PENGERTIAN
TensorFlow is a free and open-source software library for machine learning and artificial intelligence. It can be used across a range of tasks but has a particular focus on training and inference of deep neural networks.[5][6] TensorFlow was developed by the Google Brain team for internal Google use in research and production.[7][8][9] The initial version was released under the Apache License 2.0 in 2015.[1][10] Google released the updated version of TensorFlow, named TensorFlow 2.0, in September 2019.[11]
TensorFlow can be used in a wide variety of programming languages, including Python, JavaScript, C++, and Java.[12] This flexibility lends itself to a range of applications in many different sectors.
DATAFRAME
TensorFlow
TensorFlow serves as the core platform and library for machine learning. TensorFlow’s APIs use Keras to allow users to make their own machine learning models.[42] In addition to building and training their model, TensorFlow can also help load the data to train the model, and deploy it using TensorFlow Serving.[43]
TensorFlow provides a stable Python API,[44] as well as APIs without backwards compatibility guarantee for Javascript,[45] C++,[46] and Java.[47][12] Third-party language binding packages are also available for C#,[48][49] Haskell,[50] Julia,[51] MATLAB,[52] R,[53] Scala,[54] Rust,[55] OCaml,[56] and Crystal.[57] Bindings that are now archived and unsupported include Go[58] and Swift.[59]
TensorFlow.js
TensorFlow also has a library for machine learning in JavaScript. Using the provided JavaScript APIs, TensorFlow.js allows users to use either Tensorflow.js models or converted models from TensorFlow or TFLite, retrain the given models, and run on the web.[43][60]
TFLite
TensorFlow Lite has APIs for mobile apps or embedded devices to generate and deploy TensorFlow models.[61] These models are compressed and optimized in order to be more efficient and have a higher performance on smaller capacity devices.[62]
TensorFlow Lite uses FlatBuffers as the data serialization format for network models, eschewing the Protocol Buffers format used by standard TensorFlow models.[62]
TFX
TensorFlow Extended (abbrev. TFX) provides numerous components to perform all the operations needed for end-to-end production.[63] Components include loading, validating, and transforming data, tuning, training, and evaluating the machine learning model, and pushing the model itself into production.[43][63]
Integrations
Numpy
Numpy is one of the most popular Python data libraries, and TensorFlow offers integration and compatibility with its data structures.[64] Numpy NDarrays, the library’s native datatype, are automatically converted to TensorFlow Tensors in TF operations; the same is also true vice versa.[64] This allows for the two libraries to work in unison without requiring the user to write explicit data conversions. Moreover, the integration extends to memory optimization by having TF Tensors share the underlying memory representations of Numpy NDarrays whenever possible.[64]
Extensions
TensorFlow also offers a variety of libraries and extensions to advance and extend the models and methods used.[65] For example, TensorFlow Recommenders and TensorFlow Graphics are libraries for their respective functionalities in recommendation systems and graphics, TensorFlow Federated provides a framework for decentralized data, and TensorFlow Cloud allows users to directly interact with Google Cloud to integrate their local code to Google Cloud.[66] Other add-ons, libraries, and frameworks include TensorFlow Model Optimization, TensorFlow Probability, TensorFlow Quantum, and TensorFlow Decision Forests.[65][66]
Google Colab
Google also released Colaboratory, a TensorFlow Jupyter notebook environment that does not require any setup.[67] It runs on Google Cloud and allows users free access to GPUs and the ability to store and share notebooks on Google Drive.[68]
Google JAX
Google JAX is a machine learning framework for transforming numerical functions.[69][70][71] It is described as bringing together a modified version of autograd (automatic obtaining of the gradient function through differentiation of a function) and TensorFlow’s XLA (Accelerated Linear Algebra). It is designed to follow the structure and workflow of NumPy as closely as possible and works with TensorFlow as well as other frameworks such as PyTorch. The primary functions of JAX are:[69]
- grad: automatic differentiation
- jit: compilation
- vmap: auto-vectorization
- pmap: SPMD programming
FITUR
AutoDifferentiation
AutoDifferentiation is the process of automatically calculating the gradient vector of a model with respect to each of its parameters. With this feature, TensorFlow can automatically compute the gradients for the parameters in a model, which is useful to algorithms such as backpropagation which require gradients to optimize performance.[33] To do so, the framework must keep track of the order of operations done to the input Tensors in a model, and then compute the gradients with respect to the appropriate parameters.[33]
Eager execution
TensorFlow includes an “eager execution” mode, which means that operations are evaluated immediately as opposed to being added to a computational graph which is executed later.[34] Code executed eagerly can be examined step-by step-through a debugger, since data is augmented at each line of code rather than later in a computational graph.[34] This execution paradigm is considered to be easier to debug because of its step by step transparency.[34]
Distribute
In both eager and graph executions, TensorFlow provides an API for distributing computation across multiple devices with various distribution strategies.[35] This distributed computing can often speed up the execution of training and evaluating of TensorFlow models and is a common practice in the field of AI.[35][36]
Losses
To train and assess models, TensorFlow provides a set of loss functions (also known as cost functions).[37] Some popular examples include mean squared error (MSE) and binary cross entropy (BCE).[37] These loss functions compute the “error” or “difference” between a model’s output and the expected output (more broadly, the difference between two tensors). For different datasets and models, different losses are used to prioritize certain aspects of performance.
Metrics
In order to assess the performance of machine learning models, TensorFlow gives API access to commonly used metrics. Examples include various accuracy metrics (binary, categorical, sparse categorical) along with other metrics such as Precision, Recall, and Intersection-over-Union (IoU).[38]
TF.nn
TensorFlow.nn is a module for executing primitive neural network operations on models.[39] Some of these operations include variations of convolutions (1/2/3D, Atrous, depthwise), activation functions (Softmax, RELU, GELU, Sigmoid, etc.) and their variations, and other Tensor operations (max-pooling, bias-add, etc.).[39]
Optimizers
TensorFlow offers a set of optimizers for training neural networks, including ADAM, ADAGRAD, and Stochastic Gradient Descent (SGD).[40] When training a model, different optimizers offer different modes of parameter tuning, often affecting a model’s convergence and performance.[41]
LAYANAN
Layanan kami diperuntukan bagi yang ingin mendapatkan manfaat dari programming language tanpa ribet.
- Mulai dari program,
- Aplikasi,
- Tugas,
- Data science,
- Web app yang kompleks,
- dan lain-lain semua dalam satu layanan.
LANGKAH PENGERJAAN PROJECT
- Diskusi pekerjaan
- Diskusi Harga
- Order
- Pekerjaan dalam proses
- Review hasil
- Selesai
Reviews
There are no reviews yet.