# The TensorFlow Blog The official TensorFlow blog. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## What's new in TensorFlow 2.20 DevFeed: [What's new in TensorFlow 2.20]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2025-08-19T16:00:00Z Content type: news Language: en Sources: [The TensorFlow Blog]() Topics: [LiteRT](), [On-device AI](), [Inference](), [Latency](), [IO](), [GPU](), [data](), [Google](), [Cloud](), [Python](), [C++](), [Kotlin]() Tags: [announcement](), [c-plus-plus](), [data](), [google](), [gpu](), [inference](), [io](), [kotlin](), [latency](), [litert](), [npu](), [on-device](), [python](), [tensorflow](), [tensorflow-core](), [tensorflow-lite]() ### AI overview TensorFlow 2.20 introduces the independent LiteRT repository as the future home for on-device inference, replacing the deprecated tf.lite module. LiteRT adds Kotlin and C++ APIs, improves NPU and GPU acceleration, and supports lower-latency inference with fewer memory copies. The release also adds tf.data input-pipeline warm-up controls and makes Google Cloud Storage support optional. ### Source excerpt Posted by the TensorFlow team TensorFlow 2.20 has been released! For ongoing updates related to the multi-backend Keras, please note that all news and releases, starting with Keras 3.0, are now published directly on keras.io. You can find a complete list of all changes in the full release notes on GitHub. tf.lite is being replaced by LiteRT The tf.lite module will be deprecated with development for on-device inference moving to a new, independent repository: LiteRT. The new APIs are available in Kotlin and C++. This code base will decouple from the TensorFlow repository and tf.lite will be removed from future TensorFlow Python packages, so we encourage migration of projects to LiteRT to receive the latest updates. More details to follow. As announced at Google I/O '25, LiteRT improves upon TFLite, particularly for NPU and GPU hardware acceleration and performance for on-device ML and AI applications. LiteRT provides a unified interface for Neural Processing Units (NPUs), removing the need to navigate vendor-specific compilers or libraries. This approach avoids many device-specific complications, boosts performance for real-time and large-model inference, and minimizes memory copies through zero-copy hardware buffer usage. For more information on the new repository and to sign up for the NPU Early Access Program, please reach out to the team at g.co/ai/LiteRT-NPU-EAP. Faster input pipeline warm-up with tf.data To help reduce latency, especially the time it takes for your model to process the first element of a dataset, we've added autotune.min_parallelism in tf.data.Options. This new option allows asynchronous dataset operations like .map and .batch to immediately start with a specified minimum level of parallelism, speeding up the initial warm-up time for your input pipelines. Changes to I/O GCS filesystem package The tensorflow-io-gcs-filesystem package for Google Cloud Storage support is now optional. Previously, it was installed, by default, with TensorFlow. If y ## 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. ## Introducing Wake Vision: A High-Quality, Large-Scale Dataset for TinyML Computer Vision Applications DevFeed: [Introducing Wake Vision: A High-Quality, Large-Scale Dataset for TinyML Computer Vision Applications]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2024-12-05T17:00:00Z Content type: article Language: en Sources: [The TensorFlow Blog]() Topics: [Training AI Models](), [machine learning overfitting]() Tags: [ai](), [benchmarks](), [community](), [computer-vision](), [data-quality](), [datasets](), [edge](), [google-ai](), [litert](), [machine-learning](), [on-device-ai](), [person-detection](), [research](), [tensorflow-lite](), [training]() ### AI overview Wake Vision is a roughly 6-million-image dataset for TinyML person detection. It provides large and quality-focused training sets, emphasizing that accurate labels can be especially valuable for constrained models. ### Source excerpt Posted by Colby Banbury, Emil Njor, Andrea Mattia Garavagno, Vijay Janapa Reddi - Harvard University TinyML is an exciting frontier in machine learning, enabling models to run on extremely low-power devices such as microcontrollers and edge devices. However, the growth of this field has been stifled by a lack of tailored large and high-quality datasets. That's where Wake Vision comes in--a new dataset designed to accelerate research and development in TinyML. Why TinyML Needs Better Data The development of TinyML requires compact and efficient models, often only a few hundred kilobytes in size. The applications targeted by standard machine learning datasets, like ImageNet, are not well-suited for these highly constrained models. Existing datasets for TinyML, like Visual Wake Words (VWW), have laid the groundwork for progress in the field. However, their smaller size and inherent limitations pose challenges for training production-grade models. Wake Vision builds upon this foundation by providing a large, diverse, and high-quality dataset specifically tailored for person detection--the cornerstone vision task for TinyML. What Makes Wake Vision Different? Wake Vision is a new, large-scale dataset with roughly 6 million images, almost 100 times larger than VWW, the previous state-of-the-art dataset for person detection in TinyML. The dataset provides two distinct training sets: Wake Vision (Large): Prioritizes dataset size. Wake Vision (Quality): Prioritizes label quality. Wake Vision's comprehensive filtering and labeling process significantly enhances the dataset's quality. Why Data Quality Matters for TinyML Models In traditional overparameterized models, it is widely believed that data quantity matters more than data quality, as an overparameterized model can adapt to errors in the training data. But according to the image below, TinyML tells a different story: The figure above shows that high-quality labels (less error) are more beneficial for under-parameterized mo ## MLSysBook.AI: Principles and Practices of Machine Learning Systems Engineering DevFeed: [MLSysBook.AI: Principles and Practices of Machine Learning Systems Engineering]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2024-11-19T17:00:00Z Content type: article Language: en Sources: [The TensorFlow Blog]() Topics: [AI, ML & Data Engineering](), [Training AI Models]() Tags: [ai](), [community](), [data-engineering](), [deployment](), [hardware](), [inference](), [infrastructure](), [large-language-models-llms](), [machine-learning](), [model-development](), [monitoring-maintenance](), [optimization](), [socratiq](), [systems-engineering](), [tensorflow]() ### AI overview An overview of MLSysBook.ai's machine-learning systems engineering concepts, connected to the TensorFlow ecosystem. It emphasizes the infrastructure, hardware, scaling, deployment, efficiency, and reliability considerations required to build and operate machine-learning systems. ### Source excerpt Posted by Jason Jabbour, Kai Kleinbard and Vijay Janapa Reddi (Harvard University) Everyone wants to do the modeling work, but no one wants to do the engineering. If ML developers are like astronauts exploring new frontiers, ML systems engineers are the rocket scientists designing and building the engines that take them there. Introduction "Everyone wants to do modeling, but no one wants to do the engineering," highlights a stark reality in the machine learning (ML) world: the allure of building sophisticated models often overshadows the critical task of engineering them into robust, scalable, and efficient systems. The reality is that ML and systems are inextricably linked. Models, no matter how innovative, are computationally demanding and require substantial resources--with the rise of generative AI and increasingly complex models, understanding how ML infrastructure scales becomes even more critical. Ignoring the system's limitations during model development is a recipe for disaster. Unfortunately, educational resources on the systems side of machine learning are lacking. There are plenty of textbooks and materials on deep learning theory and concepts. However, we truly need more resources on the infrastructure and systems side of machine learning. Critical questions--such as how to optimize models for specific hardware, deploy them at scale, and ensure system efficiency and reliability--are still not adequately understood by ML practitioners. This lack of understanding is not due to disinterest but rather a gap in available knowledge. One significant resource addressing this gap is MLSysBook.ai. This blog post explores key ML systems engineering concepts from MLSysBook.ai and maps them to the TensorFlow ecosystem to provide practical insights for building efficient ML systems. The Connection Between Machine Learning and Systems Many think machine learning is solely about extracting patterns and insights from data. While this is fundamental, it's only part of the s ## 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 ## What's new in TensorFlow 2.17 DevFeed: [What's new in TensorFlow 2.17]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2024-07-18T16:00:00Z Content type: release Language: en Sources: [The TensorFlow Blog]() Topics: [releases]() Tags: [announcement](), [cuda](), [gpu](), [keras](), [python](), [tensorflow](), [tensorflow-core](), [tensorrt]() ### AI overview TensorFlow 2.17 adds dedicated CUDA kernels for compute capability 8.9 GPUs and ends precompiled Python-package support for compute capability 5.0. The article also previews NumPy 2.0 support in TensorFlow 2.18 and the removal of TensorRT support after 2.17. ### Source excerpt Posted by the TensorFlow team TensorFlow 2.17 has been released! Highlights of this release (and 2.16) include CUDA update, upcoming Numpy 2.0, 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 CUDA Update TensorFlow binary distributions now ship with dedicated CUDA kernels for GPUs with a compute capability of 8.9. This improves the performance on the popular Ada-Generation GPUs like NVIDIA RTX 40**, L4 and L40. To keep Python wheel sizes in check, we made the decision to no longer ship CUDA kernels for compute capability 5.0. That means the oldest NVIDIA GPU generation supported by the precompiled Python packages is now the Pascal generation (compute capability 6.0). For Maxwell support, we either recommend sticking with TensorFlow version 2.16, or compiling TensorFlow from source. The latter will be possible as long as the used CUDA version still supports Maxwell GPUs. Numpy 2.0 Upcoming TensorFlow 2.18 release will include support for Numpy 2.0. This may break some edge cases of TensorFlow API usage. Drop TensorRT support Starting with TensorFlow 2.18, support for TensorRT will be dropped. TensorFlow 2.17 will be the last version to include it. ## Faster Dynamically Quantized Inference with XNNPack DevFeed: [Faster Dynamically Quantized Inference with XNNPack]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2024-04-09T16:00:00Z Content type: article Language: en Sources: [The TensorFlow Blog]() Topics: [Inference Performance](), [quantization](), [TensorFlow Lite](), [cpu](), [Machine learning](), [model-deployment]() Tags: [ai](), [announcement](), [article](), [cpu](), [inference](), [inference-performance](), [learn](), [ml](), [performance](), [precision](), [quantization](), [range](), [scale](), [tensorflow](), [tensorflow-lite](), [tensors]() ### AI overview This article explains how dynamic range quantization for XNNPack's Fully Connected and Convolution 2D operators improves CPU inference performance in TensorFlow Lite. The approach quantizes weights to 8-bit integers during model conversion and dynamically quantizes activations during inference, delivering most of the performance benefits of full quantization while retaining higher overall accuracy. The article reports a fourfold performance improvement over the single-precision baseline and describes how this can enable AI-powered features on older and lower-tier devices. ### Source excerpt Posted by Alan Kelly, Software Engineer We are excited to announce that XNNPack's Fully Connected and Convolution 2D operators now support dynamic range quantization. XNNPack is TensorFlow Lite's CPU backend and CPUs deliver the widest reach for ML inference and remain the default target for TensorFlow Lite. Consequently, improving CPU inference performance is a top priority. We quadrupled inference performance in TensorFlow Lite's XNNPack backend compared to the single precision baseline by adding support for dynamic range quantization to the Fully Connected and Convolution operators. This means that more AI powered features may be deployed to older and lower tier devices. Previously, XNNPack offered users the choice between either full integer quantization, where the weights and activations are stored as signed 8-bit integers, or half-precision (fp16) or single-precision (fp32) floating-point inference. In this article we demonstrate the benefits of dynamic range quantization. Dynamic Range Quantization Dynamically quantized models are similar to fully-quantized models in that the weights for the Fully Connected and Convolution operators are quantized to 8-bit integers during model conversion. All other tensors are not quantized, they remain as float32 tensors. During model inference, the floating-point layer activations are converted to 8-bit integers before being passed to the Fully Connected and Convolution operators. The quantization parameters (the zero point and scale) for each row of the activation tensor are calculated dynamically based on the observed range of activations. This maximizes the accuracy of the quantization process as the activations make full use of the 8 quantized bits. In fully-quantized models, these parameters are fixed during model conversion, based on the range of the activation values observed using a representative dataset. The second difference between full quantization and dynamic range quantization is that the output of the Fully ## What's new in TensorFlow 2.16 DevFeed: [What's new in TensorFlow 2.16]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2024-03-13T20:11:00Z Content type: release Language: en Sources: [The TensorFlow Blog]() Topics: [TensorFlow Core](), [Keras](), [Compiler](), [LLVM](), [Windows](), [pip](), [Python](), [MSVC]() Tags: [announcement](), [compiler](), [estimator](), [keras](), [llvm](), [msvc](), [python](), [release](), [tensorflow-core](), [windows]() ### AI overview TensorFlow 2.16 introduces Clang as the default compiler for TensorFlow CPU wheels on Windows, makes Keras 3 the default Keras version, and adds Python 3.12 support. The release also removes the tf.estimator API and changes the recommended installation method for Apple Silicon. ### Source excerpt Posted by the TensorFlow team TensorFlow 2.16 has been released! Highlights of this release (and 2.15) include Clang as default compiler for building TensorFlow CPU wheels on Windows, Keras 3 as default version, support for Python 3.12, and much more! For the full release note, 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 Clang 17 Clang is now the preferred compiler to build TensorFlow CPU wheels on the Windows Platform starting with this release. The currently supported version is LLVM/clang 17. The official Wheels-published on PyPI will be based on Clang; however, users retain the option to build wheels using the MSVC compiler following the steps mentioned, as has been the case before. Intel owned the implementation and delivery of this change within the 3P Official Build program. Keras 3 Keras 3 will be the default Keras version for TensorFlow 2.16 onwards. You may need to update your script to use Keras 3. Please refer to the new Keras documentation for Keras 3 (https://keras.io/keras_3). Keras 2 will continue to be released alongside TensorFlow as tf_keras. To continue using Keras 2 with TensorFlow 2.16+: Install tf-keras vía pip install tf-keras~=2.16 Switch tf.keras to use Keras 2 (tf-keras), by setting environment variable TF_USE_LEGACY_KERAS=1 directly or in your Python program by doing import os;os.environ["TF_USE_LEGACY_KERAS"]="1". Please note that this needs to be set before importing TensorFlow and will set it for all packages in your Python runtime program. Estimator API tf.estimator API is removed. If you need to use the estimator API, you need to use TF 2.15 or an earlier version. Apple Silicon If you previously installed TensorFlow using pip install tensorflow-macos, please update your installation method. Use pip install tensorflow from now on. tensorflow-macos package will no longer receive ## Graph neural networks in TensorFlow DevFeed: [Graph neural networks in TensorFlow]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2024-02-06T19:00:00Z Content type: release Language: en Sources: [The TensorFlow Blog]() Topics: [AI, ML & Data Engineering](), [Training AI Models]() Tags: [ai](), [deep-learning](), [graph-mining](), [graphs](), [keras](), [learn](), [machine-learning](), [networks](), [python](), [release](), [release-notes](), [tensorflow](), [training]() ### AI overview Announces TensorFlow GNN 1.0, a production-tested library for building and training large-scale graph neural networks, including heterogeneous graphs. ### Source excerpt Posted by Dustin Zelle - Software Engineer, Research and Arno Eigenwillig - Software Engineer, CoreML This article is also shared on the Google Research Blog 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 -- for example: transportation networks, production networks, knowledge graphs, or social networks. Discrete mathematics and computer science have a long history of formalizing such networks them as graphs, consisting of nodes arbitrarily 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 scale. 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 and relations are represented by distinct sets of nodes and edges. Real-world objects and their relatio ## TensorFlow 2.15 update: hot-fix for Linux installation issue DevFeed: [TensorFlow 2.15 update: hot-fix for Linux installation issue]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2023-12-05T22:00:00Z Content type: release Language: en Sources: [The TensorFlow Blog]() Topics: [pip](), [Linux](), [TensorRT](), [CUDA](), [Python]() Tags: [announcement](), [dependencies](), [explore](), [installation](), [keras](), [linux](), [nvdia](), [nvidia](), [packages](), [release](), [tensorflow](), [tensorflow-core](), [tensorrt](), [update](), [x86-64]() ### AI overview TensorFlow released version 2.15.0.post1 to fix Linux x86_64 installation problems caused by missing TensorRT-related Python dependencies when installing TensorFlow 2.15 with NVIDIA CUDA dependencies via pip. The hotfix restores the intended installation behavior, while users pinning versions must specify 2.15.0.post1 explicitly. ### Source excerpt Posted by the TensorFlow team We are releasing a hot-fix for an installation issue affecting the TensorFlow installation process. The TensorFlow 2.15.0 Python package was released such that it requested tensorrt-related packages that cannot be found unless the user installs them beforehand or provides additional installation flags. This dependency affected anyone installing TensorFlow 2.15 alongside NVIDIA CUDA dependencies via pip install tensorflow[and-cuda]. Depending on the installation method, TensorFlow 2.14 would be installed instead of 2.15, or users could receive an installation error due to those missing dependencies. To solve this issue as quickly as possible, we have released TensorFlow 2.15.0.post1 for the Linux x86_64 platform. This version removes the tensorrt Python package dependencies from the tensorflow[and-cuda] installation method. Support for TensorRT is otherwise unaffected as long as TensorRT is already installed on the system. Now, pip install tensorflow[and-cuda] works as originally intended for TensorFlow 2.15. Using .post1 instead of a full minor release allowed us to push this release out quickly. However, please be aware of the following caveat: for users wishing to pin their Python dependency in a requirements file or other situation, under Python's version specification rules, tensorflow[and-cuda]==2.15.0 will not install this fixed version. Please use ==2.15.0.post1 to specify this exact version on Linux platforms, or a fuzzy version specification, such as ==2.15.*, to specify the most recent compatible version of TensorFlow 2.15 on all platforms. ## Half-precision Inference Doubles On-Device Inference Performance DevFeed: [Half-precision Inference Doubles On-Device Inference Performance]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2023-11-29T18:00:00Z Content type: release Language: en Sources: [The TensorFlow Blog]() Topics: [Inference Performance](), [On-device AI](), [LiteRT](), [cpu](), [AI, ML & Data Engineering]() Tags: [ai](), [announcement](), [benchmarks](), [cpu](), [how-to](), [inference](), [inference-performance](), [learn](), [on-device](), [tensorflow-lite]() ### AI overview TensorFlow Lite and XNNPack add generally available FP16 inference for supported ARM CPUs, reporting close to 2x speedups for floating-point models in production and benchmarked mobile and laptop environments. ### Source excerpt Posted by Marat Dukhan and Frank Barchard, Software Engineers CPUs deliver the widest reach for ML inference and remain the default target for TensorFlow Lite. Consequently, improving CPU inference performance is a top priority, and we are excited to announce that we doubled floating-point inference performance in TensorFlow Lite's XNNPack backend by enabling half-precision inference on ARM CPUs. This means that more AI powered features may be deployed to older and lower tier devices. Traditionally, TensorFlow Lite supported two kinds of numerical computations in machine learning models: a) floating-point using IEEE 754 single-precision (32-bit) format and b) quantized using low-precision integers. While single-precision floating-point numbers provide maximum flexibility and ease of use, they come at the cost of 4X overhead in storage and memory and exhibit a performance overhead compared to 8-bit integer computations. In contrast, half-precision (FP16) floating-point numbers pose an interesting alternative balancing ease-of-use and performance: the processor needs to transfer twice fewer bytes and each vector operation produces twice more elements. By virtue of this property, FP16 inference paves the way for 2X speedup for floating-point models compared to the traditional FP32 way. For a long time FP16 inference on CPUs primarily remained a research topic, as the lack of hardware support for FP16 computations limited production use-cases. However, around 2017 new mobile chipsets started to include support for native FP16 computations, and by now most mobile phones, both on the high-end and the low-end. Building upon this broad availability, we are pleased to announce the general availability for half-precision inference in TensorFlow Lite and XNNPack. Performance Improvements Half-precision inference has already been battle-tested in production across Google Assistant, Google Meet, YouTube, and ML Kit, and demonstrated close to 2X speedups across a wide range of ne ## What's new in TensorFlow 2.15 DevFeed: [What's new in TensorFlow 2.15]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2023-11-17T18:55:00Z Content type: release Language: en Sources: [The TensorFlow Blog]() Topics: [TensorFlow Core](), [CUDA](), [cpu](), [Linux](), [pip](), [Windows](), [Compiler]() Tags: [announcement](), [compiler](), [cpu](), [cuda](), [explore](), [installation](), [keras](), [linux](), [nvdia](), [performance](), [release](), [tensorflow](), [tensorflow-core](), [windows]() ### AI overview TensorFlow 2.15 introduces simpler optional installation of NVIDIA CUDA libraries through pip on Linux, provided the NVIDIA driver is already installed. It also enables oneDNN CPU optimizations by default for Windows x64 and x86 packages, adds full tf.function type support, upgrades CUDA to 12.2, and uses Clang 17 for package builds and source compilation. ### Source excerpt Posted by the TensorFlow team TensorFlow 2.15 has been released! Highlights of this release (and 2.14) include a much simpler installation method for NVIDIA CUDA libraries for Linux, oneDNN CPU performance optimizations for Windows x64 and x86, full availability of tf.function types, an upgrade to Clang 17.0.1, and much more! For the full release note, please check 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 check here. TensorFlow Core NVIDIA CUDA libraries for Linux The tensorflow pip package has a new, optional installation method for Linux that installs necessary NVIDIA CUDA libraries through pip. As long as the NVIDIA driver is already installed on the system, you may now run pip install tensorflow[and-cuda] to install TensorFlow's NVIDIA CUDA library dependencies in the Python environment. Aside from the NVIDIA driver, no other pre-existing NVIDIA CUDA packages are necessary. In TensorFlow 2.15, CUDA has been upgraded to version 12.2. oneDNN CPU performance optimizations For Windows x64 & x86 packages, oneDNN optimizations are now enabled by default on X86 CPUs. These optimizations can be enabled or disabled by setting the environment variable TF_ENABLE_ONEDNN_OPTS to 1 (enable) or 0 (disable) before running TensorFlow. To fall back to default settings, simply unset the environment variable. tf.function tf.function types are now fully available. tf.types.experimental.TraceType now allows custom tf.function inputs to declare Tensor decomposition and type casting support. Introducing tf.types.experimental.FunctionType as the comprehensive representation of the signature of tf.function callables. It can be accessed through the function_type property of tf.function's and ConcreteFunctions. See the tf.types.experimental.FunctionType documentation for more details. Introducing tf.types.experimental.AtomicFunction as the fastest way to perform TF computations in Python. ## Join us at the third Women in ML Symposium! DevFeed: [Join us at the third Women in ML Symposium!]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2023-11-17T17:00:00Z Content type: article Language: en Sources: [The TensorFlow Blog]() Topics: [AI, ML & Data Engineering](), [Google AI]() Tags: [ai](), [announcement](), [artificial-intelligence](), [community](), [event](), [explore](), [generative-ai](), [google-ai](), [machine-learning](), [women-in-ml]() ### AI overview An invitation to the third Women in Machine Learning Symposium, a virtual event covering machine learning, AI, generative AI, privacy-preserving AI, accelerators, ML frameworks, and practical applications. ### Source excerpt Posted by Sharbani Roy - Senior Director, Product Management, Google We're back with the third annual Women in Machine Learning Symposium on December 7, 2023! Join us virtually from 9:30 am to 1:00 pm PT for an immersive and insightful set of deep dives for every level of Machine Learning experience. The Women in ML Symposium is an inclusive event for anyone passionate about the transformative fields of Machine Learning (ML) and Artificial Intelligence (AI). Dive into the latest advancements in generative AI, explore the intricacies of privacy-preserving AI, dig into the underlying accelerators and ML frameworks that power models, and uncover practical applications of ML across multiple industries. Our event offers sessions for all expertise levels, from beginners to advanced practitioners. Hear about what's new in ML and building with Google AI from our keynote speakers, gain insights from seasoned industry leaders across Google Health, Nvidia, Adobe, and more - and discover a wealth of knowledge on topics ranging from foundational AI concepts to open source tools, techniques, and beyond. RSVP today to secure your spot and explore our exciting agenda. We can't wait to see you there! ## Simulated Spotify Listening Experiences for Reinforcement Learning with TensorFlow and TF-Agents DevFeed: [Simulated Spotify Listening Experiences for Reinforcement Learning with TensorFlow and TF-Agents]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2023-10-19T19:00:00Z Content type: article Language: en Sources: [The TensorFlow Blog]() Topics: [TensorFlow Agents](), [recommendation systems](), [AI, ML & Data Engineering](), [Training AI Models](), [TFX]() Tags: [ai](), [documentation](), [keras](), [learn](), [machine-learning](), [offline](), [reinforcement-learning](), [tensorflow](), [tensorflow-agents](), [tfx]() ### AI overview Spotify describes using TensorFlow and TF-Agents to build an offline simulator for reinforcement-learning-based music recommendations. The simulator supported training and evaluating recommendation models and RL agents, with offline estimates reported as strongly correlated with live experimental results. ### Source excerpt Posted by Surya Kanoria, Joseph Cauteruccio, Federico Tomasi, Kamil Ciosek, Matteo Rinaldi, and Zhenwen Dai - Spotify Introduction Many of our music recommendation problems involve providing users with ordered sets of items that satisfy users' listening preferences and intent at that point in time. We base current recommendations on previous interactions with our application and, in the abstract, are faced with a sequential decision making process as we continually recommend content to users. Reinforcement Learning (RL) is an established tool for sequential decision making that can be leveraged to solve sequential recommendation problems. We decided to explore how RL could be used to craft listening experiences for users. Before we could start training Agents, we needed to pick a RL library that allowed us to easily prototype, test, and potentially deploy our solutions. At Spotify we leverage TensorFlow and the extended TensorFlow Ecosystem (TFX, TensorFlow Serving, and so on) as part of our production Machine Learning Stack. We made the decision early on to leverage TensorFlow Agents as our RL Library of choice, knowing that integrating our experiments with our production systems would be vastly more efficient down the line. One missing bit of technology we required was an offline Spotify environment we could use to prototype, analyze, explore, and train Agents offline prior to online testing. The flexibility of the TF-Agents library, coupled with the broader advantages of TensorFlow and its ecosystem, allowed us to cleanly design a robust and extendable offline Spotify simulator. We based our simulator design on TF-Agents Environment primitives and using this simulator we developed, trained and evaluated sequential models for item recommendations, vanilla RL Agents (PPG, DQN) and a modified deep Q-Network, which we call the Action-Head DQN (AH-DQN), that addressed the specific challenges imposed by the large state and action space of our RL formulation. Through li ## 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 ## People of AI: Season 2 DevFeed: [People of AI: Season 2]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2023-10-17T17:00:00Z Content type: article Language: en Sources: [The TensorFlow Blog]() Topics: [Artificial Intelligence](), [Generative AI](), [Google](), [AI Chat](), [Development]() Tags: [ai](), [artificial-intelligence](), [generative-ai](), [google](), [industry-trends](), [podcast](), [podcasts]() ### AI overview People of AI returns for Season 2 with weekly conversations focused on Generative AI, its rapid growth, practical value, productivity, economic growth, and its impact on work. The season also continues exploring guests' career journeys, with later video podcasts planned. ### Source excerpt Posted by Ashley Oldacre If you are joining us for the first time, you can binge listen to our amazing 8 episodes from Season 1 wherever you get your podcasts. We are back for another season of People of AI with a new lineup of incredible guests! I am so excited to introduce my new co-host Luiz Gustavo Martins as we meet inspiring people with interesting stories in the field of Artificial Intelligence. Last season we focused on the incredible journeys that our guests took to get into the field of AI. Through our stories, we highlighted that no matter who you are, what your interests are, or what you work on, there is a place for anyone to get into this field. We also explored how much more accessible the technology has become over the years, as well as the importance of building AI-related products responsibly and ethically. It is easier than ever to use tools, platforms and services powered by machine learning to leverage the benefits of AI, and break down the barrier of entry. For season 2, we will feature amazing conversations, focusing on Generative AI! Specifically, we will be discussing the explosive growth of Generative AI tools and the major technology shift that has happened in recent months. We will dive into various topics to explore areas where Generative AI can contribute tremendous value, as well as boost both productivity and economic growth. We will also continue to explore the personal paths and career development of this season's guests as they share how their interest in technology was sparked, how they worked hard to get to where they are today, and explore what it is that they are currently working on. Starting today, we will release one new episode of season 2 per week. Listen to the first episode on the People of AI site or wherever you get your podcasts. And stay tuned for later in the season when we premiere our first video podcasts as well! Episode 1: meet your hosts, Ashley and Gus and learn about Generative AI, Bard and the big shift that ## Pre-processing temporal data made easier with TensorFlow Decision Forests and Temporian DevFeed: [Pre-processing temporal data made easier with TensorFlow Decision Forests and Temporian]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2023-09-11T20:14:00Z Content type: article Language: en Sources: [The TensorFlow Blog]() Topics: [Temporal data](), [Temporian](), [TensorFlow Decision Forests](), [Feature Engineering](), [Python](), [datasets]() Tags: [blog](), [data](), [dataset](), [feature-engineering](), [logs](), [machine-learning](), [python](), [sales](), [temporal-data](), [temporian](), [tensorflow-decision-forests](), [time-sequences](), [time-series](), [transactions](), [user-event]() ### AI overview This article demonstrates preprocessing temporal sales data with Temporian and forecasting weekly sales with TensorFlow Decision Forests. It explains event sets, aggregation, moving sums, indexing, and the trade-off between transactional detail and uniformly sampled time series. ### Source excerpt Posted by Google: Mathieu Guillame-Bert, Richard Stotz, Robert Crowe, Luiz GUStavo Martins (Gus), Ashley Oldacre, Kris Tonthat, Glenn Cameron, and Tryolabs: Ian Spektor, Braulio Rios, Guillermo Etchebarne, Diego Marvid, Lucas Micol, Gonzalo Marín, Alan Descoins, Agustina Pizarro, Lucía Aguilar, Martin Alcala Rubi Temporal data is omnipresent in applied machine learning applications. Data often changes over time or is only available or valuable at a certain point in time. For example, market prices and weather conditions change constantly. Temporal data is also often highly discriminative in decision-making tasks. For example, the rate of change and interval between two consecutive heartbeats provides valuable insights into a person's physical health, and temporal patterns of network logs are used to detect configuration issues and intrusions. Hence, it is essential to incorporate temporal data and temporal information in ML applications. INFO: Temporian is a new open-source Python library for preprocessing and feature engineering temporal data for machine learning applications. It is developed in collaboration between Google and Tryolabs. Check the sister blog post for more details. This blog post demonstrates how to train a forecasting model on transactional data. Specifically, we will show how to forecast the total weekly sales from individual sales records. For the modeling part, we will use TensorFlow Decision Forests as they are well suited to handle temporal data. To feed the transaction data to our model, and to compute temporal specific features, we will use Temporian, a newly released library designed for ingesting and aggregating transactional data from multiple non-synchronized sources. Time series are the most commonly used representation for temporal data. They consist of uniformly sampled values, which can be useful for representing aggregate signals. However, time series are sometimes not sufficient to represent the richness of available data. Instead ## Distributed Fast Fourier Transform in TensorFlow DevFeed: [Distributed Fast Fourier Transform in TensorFlow]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2023-08-24T17:00:00Z Content type: tutorial Language: en Sources: [The TensorFlow Blog]() Topics: [AI, ML & Data Engineering](), [GPU](), [NCCL]() Tags: [api](), [gpu](), [machine-learning](), [nccl](), [performance](), [tensorflow](), [tensorflow-core]() ### AI overview TensorFlow v2 adds native Distributed FFT support through DTensor. The article explains how sharded tensors can use existing FFT operations across multiple devices, and reports that communication and data shuffling dominate runtime in the demonstrated setup. ### Source excerpt Posted by Ruijiao Sun, Google Intern - DTensor team Fast Fourier Transform is an important method of signal processing, which is commonly used in a number of ways, including speeding up convolutions, extracting features, and regularizing models. Distributed Fast Fourier Transform (Distributed FFT) offers a way to compute Fourier Transforms in models that work with image-like datasets that are too large to fit into the memory of a single accelerator device. In a previous Google Research Paper, "Large-Scale Discrete Fourier Transform on TPUs" by Tianjian Lu, a Distributed FFT algorithm was implemented for TensorFlow v1 as a library. This work presents the newly added native support in TensorFlow v2 for Distributed FFT, through the new TensorFlow distribution API, DTensor. About DTensor DTensor is an extension to TensorFlow for synchronous distributed computing. It distributes the program and tensors through a procedure called Single program, multiple data (SPMD) extension. DTensor offers an uniform API for traditional data and model parallelism patterns used widely in Machine Learning. Example Usage The API interface for distributed FFT is the same as the original FFT in TensorFlow. Users just need to pass a sharded tensor as an input to the existing FFT ops in TensorFlow, such as tf.signal.fft2d. The output of a distributed FFT becomes sharded too. import TensorFlow as tf from TensorFlow.experimental import dtensor # Set up devices device_type = dtensor.preferred_device_type() if device_type == 'CPU': cpu = tf.config.list_physical_devices(device_type) tf.config.set_logical_device_configuration(cpu[0], [tf.config.LogicalDeviceConfiguration()] * 8) if device_type == 'GPU': gpu = tf.config.list_physical_devices(device_type) tf.config.set_logical_device_configuration(gpu[0], [tf.config.LogicalDeviceConfiguration(memory_limit=1000)] * 8) dtensor.initialize_accelerator_system() # Create a mesh mesh = dtensor.create_distributed_mesh(mesh_dims=[('x', 1), ('y', 2), ('z', 4)], ## 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 ## Simpleperf case study: Fast initialization of TFLite's Memory Arena DevFeed: [Simpleperf case study: Fast initialization of TFLite's Memory Arena]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2023-08-09T16:00:00Z Content type: tutorial Language: en Sources: [The TensorFlow Blog]() Topics: [TensorFlow Lite](), [Optimization](), [Machine learning](), [Android](), [Development](), [Code]() Tags: [adb](), [cache](), [display](), [models](), [performance](), [performance-optimization](), [profiling](), [reduce](), [tensorflow-lite](), [visualization]() ### AI overview This developer article presents a case study on optimizing TensorFlow Lite memory arena initialization. It explains how to profile an on-device machine-learning pipeline with Simpleperf, generate profile data, visualize it with pprof, and identify runtime bottlenecks such as ArenaPlanner::ExecuteAllocations. ### Source excerpt Posted by Alan Kelly, Software Engineer One of our previous articles, Optimizing TensorFlow Lite Runtime Memory, discusses how TFLite's memory arena minimizes memory usage by sharing buffers between tensors. This means we can run models on even smaller edge devices. In today's article, I will describe the performance optimization of the memory arena initialization so that our users get the benefit of low memory usage with little additional overhead. ML is normally deployed on-device as part of a larger pipeline. TFLite is used because it's fast and lightweight, but the rest of the pipeline must also be fast. Profiling on the target device with representative data lets us identify the slowest parts of the pipeline so that we can optimize the most important part of the code. In this article, I will describe the profiling and optimization of TFLite's memory arena with instructions on how to use Simpleperf and visualize the results. Sample commands are given. It is assumed that the Android NDK is installed and that you have a development device that you can connect to using adb. Simpleperf Simpleperf comes with some scripts to make it easier to use. run_simpleperf_on_device.py pushes simpleperf to the device and runs your binary with the given arguments. /usr/lib/android-ndk/simpleperf/run_simpleperf_on_device.py record -call-graph fp /data/local/tmp/my_binary arg0 arg1 ... This will generate the output file perf.data which you must then copy back to your computer. adb pull /data/local/tmp/perf.data You then generate the binary cache which contains all the information needed later to generate a useful profile. /usr/lib/android-ndk/simpleperf/binary_cache_builder.py -lib /your/binarys/folder -i perf.data And generate the proto buffer used for visualization: /usr/lib/android-ndk/simpleperf/pprof_proto_generator.py --ndk_path=/path/to/android-ndk -i perf.data -o profile.proto You can then display the results this using pprof: pprof -http :8888 profile.proto And open localhos ## What's new in TensorFlow 2.13 and Keras 2.13? DevFeed: [What's new in TensorFlow 2.13 and Keras 2.13?]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2023-07-25T16:00:00Z Content type: release Language: en Sources: [The TensorFlow Blog]() Topics: [TensorFlow Core](), [Keras](), [TensorFlow Lite](), [datasets](), [API]() Tags: [apple](), [datasets](), [google](), [keras](), [mac](), [python](), [quantization](), [release](), [tensorflow](), [tensorflow-core](), [tensorflow-lite](), [usability]() ### AI overview TensorFlow 2.13 and Keras 2.13 introduce Apple Silicon wheels, make the Keras V3 format the default for .keras files, and add improvements to TensorFlow Lite, tf.data, dataset padding, and CPU BF16 execution. ### Source excerpt Posted by the TensorFlow and Keras Teams TensorFlow 2.13 and Keras 2.13 have been released! Highlights of this release include publishing Apple Silicon wheels, the new Keras V3 format being default for .keras extension files and many more! TensorFlow Core Apple Silicon wheels for TensorFlow TensorFlow 2.13 is the first version to provide Apple Silicon wheels, which means when you install TensorFlow on an Apple Silicon Mac, you will be able to use the latest version of TensorFlow. The nightly builds for Apple Silicon wheels were released in March 2023 and this new support will enable more fine-grained testing, thanks to technical collaboration between Apple, MacStadium, and Google. tf.lite The Python TensorFlow Lite Interpreter bindings now have an option to use experimental_disable_delegate_clustering flag to turn-off delegate clustering during delegate graph partitioning phase. You can set this flag in TensorFlow Lite interpreter Python API interpreter = new Interpreter(file_of_a_tensorflowlite_model, experimental_preserve_all_tensors=False) The flag is set to False by default. This is an advanced feature in experimental that is designed for people who insert explicit control dependencies via with tf.control_dependencies() or need to change graph execution order. Besides, there are several operator improvements in TensorFlow Lite in 2.13 add operation now supports broadcasting up to 6 dimensions. This will remove explicit broadcast ops from many models. The new implementation is also much faster than the current one which calculates the entire index for both inputs the the input instead of only calculating the part that changes. Improve the coverage for 16x8 quantization by enabling int16x8 ops for exp, mirror_pad, space_to_batch_nd, batch_to_space_nd Increase the coverage of integer data types enabled int16 for less, greater_than, equal, bitcast, bitwise_xor, right_shift, top_k, mul, and int16 indices for gather and gather_nd enabled int8 for floor_div and floor_m ## On-device fetal ultrasound assessment with TensorFlow Lite DevFeed: [On-device fetal ultrasound assessment with TensorFlow Lite]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2023-06-20T16:00:00Z Content type: article Language: en Sources: [The TensorFlow Blog]() Topics: [TensorFlow Lite](), [Google](), [Artificial Intelligence](), [Inference](), [Mobile](), [Protocol (disambiguation)]() Tags: [ai](), [devices](), [google](), [health](), [healthcare](), [mobile](), [on-device](), [open-source](), [predictions](), [protocol](), [smartphones](), [tensorflow-lite]() ### AI overview This article explains how TensorFlow Lite and Google Research AI models are being used with portable, smartphone-integrated ultrasound devices to help health workers assess gestational age and fetal presentation in under-resourced settings. The models analyze ultrasound video collected through a blind sweep protocol and are intended to expand access to clinically useful prenatal screening. ### Source excerpt Posted by Angelica Willis and Akib Uddin, Health AI Team, Google Research How researchers at Google are working to expand global access to maternal healthcare with the help of AI TensorFlow Lite* is an open-source framework to run machine learning models on mobile and edge devices. It's popular for use cases ranging from image classification, object detection, speech recognition, natural language tasks, and more. From helping parents of deaf children learn sign language, to predicting air quality, projects using TensorFlow Lite are demonstrating how on-device ML could directly and positively impact lives by making these socially beneficial applications of AI more accessible, globally. In this post, we describe how TensorFlow Lite is being used to help develop ultrasound tools in under-resourced settings. Motivation According to the WHO, complications from pregnancy and childbirth contribute to roughly 287,000 maternal deaths and 2.4 million neonatal deaths worldwide each year. As many as 95% of these deaths occur in under-resourced settings and many are preventable if detected early. Obstetric diagnostics, such as determining gestational age and fetal presentation, are important indicators in planning prenatal care, monitoring the health of the birthing parent and fetus, and determining when intervention is required. Many of these factors are traditionally determined by ultrasound. Advancements in sensor technology have made ultrasound devices more affordable and portable, integrating directly with smartphones. However, ultrasound requires years of training and experience, and, in many rural or underserved regions, there is a shortage of trained ultrasonography experts, making it difficult for people to access care. Due to this global lack of availability, it has been estimated that as many as two-thirds of pregnant people in these settings do not receive ultrasound screening during pregnancy. Expanding access by enabling non-experts Google Research is building AI m ## Augmenting recommendation systems with LLMs DevFeed: [Augmenting recommendation systems with LLMs]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2023-06-06T21:00:00Z Content type: tutorial Language: en Sources: [The TensorFlow Blog]() Topics: [Language models](), [AI Chat]() Tags: [large-language-models](), [llm](), [llms](), [palm-api](), [recommendation-systems](), [tensorflow](), [tensorflow-recommenders]() ### AI overview A practical tutorial on using LLMs and the PaLM API to add conversational and sequential recommendation capabilities to retrieval-ranking recommendation systems. ### Source excerpt Posted by Wei Wei, Developer Advocate Large language models (LLMs) are taking the world by storm, thanks to their powerful ability to generate text, translate languages, and answer questions in a coherent and informative way. At Google I/O 2023, we released the PaLM API as 'public preview' so that many developers can start building apps with it. While PaLM API already has excellent documentation on its extensive usage and best practices, in this blog we are going to take a more focused approach to explore how to leverage LLMs to augment your ML systems in a practical application: recommendation systems. As a refresher, modern recommendation systems often follow a retrieval-ranking architecture, which enables them to effectively and efficiently filter and rank relevant items to maximize the utility in production. You can go through this codelab to learn about building a fullstack movie recommendation system using TensorFlow and Flutter. We will discuss how LLMs can be incorporated into this retrieval-ranking pipeline. Conversational recommendations If you already have access to Bard, you can ask it to create recommendations for you interactively in a dialogue. Here is an example of asking Bard for movie recommendations: As a developer, you can build a similar functionality in your own applications, using the PaLM API Chat service with minimal effort: prompt = """You are a movie recommender and your job is to recommend new movies based on user input. So for user 42, he is in the mood for some drama movies with artistic elements tonight. Could you recommend three? Output the titles only. Do not include other text.""" response = palm.chat(messages=prompt) print(response.last) # Sure, here are three drama movies with artistic elements that I recommend for user 42: # # 1. The Tree of Life (2011) # 2. 20th Century Women (2016) # 3. The Florida Project (2017) # # I hope you enjoy these movies! The PaLM API also allows you to help your user continue the exploration and inter ## Visualizing and interpreting decision trees DevFeed: [Visualizing and interpreting decision trees]() Original publisher: [Read original article]() Author: TensorFlow Blog (noreply@blogger.com) Published: 2023-06-06T17:00:00Z Content type: tutorial Language: en Sources: [The TensorFlow Blog]() Topics: [Machine Learning & Artificial Intelligence](), [Model Development](), [Google]() Tags: [article](), [google](), [how-to](), [learn](), [learning](), [machine-learning](), [model](), [predictions](), [tensorflow](), [tensorflow-decision-forests](), [training](), [visualization]() ### AI overview A tutorial on visualizing and interpreting decision trees with the dtreeviz library and TensorFlow Decision Forests. It explains how decision trees use feature-based splits and leaf nodes to make regression or classification predictions, then demonstrates how visualization can clarify those predictions and the distribution of training instances. ### Source excerpt Posted by Terence Parr, Google Decision trees are the fundamental building block of Gradient Boosted Trees and Random Forests, the two most popular machine learning models for tabular data. To learn how decision trees work and how to interpret your models, visualization is essential. TensorFlow recently published a new tutorial that shows how to use dtreeviz, a state-of-the-art visualization library, to visualize and interpret TensorFlow Decision Forest Trees. The dtreeviz library, first released in 2018, is now the most popular visualization library for decision trees. The library is constantly being updated and improved, and there is a large community of users who can provide support and answer questions. There is a helpful YouTube video and article on the design of dtreeviz. Let's demonstrate how to use dtreeviz to interpret decision tree predictions. At a basic level, a decision tree is a machine learning model that learns the relationship between observations and target values by examining and condensing training data into a binary tree. Each leaf in the decision tree is responsible for making a specific prediction. For regression trees, the prediction is a value, such as price. For classifier trees, the prediction is a target category, such as cancer or not-cancer. Any path from the root of the decision tree to a specific leaf predictor passes through a series of (internal) decision nodes. Each decision node compares a single feature's value with a specific split point value learned during training. Making a prediction means walking from the root down the tree, comparing feature values, until we reach a leaf. Consider the following simple decision tree that tries to classify animals based upon two features, the number of legs and the number of eyes. Let's say that our test animal has four legs and two eyes. To classify the test animal, we start at the root of the tree and compare our test animal's number of legs to four. Since the number of legs is equal to fo [Next page]()