Abstract
The article is an overview. We carry out the comparison of actual machine learning libraries that can be used the neural networks development. The first part of the article gives a brief description of TensorFlow, PyTorch, Theano, Keras, SciKit Learn libraries, SciPy library stack. An overview of the scope of these libraries and the main technical characteristics, such as performance, supported programming languages, the current state of development is given. In the second part of the article, a comparison of five libraries is carried out on the example of a multilayer perceptron, which is applied to the problem of handwritten digits recognizing. This problem is well known and well suited for testing different types of neural networks. The study time is compared depending on the number of epochs and the accuracy of the classifier. The results of the comparison are presented in the form of graphs of training time and accuracy depending on the number of epochs and in tabular form.
Highlights
Due to the vast development of machine learning and data science, it is not possible to review the diversity of available software solutions
The PyTorch [11] library was created on the basis of Torch [12]
The developers of PyTorch emphasize that Python is tightly integrated into the library
Summary
Due to the vast development of machine learning and data science, it is not possible to review the diversity of available software solutions. NumPy implements variety of linear algebra methods for working with vectors, matrices and tensors (multidimensional arrays in this case) It supports parallel computing by utilizing vector capabilities of modern CPUs. — Pandas [8] is the library designed to work with time series and table data (DataFrame data structure) It is written almost entirely in pure Python using NumPy arrays and is often used in machine learning to organize training and test samples. In addition to these three main libraries, the scientific Python stack includes Matplotlib [3] for data visualization and plotting, and a set of interactive shells, such as iPython and Jupyter [2]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have