPI and Heroku...all in 15 minutes.
…
In this episode we're going to try to build AND deploy a machine learning Cancer Segmentation API using Python, Tensorflow, FastAPI and Heroku...all in 15 minutes.
…
https://blog.tensorflow.org/2022/11/how-hugging-face-improved-text-generation-performance-with-xla.html
@tensorflowblog
@tensorflowblog
blog.tensorflow.org
How Hugging Face improved Text Generation performance with XLA
Design choices made by the Hugging Face team to bring in the power of XLA in the TensorFlow text generation models to achieve ~100x speed up
https://blog.tensorflow.org/2022/11/building-tensorflow-lite-based-computer-vision-emoji-input-device-openmv.html
@tensorflowblog
@tensorflowblog
blog.tensorflow.org
Building a TensorFlow Lite based computer vision emoji input device with OpenMV
This is an in-depth open-source guide that uses tinyML on an Arm Cortex-M based device to create a dedicated input device.
https://blog.tensorflow.org/2022/12/building-best-in-class-recommendation-systems-with-tensorflow-ecosystem.html
@tensorflowblog
@tensorflowblog
blog.tensorflow.org
Building best-in-class recommendation systems with the TensorFlow ecosystem
We are launching a unified page on tensorflow.org that gathers all the resources for creating powerful recommendation systems and provides a guided pa