-
Welcome to the New and Improved TensorFlow Hub! "We added search features and visual cues that enable you to find and download the right model for your use case." https://blog.tensorflow.org/2019/12/an-introduction-to-new-and-improved.html?linkId=79368720 … by
@JordanGrimstad#GoogleResearch#TFHub via@TensorFlow -
We recently announced a lot of new upgrades for TensorFlow Hub
Find out what’s new, and how #TFHub is helping you get what you need for your ML projects, faster.
Read more here → https://goo.gle/2Z4XJaS pic.twitter.com/mrfEOQW2f2 -
Stylize images with arbitrary styles in
#TensorFlow. We released a model on#TFHub, try it out yourself in our new Colab! Details here → https://goo.gle/2oiDKaT pic.twitter.com/iYtLfxURPa -
We are proud to announce that the FGVCx
#Fungi image embedding model is now live on TensorFlow Hub using training images of >1,000 species from
#SvampeAtlas#TFHub#GBIF https://tfhub.dev/google/svampeatlas/vision/embedder/fungi_V1/1 … -
SPIRAL is an RL agent that generates images by interacting with off-the-shelf graphics software. We've released 9 agents trained to paint portraits of imaginary people in just 19 brush strokes on
#TFHub! For more, see: → https://goo.gle/2Mky1f9 → https://goo.gle/2TAAvXk pic.twitter.com/zK5rthF92A -
Hello World! ≈ Bonjour le monde! ≈ こんにちは世界! Explore multilingual semantic retrieval → https://goo.gle/32yClMP and retrieval QA → https://goo.gle/2LA5aTx using our latest multilingual Universal Sentence Encoder
#TFHub models → https://goo.gle/30Gy5ZT pic.twitter.com/yf46Euu5ii
-
Hey, I recognize those two Gravatars...
Very proud of @tahsin_mayeesha and@lc0d3r for being top contributors to@TensorFlow Hub over the last few months!#TFHub
https://www.tensorflow.com/hub
https://tfhub.dev pic.twitter.com/zccfXbfxpl
-
So many tweets in so many languages about the cross language universal sentence encoder... If only there was a way to embed them in the same space with one line of python...
#tfhub https://twitter.com/GoogleDevsLATAM/status/1105552778783449089 …
-
Analyzing the semantic similarity between title tags and keywords w/
@TensorFlow#TFHub Universal Sentence Encoder
https://wordlift.io/blog/en/title-tag-seo-using-ai/ … #ai#SEO cc@seohacker@martinibuster@aaranged in a way the more I try to automate the more I find myself doing *traditional SEO*
pic.twitter.com/eELrqdTQS0
-
BERT is in
#TFHub and here's a runnable notebook!
More BERT modules at https://tfhub.dev/s?q=bert https://twitter.com/dalequark/status/1095445903475798016 … -

Day #54
#TFHub in spaaaaaaaaace! Machine Learning Space Applications on SmallSat Platforms with@TensorFlow, via the good folks at@NASAGoddard and the@NSF Center for Space, High-Performance, and Resilient Computing (SHREC).
Check out the paper: https://digitalcommons.usu.edu/cgi/viewcontent.cgi?article=4270&context=smallsat …pic.twitter.com/vFmy4nvYuN
Prikaži ovu nit -
Learn more about how you can *reuse* model components (like LEGO bricks!) for free on #TFHub: https://tfhub.dev/#TFHub uses transfer learning to bootstrap model creation: which means you can achieve higher accuracy with less data, minimal hardware, and in record time. pic.twitter.com/SEokqStVYn
Prikaži ovu nit -
2)
@TensorFlow Hub If you want to train your model on a small data set, or improve generalization, you'll need to use something called transfer learning.#TFHub modules make it easy—and are available in an#OSS marketplace: http://tfhub.dev . site: https://www.tensorflow.org/hub/ pic.twitter.com/59sWE4zH5X
Prikaži ovu nit -
What better way to celebrate
@TensorFlow's 3rd birthday than giving a talk about its magical Tensorflow Hub to 300+ devs at DevFest Rift Valley. Happy birthday Tensorflow!#TFHub#DevFestRiftValley#HappyBirthdayTFpic.twitter.com/mefr448iUQ
-

Attempting to get a handle on the full list of @TensorFlow offerings; each new discovery makes me more excited. The ecosystem expanded so much in 3 years!@TensorFlowJS#TFLite Swift for TF@TensorBoard Edge TPUs#TFHub#TFX tf.keras eager mode#TFProbability#Tensor2Tensorpic.twitter.com/hcWZgy6cqE
Prikaži ovu nit -
Image augmentation lets you get the most of your dataset. We released state-of-the-art AutoAugment Modules on
#TFHub allowing you to train better image models with less data!#TensorFlowHub#GoogleAI Check it out here → http://bit.ly/2q9Y5wd pic.twitter.com/sfIIUGZDpE
-
Perform object detection with the brand new
#tensorflowhub module from@Google, trained on the OpenImages Dataset V4! Join@jponttuset at the Google booth Wednesday 12th at#ECCV2018 for a demo.#tfhub#transferlearning Check it out here ↓ http://bit.ly/2N6k7y8 -
Check out
@JeremiahHarmsen's demonstration of how pre-trained modules from TensorFlow Hub can be leveraged to solve sentiment analysis challenges on Kaggle → http://bit.ly/2oOBxAz#tfhub#tensorflowhub#transferlearningpic.twitter.com/lvv8bRbIGe
-
With
#TensorFlowJS,#TFLite,#TFiwS,#TFHub and more, TensorFlow is no longer a library or framework, it is an ecosystem. BTW, this article doesn't mention the recent performance gains in TensorFlow: https://www.tensorflow.org/performance/performance_guide …https://twitter.com/fchollet/status/1029878879010222080 … -
First
#DeepMind module on#tfhub! Use I3D for video actions recognition, for details about this model read CVPR paper https://arxiv.org/abs/1705.07750 https://twitter.com/DeepMindAI/status/994569074062577666 …
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

