# Tensorflow TensorFlow is an end-to-end platform for machine learning that supports model construction, training, and export. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Gesture Recognition Based on TFLite DevFeed: [Gesture Recognition Based on TFLite]() Original publisher: [Read original article]() Author: John Lee Published: 2026-04-10T00:00:00Z Content type: tutorial Language: en Sources: [Blog on Developer Portal]() Topics: [TensorFlow Lite](), [Espressif](), [model-deployment](), [Tensorflow](), [Keras](), [On-device AI]() Tags: [ai](), [blog](), [deep-learning](), [deployment](), [development-board](), [edge-ai](), [edge-computing](), [esp-idf](), [espressif](), [how-to](), [inference](), [keras](), [model-deployment](), [model-training](), [tensorflow-lite]() ### AI overview This tutorial demonstrates gesture recognition on Espressif SoCs using TensorFlow Lite Micro. It covers data collection, model training, conversion for TFLite Micro, and deployment with C++ code for model loading, preprocessing, and inference. ### Source excerpt This article demonstrates how to implement gesture recognition using TensorFlow Lite Micro on Espressif SoCs. It covers the complete workflow from data collection and model training to model deployment, showcasing TensorFlow Lite Micro's applications in edge AI. ## How to Generate New Art From Existing Images Using Deep Learning? DevFeed: [How to Generate New Art From Existing Images Using Deep Learning?]() Original publisher: [Read original article]() Author: Damilare Keshinro Published: 2025-07-24T04:56:41Z Content type: tutorial Language: en Sources: [Baeldung - CS]() Topics: [Deep neural networks](), [Tensorflow](), [Tutorial](), [Image](), [Computer science]() Tags: [building](), [computer-science](), [computer-vision](), [computer-vision-image-processing](), [deep-learning](), [generate](), [how-to](), [image-processing](), [images](), [model](), [techniques](), [tensorflow]() ### AI overview A tutorial on neural style transfer using TensorFlow and a pretrained VGG16 model. It explains how to combine the content of an owl image with the artistic style of Edvard Munch's "Scream" by extracting features, defining losses, preprocessing images, and optimizing the result. ### Source excerpt A walkthrough of building an art style transfer program using deep learning techniques and tools like TensorFlow and the VGG16 model. The post How to Generate New Art From Existing Images Using Deep Learning? first appeared on Baeldung on Computer Science. ## How Deliveroo Built Its Machine Learning Platform DevFeed: [How Deliveroo Built Its Machine Learning Platform]() Original publisher: [Read original article]() Author: Saikrishna Desaraju Published: 2025-07-02T00:00:00Z Content type: article Language: en Sources: [Deliveroo]() Topics: [Machine Learning & Artificial Intelligence](), [Deployment](), [model-deployment](), [Kubernetes](), [Amazon Web Services](), [distributed-training](), [Inference](), [Python](), [PyTorch](), [Tensorflow]() Tags: [aws](), [deployment](), [distributed-training](), [inference](), [kubernetes](), [machine-learning](), [machine-learning-platform](), [python](), [pytorch](), [rest](), [tensorflow]() ### AI overview Deliveroo describes its machine learning platform for standardizing model-building and deployment workflows. The platform combines open-source tools, in-house components, Kubernetes on AWS EKS, TensorFlow, PyTorch, Metaflow, and Argo; it also supports GPU and distributed training and includes Inferoo for real-time model predictions. ### Source excerpt Enter Deliveroo's ML Platform For the past three years, we have been building Deliveroo's Machine Learning Platform, or the ML Platform as we like to call it. The ML Platform boosts our model-building and deployment capabilities by standardising ML workflows, streamlining the end-to-end development process and simplifying model deployment. Besides saving software engineering effort through centralising tooling, the ML Platform also reduces the time that our ML engineers spend on infrastructure tasks. As a result, our ML engineers can now iterate their ML models 2-3x faster than before. What makes our ML Platform tick? At the core of our ML Platform lies a carefully curated tech stack - an integrated suite of infrastructure tools, services, and libraries. It blends robust open source technologies with purpose-built, in-house components. Key open source tools include Kubernetes, Argo, and Metaflow, all seamlessly connected with leading ML frameworks like TensorFlow and PyTorch. We choose mature, community-driven solutions and actively contribute back where we can. This entire ecosystem is powered by AWS, running on EKS, and anchored by our data warehouse. In the sections that follow, we'll take a closer look at the key components that drive our ML Platform. Metaflow To give ML engineers seamless access to scalable compute on Kubernetes, we use Metaflow, a powerful Python library that helps break down complex model-building workflows into smaller, manageable jobs. These jobs are orchestrated by Argo, one of the backbone tools in our infrastructure. One of Metaflow's biggest strengths is its flexibility. It allows engineers to move effortlessly between local development, staging on Kubernetes, and production deployment--helping teams iterate quickly as they experiment and scale. Recently, we added support for GPUs and distributed training, enabling faster training times and the ability to work with much larger datasets. Inferoo For models that require real-time predictio ## What's new in TensorFlow 2.19 DevFeed: [What's new in TensorFlow 2.19]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2025-03-13T16:00:00Z Content type: release Language: en Sources: [The TensorFlow Blog]() Topics: [Tensorflow](), [LiteRT](), [releases](), [API](), [C++](), [Release notes](), [Keras](), [migration]() Tags: [2025](), [announcement](), [api](), [c-plus-plus](), [keras](), [libentensorflow](), [litert](), [migration-guide](), [pypi](), [release](), [release-notes](), [tensorflow](), [tensorflow-core](), [tensorflowlite]() ### AI overview TensorFlow 2.19 introduces C++ API changes in LiteRT, adds bfloat16 support for the tflite casting operation, and deprecates tf.lite.Interpreter in favor of ai_edge_litert.interpreter. The release also stops publishing libtensorflow packages, although they remain extractable from the PyPI package. Updates for multi-backend Keras are directed to keras.io. ### Source excerpt Posted by the TensorFlow team TensorFlow 2.19 has been released! Highlights of this release include changes to the C++ API in LiteRT, bfloat16 support for tflite casting, discontinue of releasing libtensorflow packages. Learn more by reading the full release notes. Note: Release updates on the new multi-backend Keras will be published on keras.io, starting with Keras 3.0. For more information, please see https://keras.io/keras_3/. TensorFlow Core LiteRT The public constants tflite::Interpreter:kTensorsReservedCapacity and tflite::Interpreter:kTensorsCapacityHeadroom are now const references, rather than constexpr compile-time constants. (This is to enable better API compatibility for TFLite in Play services while preserving the implementation flexibility to change the values of these constants in the future.) TF-Lite tfl.Cast op is now supporting bfloat16 in the runtime kernel. tf.lite.Interpreter gives a deprecation warning redirecting to its new location at ai_edge_litert.interpreter, as the API tf.lite.Interpreter will be deleted in TF 2.20. See the migration guide for details. Libtensorflow We have stopped publishing libtensorflow packages but it can still be unpacked from the PyPI package. ## What's new in TensorFlow 2.18 DevFeed: [What's new in TensorFlow 2.18]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2024-10-28T19:00:00Z Content type: release Language: en Sources: [The TensorFlow Blog]() Topics: [Tensorflow](), [releases](), [LiteRT](), [NumPy](), [CUDA](), [cudnn](), [NCCL](), [Google]() Tags: [announcement](), [cuda](), [cudnn](), [gpu](), [litert](), [migration](), [nccl](), [nvidia](), [nvidia-rtx](), [python](), [release](), [releases](), [reproducible-builds](), [tensorflow](), [tensorflow-core]() ### AI overview TensorFlow 2.18 introduces NumPy 2.0 compatibility updates, transitions TFLite development to the LiteRT repository, and adds hermetic CUDA, cuDNN, and NCCL dependencies for more reproducible source builds. Binary packages add dedicated kernels for compute capability 8.9 GPUs, including NVIDIA RTX 40 series, L4, and L40, while dropping precompiled support for Maxwell GPUs. ### Source excerpt Posted by the TensorFlow team TensorFlow 2.18 has been released! Highlights of this release (and 2.17) include NumPy 2.0, LiteRT repository, CUDA Update, Hermetic CUDA and more. For the full release notes, please click here. Note: Release updates on the new multi-backend Keras will be published on keras.io, starting with Keras 3.0. For more information, please see https://keras.io/keras_3/. TensorFlow Core NumPy 2.0 The upcoming TensorFlow 2.18 release will include support for NumPy 2.0. While the majority of TensorFlow APIs will function seamlessly with NumPy 2.0, this may break some edge cases of usage, e.g., out-of-boundary conversion errors and numpy scalar representation errors. You can consult the following common solutions. Note that NumPy's type promotion rules have been changed (See NEP 50 for details). This may change the precision at which computations happen, leading either to type errors or to numerical changes to results. Please see the NumPy 2 migration guide. We've updated some TensorFlow tensor APIs to maintain compatibility with NumPy 2.0 while preserving the out-of-boundary conversion behavior in NumPy 1.x. LiteRT Repository We're making some changes to how LiteRT (formerly known as TFLite) is developed. Over the coming months, we'll be gradually transitioning TFLite's codebase to LiteRT. Once the migration is complete, we'll start accepting contributions directly through the LiteRT repository. There will no longer be any binary TFLite releases and developers should switch to LiteRT for the latest updates. Hermetic CUDA If you build TensorFlow from source, Bazel will now download specific versions of CUDA, CUDNN and NCCL distributions, and then use those tools as dependencies in various Bazel targets. This enables more reproducible builds for Google ML projects and supported CUDA versions because the build no longer relies on the locally installed versions. More details are provided here. CUDA Update TensorFlow binary distributions now ship with d ## "Llama 3.2 in Keras" DevFeed: ["Llama 3.2 in Keras"]() Original publisher: [Read original article]() Author: Martin Görner Published: 2024-10-21T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Keras](), [llama3](), [Large Language Model](), [tokenization](), [Fine-tuning](), [PyTorch](), [Tensorflow](), [Transformers]() Tags: [fine-tuning](), [keras](), [llama3](), [llm](), [llms](), [open-source](), [pytorch](), [tensorflow](), [tokenization](), [training](), [transformers]() ### AI overview The article introduces Llama 3.2 support in Keras, explaining that Hugging Face checkpoints can be loaded directly and converted on the fly when needed. It also describes Keras and keras-hub support for multiple backends, pretrained models, tokenization, preprocessing, training, and fine-tuning. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Deep Learning Frameworks for Beginners: A Comparison of TensorFlow vs. PyTorch vs. Keras DevFeed: [Deep Learning Frameworks for Beginners: A Comparison of TensorFlow vs. PyTorch vs. Keras]() Original publisher: [Read original article]() Author: admin Published: 2024-05-14T10:48:43Z Content type: comparison Language: en Sources: [Posts on Chris Banes]() Topics: [Deep learning](), [Frameworks](), [Tensorflow](), [PyTorch]() Tags: [ai](), [comparison](), [deep-learning](), [frameworks](), [pytorch](), [tensorflow](), [uncategorized](), [vs]() ### AI overview This beginner-oriented comparison introduces deep learning frameworks and discusses TensorFlow, PyTorch, and Keras. It explains how frameworks support the design, training, and testing of deep learning models, with particular attention to TensorFlow's scalability, mobile deployment through TensorFlow Lite, and production pipelines through TFX. ### Source excerpt Have you ever wondered how computers can recognize faces, understand your voice commands, or even beat you at a game of chess? That's deep learning in action! Deep learning is a powerful part of artificial intelligence (AI) that teaches computers to learn from data, just like humans do. Deep learning frameworks are handy tools, enabling [...] ## Total noob's intro to Hugging Face Transformers DevFeed: [Total noob's intro to Hugging Face Transformers]() Original publisher: [Read original article]() Author: Andrew Jardine Published: 2024-03-22T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [Transformers](), [hugging face](), [Machine learning](), [Open Source](), [Natural language processing](), [Library](), [Python](), [spaces](), [datasets](), [Computer vision](), [PyTorch](), [Tensorflow]() Tags: [artificial-intelligence](), [community](), [computer-vision](), [datasets](), [frameworks](), [github](), [guide](), [hugging-face](), [library](), [machine-learning](), [open-source](), [python](), [pytorch](), [science](), [source](), [spaces](), [tensorflow](), [transformers](), [vision]() ### AI overview This beginner-friendly guide introduces Hugging Face Transformers and open-source machine learning to readers without prior technical or Python knowledge. It explains the Transformers library, pretrained models, supported tasks and frameworks, the Hugging Face Hub for sharing models and datasets, and Spaces for building and hosting web-based machine learning demos and applications. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Graph neural networks in TensorFlow DevFeed: [Graph neural networks in TensorFlow]() Original publisher: [Read original article]() Author: Google AI (noreply@blogger.com) Published: 2024-02-06T19:17:00Z Content type: release Language: en Sources: [Google Research]() Topics: [Graphs](), [Tensorflow](), [Library](), [Google](), [Neural Network]() Tags: [google](), [graph](), [graph-mining](), [graphs](), [library](), [machine-learning](), [neural-networks](), [release](), [tensorflow]() ### AI overview Google Research announces TensorFlow GNN 1.0, a production-tested library for building and training graph neural networks at large scales. The library supports heterogeneous graphs, TensorFlow modeling and training, and extracting input graphs from large data stores. ### Source excerpt Posted by Dustin Zelle, Software Engineer, Google Research, and Arno Eigenwillig, Software Engineer, CoreML Objects and their relationships are ubiquitous in the world around us, and relationships can be as important to understanding an object as its own attributes viewed in isolation -- take for example transportation networks, production networks, knowledge graphs, or social networks. Discrete mathematics and computer science have a long history of formalizing such networks as graphs, consisting of nodes connected by edges in various irregular ways. Yet most machine learning (ML) algorithms allow only for regular and uniform relations between input objects, such as a grid of pixels, a sequence of words, or no relation at all. Graph neural networks, or GNNs for short, have emerged as a powerful technique to leverage both the graph's connectivity (as in the older algorithms DeepWalk and Node2Vec) and the input features on the various nodes and edges. GNNs can make predictions for graphs as a whole (Does this molecule react in a certain way?), for individual nodes (What's the topic of this document, given its citations?) or for potential edges (Is this product likely to be purchased together with that product?). Apart from making predictions about graphs, GNNs are a powerful tool used to bridge the chasm to more typical neural network use cases. They encode a graph's discrete, relational information in a continuous way so that it can be included naturally in another deep learning system. We are excited to announce the release of TensorFlow GNN 1.0 (TF-GNN), a production-tested library for building GNNs at large scales. It supports both modeling and training in TensorFlow as well as the extraction of input graphs from huge data stores. TF-GNN is built from the ground up for heterogeneous graphs, where types of objects and relations are represented by distinct sets of nodes and edges. Real-world objects and their relations occur in distinct types, and TF-GNN's heterogen ## Building a board game with the TFLite plugin for Flutter DevFeed: [Building a board game with the TFLite plugin for Flutter]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2023-10-18T17:00:00Z Content type: tutorial Language: en Sources: [The TensorFlow Blog]() Topics: [Flutter](), [TensorFlow Lite](), [Inference](), [Reinforcement learning](), [Tensorflow](), [TensorFlow Agents](), [cross-platform](), [Mobile](), [board-game](), [Android](), [iOS]() Tags: [android](), [building](), [cross-platform](), [flutter](), [games](), [how-to](), [inference](), [ios](), [learn](), [mobile](), [plugin](), [reinforcement-learning](), [tensorflow](), [tensorflow-agents](), [tensorflow-lite](), [tutorial](), [tutorials]() ### AI overview This tutorial shows how to port a TensorFlow Lite reinforcement-learning board game to Flutter. It loads a converted model, runs inference to choose the next move, and renders the game for Android and iOS using the Flutter frontend and TensorFlow Lite plugin. ### Source excerpt Posted by Wei Wei, Developer Advocate In our previous blog posts Building a board game app with TensorFlow: a new TensorFlow Lite reference app and Building a reinforcement learning agent with JAX, and deploying it on Android with TensorFlow Lite, we demonstrated how to train a reinforcement learning (RL) agent with TensorFlow, TensorFlow Agents and JAX respectively, and then deploy the converted TFLite model in an Android app using TensorFlow Lite, to play a simple board game 'Plane Strike'. While these end-to-end tutorials are helpful for Android developers, we have heard from the Flutter developer community that it would be interesting to make the app cross-platform. Inspired by the officially released TensorFlow Lite Plugin for Flutter recently, we are going to write one last tutorial and port the app to Flutter. Since we already have the model trained with TensorFlow and converted to TFLite, we can just load the model with TFLite interpreter: void _loadModel() async { // Create the interpreter _interpreter = await Interpreter.fromAsset(_modelFile); } Then we pass in the user board state and help the game agent identify the most promising position to strike next (please refer to our previous blog posts if you need a refresher on the game rules) by running TFLite inference: int predict(List> boardState) { var input = [boardState]; var output = List.filled(_boardSize * _boardSize, 0) .reshape([1, _boardSize * _boardSize]); // Run inference _interpreter.run(input, output); // Argmax double max = output[0][0 ]; int maxIdx = 0; for (int i = 1; i < _boardSize * _boardSize; i++) { if (max < output[0][i]) { maxIdx = i; max = output[0][i]; } } return maxIdx; } That's it! With some additional Flutter frontend code to render the game boards and track game progress, we can immediately run the game on both Android and iOS (currently the plugin only supports these two mobile platforms). You can find the complete code on GitHub. If you want to dig digger, there ar ## The TensorFlow Lite Plugin for Flutter is Officially Available DevFeed: [The TensorFlow Lite Plugin for Flutter is Officially Available]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2023-08-18T16:00:00Z Content type: news Language: en Sources: [The TensorFlow Blog]() Topics: [Flutter](), [TensorFlow Lite](), [Tensorflow](), [cross-platform](), [Mobile](), [object-detection](), [GitHub](), [Google](), [Kaggle]() Tags: [announcement](), [cross-platform](), [explore](), [flutter](), [github](), [google](), [inference](), [kaggle](), [mobile](), [object-detection](), [plugin](), [tensorflow](), [tensorflow-lite](), [tensorflowlite](), [tutorial]() ### AI overview The TensorFlow Lite plugin for Flutter has been officially migrated to the TensorFlow GitHub account and released. The updated plugin adds features and example apps, including live-camera object detection, and enables local TensorFlow model inference in Flutter apps across supported platforms. ### Source excerpt Posted by Paul Ruiz, Developer Relations Engineer We're excited to announce that the TensorFlow Lite plugin for Flutter has been officially migrated to the TensorFlow GitHub account and released! Three years ago, Amish Garg, one of our talented Google Summer of Code contributors, wrote a widely used TensorFlow Lite plugin for Flutter. The plugin was so popular that we decided to migrate it to our official repo, making it easier to maintain directly by the Google team. We are grateful to Amish for his contributions to the TensorFlow Lite Flutter plugin. Through the efforts of developers in the community, the plugin has been updated to the latest version of TensorFlow Lite, and a collection of new features and example apps have been added, such as object detection through a live camera feed. So what is TensorFlow Lite? TensorFlow Lite is a way to run TensorFlow models on devices locally, supporting mobile, embedded, web, and edge devices. TensorFlow Lite's cross-platform support and on-device performance optimizations make it a great addition to the Flutter development toolbox. Our goal with this plugin is to make it easy to integrate TensorFlow Lite models into Flutter apps across mobile platforms, with desktop support currently in development through the efforts of our developer community. Find pre-trained TensorFlow Lite models on model repos like Kaggle Models or create your own custom TensorFlow Lite models. Let's take a look at how you could use the Flutter TensorFlow Lite plugin for image classification: TensorFlow Lite Image Classification with Flutter First you will need to install the plugin from pub.dev. Once the plugin is installed, you can load a TensorFlow Lite model into your Flutter app and define the input and output tensor shapes. If you're using the MobileNet model, then the input tensor will be a 224 by 224 RGB image, and the output will be a list of confidence scores for the trained labels. // Load model Future _loadModel() async { final opt ## Building Firebase Quickdraw DevFeed: [Building Firebase Quickdraw]() Original publisher: [Read original article]() Author: Firebase Team Published: 2021-06-29T00:00:00Z Content type: tutorial Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [App](), [AI Models](), [Cloud Functions](), [Firestore](), [hosting](), [Tensorflow]() Tags: [ai](), [ai-models](), [building](), [case-study](), [cloud-functions](), [firebase](), [firestore](), [hosting](), [machine-learning](), [tutorials]() ### AI overview The Firebase team describes building Firebase Quickdraw, a collaborative hackathon app that uses an AI bot to guess users' drawings. The article explains how Firebase Hosting, Cloud Firestore, Cloud Functions, and a deployed TensorFlow model support the game, scoring, leaderboard, and deployment. ### Source excerpt News, tutorials, and updates from the Firebase team. ## KotlinDL 0.2: Functional API, зоопарк моделей c ResNet и MobileNet, DSL для обработки изображений DevFeed: [KotlinDL 0.2: Functional API, зоопарк моделей c ResNet и MobileNet, DSL для обработки изображений]() Original publisher: [Read original article]() Author: zaleslaw (JetBrains) Published: 2021-05-25T08:54:42Z Content type: release Language: ru Sources: [JetBrains RU]() Topics: [Kotlin](), [Deep neural networks](), [Maven Central](), [Tensorflow](), [Keras](), [ImageNet]() Tags: [dataset](), [deep-learning](), [image-processing](), [keras](), [kotlin](), [machine-learning](), [maven-central](), [neural-networks](), [tag-00486ebd8d87](), [tag-9d8cf70dc46c](), [tensorflow]() ### AI overview This article presents KotlinDL 0.2, a deep-learning library written in Kotlin with TensorFlow used for low-level computations. The release adds a Functional API for graph-based neural networks, an image-preprocessing DSL, new dataset types, and a model zoo containing ResNet, MobileNet, and VGG models. KotlinDL 0.2 is available on Maven Central. ### Source excerpt Представляем вам версию 0.2 библиотеки KotlinDL. Это библиотека глубокого обучения, где для низкоуровневых вычислений используется TensorFlow, но с высокоуровневым API и логикой, написанными на Kotlin. KotlinDL 0.2 теперь доступен на Maven Central (до этого он лежал на bintray, но закатилось солнышко земли опенсорсной). Появилось столько всего нового: новые слои, специальный DSL для препроцессинга изображений, новые типы датасетов, зоопарк моделей с несколькими моделями из семейства ResNet, MobileNet и старой доброй моделью VGG (рабочая лошадка, впрочем). В этой статье мы коснемся самых главных изменений релиза 0.2. Полный список изменений доступен по ссылке. Читать далее ## Why Data Pipelines Should Avoid Monolithic Queue Processors DevFeed: [Why Data Pipelines Should Avoid Monolithic Queue Processors]() Original publisher: [Read original article]() Author: Fuzzygroup Published: 2020-07-20T00:00:00Z Content type: article Language: en Sources: [Scott Johnson]() Topics: [data observability](), [Amazon Simple Queue Service (SQS)](), [debugging](), [Amazon Web Services](), [GPU](), [cpu](), [Tensorflow]() Tags: [aws](), [cpu](), [data-pipeline](), [data-pipelines](), [data-processing](), [debugging](), [gpu](), [process](), [sqs](), [tensorflow]() ### AI overview The article describes lessons from building a high-performance, near-real-time data pipeline on AWS with SQS and machine learning components. It argues that a monolithic queue processor can increase cloud costs when GPU-backed processing is applied to work that does not require a GPU, make debugging harder, and limit independent scaling of different processing routines. ### Source excerpt I am in the process of wrapping up a year long engagement where I: Built a high performance data pipeline Capable of processing all of Twitter in real time / near real time Applied multiple tools to the data at different stages of the pipeline Applied one or more Machine Learning models at different stages of the pipeline Operated on AWS using SQS as the queueing structure This blog post talks about one of the key things I learned in terms of the data pipeline, specifically: **Do Not Build Data Pipelines Around a Monolithic Queue Processor ** Note: By queue processor I mean the bit of software which pulls the data of the queue, operates on it and then puts it back. This lesson may be obvious to some but we took a meandering approach to this problem where we started with the idea of distributed pipeline components, moved to a monolithic approach and then ended up back at a distributed approach. As with a lot of research endeavors, the obvious conclusion wasn't quite so obvious in the throes of the research. Lesson 01: Monolithic Queue Processing Raises Your Costs At the heart of our queue processing were a number of Machine Learning components (python / tensorflow) that really needed a GPU for efficient data processing. The problem here is that when you have a monolithic queue processor, all your processing happens on a box with the GPU whether or not all that processing needs the GPU. When you are using cloud computing, you pay for the GPU whether not not it is being used for a given operation. And since GPU boxes generally cost at least 5x to 6x more than CPU only boxes, well, our monolithic queue processor proved to be an economic disaster. Lesson 02: Monolithic Queue Processing Is Harder to Debug After realizing Lesson 01, I took our monolithic queue processor apart and broke it down into 8 (ultimately 9) individual queue processors. One thing that I quickly found is that debugging the 8 individual queue processors was dramatically easier than debugging the singl ## Neural network inference pipeline for videos in Tensorflow DevFeed: [Neural network inference pipeline for videos in Tensorflow]() Original publisher: [Read original article]() Author: Suresh Alse (noreply@blogger.com) Published: 2019-08-08T18:03:00Z Content type: tutorial Language: en Sources: [Life Plus Linux]() Topics: [Tensorflow](), [Inference](), [Machine learning](), [GPU](), [cpu](), [dataset](), [Keras]() Tags: [cpu](), [dataset](), [deeplearning](), [gpu](), [inference](), [keras](), [performance](), [pipeline](), [tensorflow]() ### AI overview A tutorial on building an efficient TensorFlow pipeline for video inference. It describes processing video frames in batches with tf.data.Dataset, parallelizing CPU preprocessing and I/O, and prefetching to keep CPU and GPU work supplied. ### Source excerpt Just as we saw a huge influx of images in the past decade or so, we are now seeing a lot of videos being produced on social media. The need to understand and moderate videos using machine learning has never been greater. In this post, I will show you how to build an efficient pipeline to processes videos in Tensorflow. For simplicity, let us consider a Resnet50 model pre-trained on Imagenet. Pretty straightforward, using tf.keras.applications Now, let us break it up to see what exactly is happening: We are loading the model with weights. We are reading an image and resizing it to 224x224. Do some preprocessing of the image. Run inference. Do some post processing. If we want to do something similar for large videos, we need to have a pipeline that takes a stream of frames from the video, applies preprocess transformations, run inference of frames, unravel the inferences and apply post processing. We can see that doing all these in a sequence - frame by frame is clearly not the right thing as it is slow and inefficient. In order to tackle this, we will use tf.data.Dataset and run inference in batch. First, lets create a generator that can produce frames from a video: We will use the tf.data.Dataset.from_generator method to create a dataset object out of this. Now let us define a function which does resizing, normalization and other preprocessing steps that are required on a batch of frames. Then, using the batch operation on the dataset created above, create a batch of size 64. Map the preprocess method that we defined onto the batch in parallel on CPU as it is a CPU intensive task. It is important to make sure that I/O is parallelized as much as possible. For best performance, instructions that are well suited for CPU should run on CPU and the ones suited for GPU should run on GPU. Also, If you observe the code above, we are prefetching. What this means is that, before consuming the dataset, a batch of 64 frames are preprocessed and is ready for consumption. By the t ## The perils of tensor.dataSync() DevFeed: [The perils of tensor.dataSync()]() Original publisher: [Read original article]() Author: Monica Dinculescu Published: 2019-02-22T00:00:00Z Content type: tutorial Language: en Sources: [Monica Dinculescu]() Topics: [Tensorflow](), [WebGL](), [GPU](), [cpu]() Tags: [cpu](), [gpu](), [javascript](), [tensorflow](), [webgl]() ### AI overview This TensorFlow.js post explains why synchronously converting tensors to JavaScript values with tensor.dataSync() can block the UI and cause janky rendering. It describes how tensor data moves between CPU memory and GPU-backed WebGL textures, and why repeated transfers are costly. ### Source excerpt One of the first things you stumble on when you start using TensorFlow.js is that sometimes you need your data as a Tensor, and sometimes you need it as a JavaScript number. Maybe it's for logging it, maybe it's for displaying it somewhere during training, maybe it's because you don't trust the robots to be better than you at math. This is a quick post that tries to clarify why doing this synchronously is probably bad and will leave your UI really janky. Nikhil (who like, birthed TensorFlow.js, bless) was kind enough to explain this to me recently, so I figured I'd return the favour, with fewer meeps and more mistakes. Downloading and Uploading When you create a Tensor, it lives on the CPU. The mere fact that it's a Tensor doesn't automatically move that data into its GPU mansion - it needs to be used in a WebGL program. (I'm playing fast and loose here with the words GPU and CPU btw, so hold back the pedantics: when I say "it lives on the CPU" I mean "in main memory, where the CPU processes stuff"; the GPU has it's own memory, that's where it processes stuff, and that's where that data has to get transferred to. It's fine. You know I know.) You upload the tensor to the GPU when you call one of the tf. operations on it. Tensor operations are matrix math, and matrix math is really fast on the GPU, so every time you call something like sum or sqrt on a Tensor, TensorFlow.js creates a little WebGL operation, and sends it to the backend. Whatever data lived on the CPU is now "uploaded" to the GPU (to a WebGL texture). You download a Tensor when you want to get that data from the GPU back onto the CPU. The data now lives in a WebGL texture, so TensorFlow.js needs to call readPixels to ... read... those pixels... from the texture and convert them back into something you can use. Here's the problem: calling readPixels is fundamentally a blocking operation: when you ask the GPU to give you data, you have to wait for it to respond; this means you can't really do anything else on t ## Presenting Project Ergo: How to Build an Airplane Detector for Satellite Imagery With Deep Learning DevFeed: [Presenting Project Ergo: How to Build an Airplane Detector for Satellite Imagery With Deep Learning]() Original publisher: [Read original article]() Author: Simone Margaritelli Published: 2018-11-22T17:15:50Z Content type: tutorial Language: en Sources: [evilsocket]() Topics: [Keras](), [Tensorflow](), [Framework](), [Deep learning](), [Deep neural networks](), [datasets](), [Open Source](), [Code](), [Development](), [Back end](), [Python](), [Shell]() Tags: [cnn](), [code](), [computer-vision](), [convolutional-neural-networks](), [cpu](), [cuda](), [cudnn](), [cybersecurity](), [deep-learning](), [deep-neural-networks](), [dnn](), [ergo](), [how-to](), [image-classification](), [keras](), [machine-learning](), [neural-networks](), [nvidia](), [open-source](), [planes](), [planes-detector](), [planesnet](), [project-release](), [python](), [shell](), [tensorflow](), [tf](), [train](), [training](), [tutorial]() ### AI overview The article introduces Project Ergo, an open-source framework and manager for Keras-based machine-learning projects. It demonstrates prototyping, training, and testing a convolutional neural network with the PlanesNet dataset to build an airplane detector for satellite imagery, including CPU and GPU setup considerations. ### Source excerpt It's been a while that i've been quite intensively playing with Deep Learning both for work related research and personal projects. More specifically, I've been using the Keras framework on top of a TensorFlow backend for all sorts of stuff. From big and complex projects for malware detection, to smaller and simpler experiments about ideas i just wanted to quickly implement and test - it didn't really matter the scope of the project, I always found myself struggling with the same issues: code reuse over tens of crap python and shell scripts, datasets and models that are spread all over my dev and prod servers, no real standard for versioning them, no order, no structure. So a few days ago I started writing what it was initially meant to be just a simple wrapper for the main commands of my training pipelines but quickly became a full-fledged framework and manager for all my Keras based projects. Today I'm pleased to open source and present project Ergo by showcasing an example use-case: we'll prototype, train and test a Convolutional Neural Network on top of the PlanesNet raw dataset in order to build an airplane detector for satellite imagery. ## Deep learning experiments in OCaml DevFeed: [Deep learning experiments in OCaml]() Original publisher: [Read original article]() Author: Laurent Mazare Published: 2018-09-20T00:00:00Z Content type: tutorial Language: en Sources: [Jane Street]() Topics: [OCaml](), [Machine learning](), [Tensorflow](), [Programming](), [GPU]() Tags: [deep-learning](), [gpu](), [machine-learning](), [neural-networks](), [ocaml](), [programming](), [programming-language](), [recurrent](), [rnn](), [tensorflow]() ### AI overview This article describes reproducing classical deep learning experiments in OCaml instead of Python. It explains using TensorFlow bindings to train functional OCaml models on a GPU, including Neural Style Transfer and character-level language modeling, and discusses type-safe representations of TensorFlow computation graphs. ### Source excerpt Last year we held a machine learning seminar in our London office, which was an opportunity to reproduce some classical deep learning results with a nice twist: we used OCaml as a programming language rather than Python. This allowed us to train models defined in a functional way in OCaml on a GPU using TensorFlow. ## Using TensorFlow and the Serverless Framework for deep learning and image recognition DevFeed: [Using TensorFlow and the Serverless Framework for deep learning and image recognition]() Original publisher: [Read original article]() Author: Rustem Feyzkhanov Published: 2018-07-24T00:00:00Z Content type: tutorial Language: en Sources: [Serverless Blog]() Topics: [Tensorflow](), [serverless framework](), [Deep learning](), [AWS Lambda](), [Amazon API Gateway](), [Amazon Web Services]() Tags: [api-gateway](), [aws](), [aws-lambda](), [cloud-computing](), [deep-learning](), [engineering](), [faas](), [function-as-a-service](), [how-to](), [image-recognition](), [infrastructure-as-code](), [serverless](), [serverless-architecture](), [serverless-framework](), [tensorflow]() ### AI overview A tutorial on deploying a simple deep learning model for image recognition with TensorFlow, the Serverless Framework, AWS Lambda, and API Gateway. ### Source excerpt We'll cover how to use TensorFlow, the Serverless Framework, AWS Lambda and API Gateway to deploy a simple deep learning model. ## Introduction to Machine Learning with TensorFlow.js DevFeed: [Introduction to Machine Learning with TensorFlow.js]() Original publisher: [Read original article]() Author: Monica Dinculescu Published: 2018-05-22T00:00:00Z Content type: tutorial Language: en Sources: [Monica Dinculescu]() Topics: [Tensorflow](), [Machine learning](), [JavaScript](), [Code](), [Algorithms](), [math](), [Demo]() Tags: [algorithms](), [code](), [demo](), [graph](), [javascript](), [machine-learning](), [math](), [models](), [open-source](), [tensorflow]() ### AI overview This tutorial introduces machine learning concepts with TensorFlow.js, an open-source JavaScript library. It explains how models learn patterns from data and demonstrates fitting a curve by learning unknown coefficients from training points. ### Source excerpt Machine Learning (ML) is the dope new thing that everyone's talking about, because it's really good at learning from data so that it can predict similar things in the future. Doing ML by hand is pretty annoying since it usually involves matrix math which is zero fun in JavaScript (or if you ask me: anywhere 😅). Thankfully, TensorFlow.js is here to help! It's an open source library that has a lot of built-in Machine Learning-y things like models and algorithms so that you don't have to write them from scratch. Is your problem a Machine Learning problem? Machine learning is good at classifying and labelling data. The premise of every machine learning problem is: Someone gives us some data that was generated according to a secret formula. This data could be a bunch of points (that are generated based on some math equation), but could also be fun, like images (the secret formula could be "some of these images are chihuahuas and some are blueberry muffins) or bus schedules. By looking at this data we were given, we approximate the secret formula so that we can correctly predict a future data point. For example, if we're given a photo, we will eventually be able to confidently say whether it's a dog or a muffin. A fun demo! If you want to get started, predicting numbers tends to be easier than predicting images, so in this example we're trying to fit a curve to a bunch of data (this is the same example from the TensorFlow site but with waaaaay more code comments and a prettier graph). We are given a bunch of points (for x between -1 and 1, calculate a y according to y = a * x^3 + b * x^2 + c * x + d - we know this is the secret formula but we don't know the values of those a,b,c,d coefficients.) Our goal is to learn these coefficients, so that if we're given a new x value, we can say what the y value should be. The blue dots are the training points we were given. The red dots would be our guesses, based on our initial, default coefficients (hella incorrect!). Once you cli ## Higher level ops for building neural network layers with deeplearn.js DevFeed: [Higher level ops for building neural network layers with deeplearn.js]() Original publisher: [Read original article]() Author: Suresh Alse (noreply@blogger.com) Published: 2018-01-23T22:36:00Z Content type: tutorial Language: en Sources: [Life Plus Linux]() Topics: [Neural Network](), [Tensorflow](), [Code](), [Graphs]() Tags: [batching](), [code](), [datasets](), [deeplearning](), [graph](), [javascript](), [ml](), [neural](), [tensorflow](), [visualization]() ### AI overview This tutorial describes higher-level neural-network operations built for deeplearn.js, specifically implementations of tf.layers.conv2d and tf.layers.flatten. The operations are designed to closely follow corresponding TensorFlow function definitions, with documented arguments and return behavior. ### Source excerpt I have been meddling with google's deeplearn.js lately for fun. It is surprisingly good given how new the project is and it seems to have a sold roadmap. However it still lacks something like tf.layers and tf.contrib.layers which have many higher level functions that has made using tensorflow so easy. It looks like they will be added to Graphlayers in future but their priorities as of now is to fix the lower level APIs first - which totally makes sense. So, I quickly built one for tf.layers.conv2d and tf.layers.flatten which I will share in this post. I have made them as close to function definitions in tensorflow as possible. 1. conv2d - Functional interface for the 2D convolution layer. Arguments: inputs Tensor input. filters Integer, the dimensionality of the output space (i.e. the number of filters in the convolution). kernel_size Number to specify the height and width of the 2D convolution window. graph Graph opbject. strides Number to specify the strides of convolution. padding One of "valid" or "same" (case-insensitive). data_format "channels_last" or "channel_first" activation Optional. Activation function which is applied on the final layer of the function. Function should accept Tensor and graph as parameters kernel_initializer An initializer object for the convolution kernel. bias_initializer An initializer object for bias. name string which represents name of the layer. Returns: Tensor output. Usage: Add this to your code: 2. flatten - Flattens an input tensor. I wrote these snippets while building a tool using deeplearnjs where I do things like loading datasets, batching, saving checkpoints along with visualization. I will share more on that in my future posts. ## Tensorflow and AEM DevFeed: [Tensorflow and AEM]() Original publisher: [Read original article]() Author: Suresh Alse (noreply@blogger.com) Published: 2017-12-17T20:40:00Z Content type: tutorial Language: en Sources: [Life Plus Linux]() Topics: [Tensorflow](), [Java](), [configuration](), [interoperability](), [Deep learning](), [Machine learning]() Tags: [aem](), [c-plus-plus](), [configuration](), [deep-learning](), [deeplearning](), [gpu](), [guide](), [interoperability](), [java](), [ml](), [tensorflow](), [testing]() ### AI overview A tutorial on setting up TensorFlow for Java in Adobe Experience Manager and other Felix-based systems. It covers Maven and bundle configuration, JNI installation, library placement, and testing with a Sling servlet. ### Source excerpt It has been a while since google released Tensorflow support for java. Even though it is still in its infancy, I feel like it has everything we need. Build computation graphs - check, run session and compute stuff - check, GPU support - check. Now if you have all the time in the world to reinvent the wheel, you can pretty much build anything in java that we can build using python or c++. So, I have been working on Adobe Experience Manager since I joined Adobe and recently, I started experimenting with several use cases where machine learning can help in content creation and discovery. As I have zero knowledge in building any deep learning models in java, I decided to build everything in java. How hard can it be? Right? Right? Sarcasm aside, as I mentioned earlier, Tensorflow for java has everything we need and as it internally uses JNI we can have interoperability with python and c++ (that's why I preferred this over deeplearning4j). First off, I followed their official guide for the setup and had to face a lot of hurdles along the way. In this post I will show you how I managed to successfully setup Tensorflow on AEM (or any felix based systems). Step 1 Add the dependency to your pom.xml file. Note that the scope set to compile. Step 2 Add this configuration to your maven-bundle-plugin. Step 3 Build and install to your AEM instance. Then, navigate to /system/console/bundles/ and look for the bundle which contains the dependency. See if the "Exported Packages" section has the following packages: Step 4 Install JNI if necessary (this is mentioned in the link that I shared earlier). Then place the library file in the appropriate place. Testing Lets write a simple sling servlet to check if everything is working as expected. Like I told earlier, Tensorflow for java is still in its infancy. So, I wrote a helper class a while back to manipulate the computation graph. Get GraphBuilder.java and place it where it is accessible to the sling servlet. GraphBuilder.java The foll ## Running Tensorflow on AWS GPUs DevFeed: [Running Tensorflow on AWS GPUs]() Original publisher: [Read original article]() Author: Nelson Elhage Published: 2017-02-26T23:41:27Z Content type: tutorial Language: en Sources: [Nelson Elhage]() Topics: [Tensorflow](), [Amazon Web Services](), [Amazon EC2](), [CUDA](), [cudnn](), [Ubuntu]() Tags: [aws](), [cuda](), [cudnn](), [ec2](), [gpu](), [tensorflow](), [ubuntu]() ### AI overview A tutorial-style post describing how to prepare an Ubuntu Amazon EC2 GPU environment for TensorFlow model training. It covers creating an AMI with NVIDIA drivers, CUDA, cuDNN, and GPU-enabled TensorFlow, along with kernel-driver installation issues. ### Source excerpt I've been spending some time learning deep learning and tensorflow recently, and as part of that project I wanted to be able to train models using GPUs on EC2. This post contains some notes on what it took to get that working. As many people have commented, the environment setup is often the hardest part of getting a deep learning setup going, so hopefully this will be useful reference to someone.