PAN Blend machine-learning packages

Keras is a Python library for machine learning based on deep (multi- layered) artificial neural networks (DNN), which follows a minimalistic and modular design with a focus on fast experimentation.

Features of DNNs like neural layers, cost functions, optimizers, initialization schemes, activation functions and regularization schemes are available in Keras a standalone modules which can be plugged together as wanted to create sequence models or more complex architectures. Keras supports convolutions neural networks (CNN, used for image recognition resp. classification) and recurrent neural networks (RNN, suitable for sequence analysis like in natural language processing).

It runs as an abstraction layer on the top of Theano (math expression compiler) by default, which makes it possible to accelerate the computations by using (GP)GPU devices. Alternatively, Keras could run on Google's TensorFlow (not yet available in Debian).

This package contains the documentation for Keras.

Questo pacchetto contiene i file header e la libreria statica necessari per compilare con il modulo per reti neurali profonde.

La libreria Open Computer Vision è una raccolta di algoritmi e codice d'esempio per vari problemi relativi alla visione artificiale. La libreria è compatibile con IPL (Image Processing Library di Intel) e, se disponibile, può usare IPP (Integrated Performance Primitives di Intel) per ottenere prestazioni migliori.

OpenCV fornisce tipi di dati e operatori portabili di basso livello e un insieme di funzionalità di alto livello per l'acquisizione video, l'elaborazione e l'analisi di immagini, analisi strutturale, analisi del movimento e inseguimento di oggetti, riconoscimento di oggetti, calibrazione di videocamere e ricostruzione 3D.

Questo pacchetto contiene il modulo per reti neurali profonde di OpenCV (Open Computer Vision).

La libreria Open Computer Vision è una raccolta di algoritmi e codice d'esempio per vari problemi relativi alla visione artificiale. La libreria è compatibile con IPL (Image Processing Library di Intel) e, se disponibile, può usare IPP (Integrated Performance Primitives di Intel) per ottenere prestazioni migliori.

OpenCV fornisce tipi di dati e operatori portabili di basso livello e un insieme di funzionalità di alto livello per l'acquisizione video, l'elaborazione e l'analisi di immagini, analisi strutturale, analisi del movimento e inseguimento di oggetti, riconoscimento di oggetti, calibrazione di videocamere e ricostruzione 3D.

PyTorch is a Python package that provides two high-level features:

(1) Tensor computation (like NumPy) with strong GPU acceleration (2) Deep neural networks built on a tape-based autograd system

You can reuse your favorite Python packages such as NumPy, SciPy and Cython to extend PyTorch when needed.

This is the CPU-only version of PyTorch (Test Binaries).

This package provides an easy and modular way to build and train simple or complex neural networks using Torch Framework.

This package contains libTHNN.so , backend library for lua-torch-nn.

Consider TPOT your Data Science Assistant. TPOT is a Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.

TPOT will automate the most tedious part of machine learning by intelligently exploring thousands of possible pipelines to find the best one for your data.

Once TPOT is finished searching (or you get tired of waiting), it provides you with the Python code for the best pipeline it found so you can tinker with the pipeline from there.

TPOT is built on top of scikit-learn, so all of the code it generates should look familiar... if you're familiar with scikit-learn, anyway.

This package contains the documentation, example scripts, and tutorials for TPOT.

Brian è un simulatore per reti neurali spiking guidato dal tempo. È progettato con un'enfasi su flessibilità ed estensibilità, per lo sviluppo rapido e l'affinamento di modelli neurali. I modelli dei neuroni sono specificati dall'utente con insiemi di equazioni differenziali, condizioni di soglia e condizioni di ripristino (date come stringhe). L'attenzione è principalmente su reti di modelli di neuroni a compartimento singolo (es. neuroni di tipo Hodgkin-Huxley o integra-e-spara con perdita). Le funzionalità includono:

• un sistema per specificare quantità con dimensioni fisiche;
• integrazione numerica esatta per equazioni differenziali lineari;
• integrazione di Eulero, Runge-Kutta ed esponenziale di Eulero per equazioni differenziali non lineari;
• connessioni sinaptiche con ritardi;
• plasticità a breve termine e a lungo termine (plasticità dipendente dalla tempistica degli spike);
• una libreria di componenti modello standard che include equazioni integra-e-spara, sinapsi e correnti ioniche;
• strumenti per fare automaticamente il fitting di modelli di neuroni spiking su registrazioni elettrofisiologiche.

EagerPy è una infrastruttura Python che consente di scrivere codice che funziona nativamente in maniera automatica con PyTorch, TensorFlow, JAX e NumPy.

Keras is a Python library for machine learning based on deep (multi- layered) artificial neural networks (DNN), which follows a minimalistic and modular design with a focus on fast experimentation.

Features of DNNs like neural layers, cost functions, optimizers, initialization schemes, activation functions and regularization schemes are available in Keras a standalone modules which can be plugged together as wanted to create sequence models or more complex architectures. Keras supports convolutions neural networks (CNN, used for image recognition resp. classification) and recurrent neural networks (RNN, suitable for sequence analysis like in natural language processing).

It runs as an abstraction layer on the top of Theano (math expression compiler) by default, which makes it possible to accelerate the computations by using (GP)GPU devices. Alternatively, Keras could run on Google's TensorFlow (not yet available in Debian).

Keras is a Python library for machine learning based on deep (multi- layered) artificial neural networks (DNN), which follows a minimalistic and modular design with a focus on fast experimentation.

Features of DNNs like neural layers, cost functions, optimizers, initialization schemes, activation functions and regularization schemes are available in Keras a standalone modules which can be plugged together as wanted to create sequence models or more complex architectures. Keras supports convolutions neural networks (CNN, used for image recognition resp. classification) and recurrent neural networks (RNN, suitable for sequence analysis like in natural language processing).

It runs as an abstraction layer on the top of Theano (math expression compiler) by default, which makes it possible to accelerate the computations by using (GP)GPU devices. Alternatively, Keras could run on Google's TensorFlow (not yet available in Debian).

Keras Applications is the applications module of the Keras deep learning library. It provides model definitions and pre-trained weights for a number of popular architectures, such as VGG16, ResNet50, Xception, MobileNet, and more.

Keras is a Python library for machine learning based on deep (multi- layered) artificial neural networks (DNN), which follows a minimalistic and modular design with a focus on fast experimentation.

Features of DNNs like neural layers, cost functions, optimizers, initialization schemes, activation functions and regularization schemes are available in Keras a standalone modules which can be plugged together as wanted to create sequence models or more complex architectures. Keras supports convolutions neural networks (CNN, used for image recognition resp. classification) and recurrent neural networks (RNN, suitable for sequence analysis like in natural language processing).

It runs as an abstraction layer on the top of Theano (math expression compiler) by default, which makes it possible to accelerate the computations by using (GP)GPU devices. Alternatively, Keras could run on Google's TensorFlow (not yet available in Debian).

Keras Preprocessing is the data preprocessing and data augmentation module of the Keras deep learning library. It provides utilities for working with image data, text data, and sequence data.

Lasagne è una libreria Python per costruire e addestrare reti neurali artificiali profonde (multi-livello) sopra a Theano (compilatore di espressioni matematiche). In confronto ad altri livelli di astrazione come ad esempio Keras, astrae Theano il meno possibile.

Lasagne gestisce reti come Convolutional Neural Network (CNN, usate principalmente per il riconoscimento di immagini per classificarle) e il tipo Long Short-Term Memory (LSTM, un sottotipo di Recurrent Neural Network, RNN).

Questo pacchetto contiene i moduli per Python 3.

Infrastruttura Python per elaborazione di dati per creare software per complesse elaborazioni di dati combinando in pipe e reti algoritmi largamente usati di apprendimento macchina. Gli algoritmi implementati includono: PCA (Principal Component Analysis), ICA (Independent Component Analysis), SFA (Slow Feature Analysis), ISFA (Independent Slow Feature Analysis), GNG (Growing Neural Gas), analisi fattoriale, FDA (Fisher Discriminant Analysis) e classificatori gaussiani.

Open Neural Network Exchange (ONNX) is the first step toward an open ecosystem that empowers AI developers to choose the right tools as their project evolves. ONNX provides an open source format for AI models. It defines an extensible computation graph model, as well as definitions of built-in operators and standard data types. Initially onnx focuses on the capabilities needed for inferencing (evaluation).

Caffe2, PyTorch, Microsoft Cognitive Toolkit, Apache MXNet and other tools are developing ONNX support. Enabling interoperability between different frameworks and streamlining the path from research to production will increase the speed of innovation in the AI community.

This package contains the python interface.

Questa libreria fornisce strumenti per algoritmi per cluster, reti oscillatorie e reti neurali.

Questo pacchetto installa la libreria per Python 3.

scikit-learn è una raccolta di moduli Python relativi ad apprendimento automatico/statistico e data mining. Una lista non esaustiva di funzionalità incluse:

• modelli misti gaussiani,
• apprendimento tramite varietà,
• kNN,
• SVM (tramite LIBSVM).

Questo pacchetto contiene la versione per Python 3.

The goal of skorch is to make it possible to use PyTorch with sklearn. This is achieved by providing a wrapper around PyTorch that has an sklearn interface. In that sense, skorch is the spiritual successor to nolearn, but instead of using Lasagne and Theano, it uses PyTorch.

skorch does not re-invent the wheel, instead getting as much out of your way as possible. If you are familiar with sklearn and PyTorch, you don’t have to learn any new concepts, and the syntax should be well known. (If you’re not familiar with those libraries, it is worth getting familiarized.)

Additionally, skorch abstracts away the training loop, making a lot of boilerplate code obsolete. A simple net.fit(X, y) is enough. Out of the box, skorch works with many types of data, be it PyTorch Tensors, NumPy arrays, Python dicts, and so on. However, if you have other data, extending skorch is easy to allow for that.

Overall, skorch aims at being as flexible as PyTorch while having a clean interface as sklearn.

PyTorch is a Python package that provides two high-level features:

(1) Tensor computation (like NumPy) with strong GPU acceleration (2) Deep neural networks built on a tape-based autograd system

You can reuse your favorite Python packages such as NumPy, SciPy and Cython to extend PyTorch when needed.

This is the CPU-only version of PyTorch (Python interface).

Ignite is a high-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

Features

• Less code than pure PyTorch while ensuring maximum control and simplicity
• Library approach and no program's control inversion
• Extensible API for metrics, experiment managers, and other components

Consider TPOT your Data Science Assistant. TPOT is a Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.

TPOT will automate the most tedious part of machine learning by intelligently exploring thousands of possible pipelines to find the best one for your data.

Once TPOT is finished searching (or you get tired of waiting), it provides you with the Python code for the best pipeline it found so you can tinker with the pipeline from there.

TPOT is built on top of scikit-learn, so all of the code it generates should look familiar... if you're familiar with scikit-learn, anyway.

This package contains the Python 3.x version of TPOT.

PyTorch is a Python package that provides two high-level features:

(1) Tensor computation (like NumPy) with strong GPU acceleration (2) Deep neural networks built on a tape-based autograd system

You can reuse your favorite Python packages such as NumPy, SciPy and Cython to extend PyTorch when needed.

This is the CUDA version of PyTorch (Python interface).