Difference between revisions of "TensorFlow"
m |
|||
(48 intermediate revisions by the same user not shown) | |||
Line 2: | Line 2: | ||
|title=PRIMO.ai | |title=PRIMO.ai | ||
|titlemode=append | |titlemode=append | ||
− | |keywords=artificial, intelligence, machine, learning, models | + | |keywords=ChatGPT, artificial, intelligence, machine, learning, GPT-4, GPT-5, NLP, NLG, NLC, NLU, models, data, singularity, moonshot, Sentience, AGI, Emergence, Moonshot, Explainable, TensorFlow, Google, Nvidia, Microsoft, Azure, Amazon, AWS, Hugging Face, OpenAI, Tensorflow, OpenAI, Google, Nvidia, Microsoft, Azure, Amazon, AWS, Meta, LLM, metaverse, assistants, agents, digital twin, IoT, Transhumanism, Immersive Reality, Generative AI, Conversational AI, Perplexity, Bing, You, Bard, Ernie, prompt Engineering LangChain, Video/Image, Vision, End-to-End Speech, Synthesize Speech, Speech Recognition, Stanford, MIT |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools |
− | |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools | + | |
+ | <!-- Google tag (gtag.js) --> | ||
+ | <script async src="https://www.googletagmanager.com/gtag/js?id=G-4GCWLBVJ7T"></script> | ||
+ | <script> | ||
+ | window.dataLayer = window.dataLayer || []; | ||
+ | function gtag(){dataLayer.push(arguments);} | ||
+ | gtag('js', new Date()); | ||
+ | |||
+ | gtag('config', 'G-4GCWLBVJ7T'); | ||
+ | </script> | ||
}} | }} | ||
− | [ | + | [https://www.youtube.com/results?search_query=TensorFlow YouTube] |
− | [ | + | [https://www.quora.com/search?q=TensorFlow ... Quora] |
+ | [https://www.google.com/search?q=TensorFlow ...Google search] | ||
+ | [https://news.google.com/search?q=TensorFlow ...Google News] | ||
+ | [https://www.bing.com/news/search?q=TensorFlow&qft=interval%3d%228%22 ...Bing News] | ||
− | * [[Libraries & Frameworks]] | + | * [[Python]] ... [[Generative AI with Python|GenAI w/ Python]] ... [[JavaScript]] ... [[Generative AI with JavaScript|GenAI w/ JavaScript]] ... [[TensorFlow]] ... [[PyTorch]] |
+ | * [[Google]] offerings | ||
+ | * [[Libraries & Frameworks Overview]] ... [[Libraries & Frameworks]] ... [[Git - GitHub and GitLab]] ... [[Other Coding options]] | ||
* TensorFlow is a [[Python]] library | * TensorFlow is a [[Python]] library | ||
* [[Keras]] (currently part of TensorFlow 2.0) | * [[Keras]] (currently part of TensorFlow 2.0) | ||
+ | * [[Analytics]] ... [[Visualization]] ... [[Graphical Tools for Modeling AI Components|Graphical Tools]] ... [[Diagrams for Business Analysis|Diagrams]] & [[Generative AI for Business Analysis|Business Analysis]] ... [[Requirements Management|Requirements]] ... [[Loop]] ... [[Bayes]] ... [[Network Pattern]] | ||
+ | * [[Development]] ... [[Notebooks]] ... [[Development#AI Pair Programming Tools|AI Pair Programming]] ... [[Codeless Options, Code Generators, Drag n' Drop|Codeless]] ... [[Hugging Face]] ... [[Algorithm Administration#AIOps/MLOps|AIOps/MLOps]] ... [[Platforms: AI/Machine Learning as a Service (AIaaS/MLaaS)|AIaaS/MLaaS]] | ||
+ | * [[Gaming]] ... [[Game-Based Learning (GBL)]] ... [[Games - Security|Security]] ... [[Game Development with Generative AI|Generative AI]] ... [[Metaverse#Games - Metaverse|Games - Metaverse]] ... [[Games - Quantum Theme|Quantum]] ... [[Game Theory]] ... [[Game Design | Design]] | ||
* [http://venturebeat.com/2019/09/30/google-launches-tensorflow-2-0-with-tighter-keras-integration/ Google launches TensorFlow 2.0 with tighter Keras integration | Khari Johnson] | * [http://venturebeat.com/2019/09/30/google-launches-tensorflow-2-0-with-tighter-keras-integration/ Google launches TensorFlow 2.0 with tighter Keras integration | Khari Johnson] | ||
* [[TensorFlow.js]] ... Browser and Node Server | * [[TensorFlow.js]] ... Browser and Node Server | ||
− | * [[TensorFlow Serving]] .. Cloud, On-prem ...support model versioning (for model updates with a rollback option) and multiple models (for experimentation via A/B testing) | + | * [[TensorFlow Serving]] .. Cloud, On-prem ...support model versioning (for model updates with a rollback option) and multiple models (for experimentation via [[AI Verification and Validation#A/B Testing|A/B testing]]) |
* [[TensorFlow Lite]] ... Android, iOS, Raspberry Pi | * [[TensorFlow Lite]] ... Android, iOS, Raspberry Pi | ||
** [[Converting to TensorFlow Lite]] convert models into TensorFlow Lite format | ** [[Converting to TensorFlow Lite]] convert models into TensorFlow Lite format | ||
− | + | * TensorFlow [[Decentralized: Federated & Distributed|Federated]] | |
− | * TensorFlow [[Federated]] | + | * [[TensorFlow Extended (TFX)]] an end-to-end platform for deploying production ML pipelines |
− | * [[TensorFlow Extended (TFX)] | + | * [[TensorFlow Playground]] |
− | + | * [[TensorBoard]] with [http://projector.tensorflow.org/ Embedding Projector] - visualization of high-dimensional data | |
− | * [ | ||
− | * [ | ||
− | |||
* [http://ai.google/tools/ We’re making tools and resources available so that anyone can use technology to solve problems | Google AI] | * [http://ai.google/tools/ We’re making tools and resources available so that anyone can use technology to solve problems | Google AI] | ||
* [http://github.com/tensorflow/workshops TensorFlow Workshops] click on links to run in [[Colaboratory]] (Colab) | * [http://github.com/tensorflow/workshops TensorFlow Workshops] click on links to run in [[Colaboratory]] (Colab) | ||
Line 30: | Line 44: | ||
* [http://www.notion.so/Simple-Tensorflow-Cookbook-6f4563d0cd7343cb9d1e60cd1698b54d Simple Tensorflow Cookbook] | * [http://www.notion.so/Simple-Tensorflow-Cookbook-6f4563d0cd7343cb9d1e60cd1698b54d Simple Tensorflow Cookbook] | ||
* [http://github.com/machinelearningmindset/TensorFlow-Course TensorFlow-Course | GitHub] | * [http://github.com/machinelearningmindset/TensorFlow-Course TensorFlow-Course | GitHub] | ||
+ | * [http://www.tensorflow.org/hub TensorFlow Hub] is a library for reusable machine learning modules that you can use to speed up the process of training your model. A TensorFlow module is a reusable piece of a TensorFlow graph. With transfer learning, you can use TensorFlow modules to preprocess input feature vectors, or you can incorporate a TensorFlow module into your model as a trainable layer. This can help you train your model faster, using a smaller dataset, while improving generalization. | ||
+ | * [[Neural Structured Learning (NSL)]] in TensorFlow | ||
* [[Git - GitHub and GitLab]] | * [[Git - GitHub and GitLab]] | ||
* The API... | * The API... | ||
** [http://www.tensorflow.org/guide/estimators tf.estimator] available alongside the newer Keras high-level API. | ** [http://www.tensorflow.org/guide/estimators tf.estimator] available alongside the newer Keras high-level API. | ||
− | ** [http://www.tensorflow.org/alpha/tutorials/eager/tf_function tf.function] a wrapper to use when writing certain functions in Python | + | ** [http://www.tensorflow.org/alpha/tutorials/eager/tf_function tf.function] a wrapper to use when writing certain functions in Python |
** [http://www.tensorflow.org/tfx/guide/tft tf.Transform] includes converting between formats, tokenizing and stemming text and forming vocabularies | ** [http://www.tensorflow.org/tfx/guide/tft tf.Transform] includes converting between formats, tokenizing and stemming text and forming vocabularies | ||
* Related... | * Related... | ||
** [[TFLearn]] | ** [[TFLearn]] | ||
** [[Swift]] | ** [[Swift]] | ||
+ | * [https://www.altexsoft.com/blog/datascience/the-best-machine-learning-tools-experts-top-picks/ Best Machine Learning Tools: Experts’ Top Picks | Altexsoft] | ||
+ | * [https://blog.tensorflow.org/2023/07/whats-new-in-tensorflow-213-and-keras-213.html What's new in TensorFlow 2.13 and Keras 2.13? | TensorFlow & Keras Teams] | ||
+ | |||
− | + | <img src="https://content.altexsoft.com/media/2017/08/tensors_flowing-1.gif" width="400"> | |
* [[Coding TensorFlow]] <--- video series | * [[Coding TensorFlow]] <--- video series | ||
− | + | TensorFlow focuses on simplicity and ease of use, with updates like eager execution, intuitive higher-level APIs, and flexible model building on any platform, tight [[Keras]] integration. You can easily ingest datasets via tf.data pipelines, and you can monitor your training in [[TensorBoard]] directly from [[Colaboratory]] and [http://jupyter.org/index.html Jupyter] Notebooks. [http://cloud.google.com/blog/products/ai-machine-learning/tensorflow-2-0-and-cloud-ai-make-it-easy-to-train-deploy-and-maintain-scalable-machine-learning-models TensorFlow 2.0 and [[Google]] Cloud AI make it easy to train, deploy, and maintain scalable machine learning models | Paige Bailey and Barrett Williams - Google] | |
− | |||
* [http://medium.com/tensorflow/whats-coming-in-tensorflow-2-0-d3663832e9b8 What’s coming in TensorFlow 2.0 | TensorFlow Team - Medium] | * [http://medium.com/tensorflow/whats-coming-in-tensorflow-2-0-d3663832e9b8 What’s coming in TensorFlow 2.0 | TensorFlow Team - Medium] | ||
* [http://jaxenter.com/ml-tensorflow-2-0-154466.html What’s in store for ML developers in TensorFlow 2.0? | Jane Elizabeth] | * [http://jaxenter.com/ml-tensorflow-2-0-154466.html What’s in store for ML developers in TensorFlow 2.0? | Jane Elizabeth] | ||
+ | <youtube>6g4O5UOH304</youtube> | ||
+ | <youtube>6D7-2JGvFgk</youtube> | ||
<youtube>EqWsPO8DVXk</youtube> | <youtube>EqWsPO8DVXk</youtube> | ||
− | <youtube> | + | <youtube>bDZ2q6OktQI</youtube> |
<youtube>-5LJ77kAYqo</youtube> | <youtube>-5LJ77kAYqo</youtube> | ||
+ | <youtube>jJaG2ytJVQU</youtube> | ||
<youtube>b5Rs1ToD9aI</youtube> | <youtube>b5Rs1ToD9aI</youtube> | ||
− | <youtube> | + | <youtube>WS9Nckd2kq0</youtube> |
+ | |||
+ | === GPU === | ||
+ | * [[Processing Units - CPU, GPU, APU, TPU, VPU, FPGA, QPU]] | ||
+ | * [http://www.youtube.com/results?search_query=GPU+tensorflow Youtube search...] | ||
− | |||
<youtube>r7-WPbx8VuY</youtube> | <youtube>r7-WPbx8VuY</youtube> | ||
<youtube>tCYSce6l8gA</youtube> | <youtube>tCYSce6l8gA</youtube> | ||
− | |||
− | === | + | === tf.function === |
− | <youtube> | + | * [http://www.youtube.com/results?search_query=tf.function+tensorflow Youtube search...] |
− | <youtube> | + | |
+ | <youtube>yH1cF7GnoIo</youtube> | ||
+ | <youtube>Up9CvRLIIIw</youtube> | ||
+ | |||
+ | === Eager Execution (Default in 2.0) ==== | ||
+ | * [http://www.youtube.com/results?search_query=eager+execution+tensorflow Youtube search...] | ||
− | ==== Examples | + | * [http://towardsdatascience.com/the-roadmap-of-mathematics-for-deep-learning-357b3db8569b Eager Execution vs. Graph Execution in TensorFlow: Which is Better? | Orhan G. Yalcin] ...Comparing Eager Execution and Graph Execution using Code Examples, Understanding When to Use Each and why TensorFlow switched to Eager Execution | Deep Learning with TensorFlow 2.x |
+ | |||
+ | <youtube>T8AW0fKP0Hs</youtube> | ||
+ | <youtube>yPgvoLWSkFo</youtube> | ||
+ | |||
+ | === tf.data - TF Input Pipeline === | ||
+ | * [http://www.youtube.com/results?search_query=tf.data+TF+Input+Pipeline+tensorflow Youtube search...] | ||
+ | |||
+ | <youtube>kVEOCfBy9uY</youtube> | ||
+ | <youtube>n7byMbl2VUQ</youtube> | ||
+ | <youtube>uIcqeP7MFH0</youtube> | ||
+ | <youtube>VeV65oVvoes</youtube> | ||
+ | |||
+ | === tf.distribute === | ||
+ | * [http://www.youtube.com/results?search_query=tf.distribute+tensorflow Youtube search...] | ||
+ | |||
+ | <youtube>ZnukSLKEw34</youtube> | ||
+ | <youtube>jKV53r9-H14</youtube> | ||
+ | |||
+ | === mesh-TensorFlow === | ||
+ | * [http://www.youtube.com/results?search_query=mesh+tensorflow Youtube search...] | ||
+ | |||
+ | <youtube>HgGyWS40g-g</youtube> | ||
+ | <youtube>uPDuJb35bGg</youtube> | ||
+ | |||
+ | === TensorFlow Probability === | ||
+ | * [http://www.youtube.com/results?search_query=Probability+tensorflow Youtube search...] | ||
+ | |||
+ | <youtube>BrwKURU-wpk</youtube> | ||
+ | <youtube>_U-1kJo76o4</youtube> | ||
+ | |||
+ | === Reinforcement Learning with TF-Agents === | ||
+ | * [http://www.youtube.com/results?search_query=TF-Agents+tensorflow Youtube search...] | ||
+ | |||
+ | <youtube>-TTziY7EmUA</youtube> | ||
+ | <youtube>tAOApRQAgpc</youtube> | ||
+ | |||
+ | === Examples === | ||
<youtube>bNntsCOdFxg</youtube> | <youtube>bNntsCOdFxg</youtube> | ||
<youtube>HsgyKcC0f_s</youtube> | <youtube>HsgyKcC0f_s</youtube> | ||
Line 73: | Line 138: | ||
− | = | + | = Tensorflow for Practice Specialization = |
− | + | ||
− | + | * [http://www.coursera.org/specializations/tensorflow-in-practice TensorFlow in Practice Specialization |] [http://www.coursera.org/instructor/lmoroney Laurence Moroney - Coursera] | |
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | + | * [http://www.meetup.com/Deep-Learning-Adventures/events/269909321/ Deep Learning Adventures | hosted by George Zoto - Meetup] | |
− | [http://www. | ||
− | + | * Chapter 1: | |
− | + | ** [http://docs.google.com/presentation/d/1GEvlIo8g_OFWWq7S3Ob82wRh5NroXpVSivRvVjFpm4Q/edit?usp=sharing Presentation] | |
+ | ** [http://www.meetup.com/Deep-Learning-Adventures/events/269760835/ Meetup #1 fun-packed event] | ||
+ | ** Notes: | ||
+ | *** [http://stats.stackexchange.com/questions/376224/why-map-the-pixel-grayscale-0-1-to-0-01-0-99-before-feeding-to-the-neural Why map the pixel grayscale [0,1] to [0.01, 0.99] before feeding to the neural network?] | ||
+ | *** [http://machinelearningmastery.com/how-to-normalize-center-and-standardize-images-with-the-imagedatagenerator-in-keras/ How to Normalize, Center, and Standardize Image Pixels in Keras | Jason Brownlee] |
Latest revision as of 11:42, 6 November 2024
YouTube ... Quora ...Google search ...Google News ...Bing News
- Python ... GenAI w/ Python ... JavaScript ... GenAI w/ JavaScript ... TensorFlow ... PyTorch
- Google offerings
- Libraries & Frameworks Overview ... Libraries & Frameworks ... Git - GitHub and GitLab ... Other Coding options
- TensorFlow is a Python library
- Keras (currently part of TensorFlow 2.0)
- Analytics ... Visualization ... Graphical Tools ... Diagrams & Business Analysis ... Requirements ... Loop ... Bayes ... Network Pattern
- Development ... Notebooks ... AI Pair Programming ... Codeless ... Hugging Face ... AIOps/MLOps ... AIaaS/MLaaS
- Gaming ... Game-Based Learning (GBL) ... Security ... Generative AI ... Games - Metaverse ... Quantum ... Game Theory ... Design
- Google launches TensorFlow 2.0 with tighter Keras integration | Khari Johnson
- TensorFlow.js ... Browser and Node Server
- TensorFlow Serving .. Cloud, On-prem ...support model versioning (for model updates with a rollback option) and multiple models (for experimentation via A/B testing)
- TensorFlow Lite ... Android, iOS, Raspberry Pi
- Converting to TensorFlow Lite convert models into TensorFlow Lite format
- TensorFlow Federated
- TensorFlow Extended (TFX) an end-to-end platform for deploying production ML pipelines
- TensorFlow Playground
- TensorBoard with Embedding Projector - visualization of high-dimensional data
- We’re making tools and resources available so that anyone can use technology to solve problems | Google AI
- TensorFlow Workshops click on links to run in Colaboratory (Colab)
- Machine Learning Crash Course with TensorFlow APIs | Google
- TensorFlow without a PhD | Martin Görner
- Running Tensorflow in Production | Matthias Feys
- Simple Tensorflow Cookbook
- TensorFlow-Course | GitHub
- TensorFlow Hub is a library for reusable machine learning modules that you can use to speed up the process of training your model. A TensorFlow module is a reusable piece of a TensorFlow graph. With transfer learning, you can use TensorFlow modules to preprocess input feature vectors, or you can incorporate a TensorFlow module into your model as a trainable layer. This can help you train your model faster, using a smaller dataset, while improving generalization.
- Neural Structured Learning (NSL) in TensorFlow
- Git - GitHub and GitLab
- The API...
- tf.estimator available alongside the newer Keras high-level API.
- tf.function a wrapper to use when writing certain functions in Python
- tf.Transform includes converting between formats, tokenizing and stemming text and forming vocabularies
- Related...
- Best Machine Learning Tools: Experts’ Top Picks | Altexsoft
- What's new in TensorFlow 2.13 and Keras 2.13? | TensorFlow & Keras Teams
- Coding TensorFlow <--- video series
TensorFlow focuses on simplicity and ease of use, with updates like eager execution, intuitive higher-level APIs, and flexible model building on any platform, tight Keras integration. You can easily ingest datasets via tf.data pipelines, and you can monitor your training in TensorBoard directly from Colaboratory and Jupyter Notebooks. TensorFlow 2.0 and Google Cloud AI make it easy to train, deploy, and maintain scalable machine learning models | Paige Bailey and Barrett Williams - Google
- What’s coming in TensorFlow 2.0 | TensorFlow Team - Medium
- What’s in store for ML developers in TensorFlow 2.0? | Jane Elizabeth
Contents
GPU
tf.function
Eager Execution (Default in 2.0) =
- Eager Execution vs. Graph Execution in TensorFlow: Which is Better? | Orhan G. Yalcin ...Comparing Eager Execution and Graph Execution using Code Examples, Understanding When to Use Each and why TensorFlow switched to Eager Execution | Deep Learning with TensorFlow 2.x
tf.data - TF Input Pipeline
tf.distribute
mesh-TensorFlow
TensorFlow Probability
Reinforcement Learning with TF-Agents
Examples
Tensorflow for Practice Specialization
- Chapter 1:
- Presentation
- Meetup #1 fun-packed event
- Notes:
- Why map the pixel grayscale [0,1 to [0.01, 0.99] before feeding to the neural network?]
- How to Normalize, Center, and Standardize Image Pixels in Keras | Jason Brownlee