TensorFlow (Google), PyTorch (Facebook), Keras (Open)
TensorFlow is one of the most popular deep learning Frameworks. Built by Google. Low level, so full control over the neural network, training, parameters, computations. Great if you’re an ML researcher building novel models.
Keras is a higher level API that uses lower level frameworks like TensorFlow. Can build simple and very complex models quickly. Great to take an existing paper or existing concept and create a model from that.
https://medium.com/implodinggradients/tensorflow-or-keras-which-one-should-i-learn-5dd7fa3f9ca0
https://towardsdatascience.com/battle-of-the-deep-learning-frameworks-part-i-cff0e3841750
Or scikit-learn, for machine learning and data scientists. Very easily solve problems like classification, regression, clustering etc using all sorts of built-in algorithms (SVM, nearest neighbor, k-means, PCA, etc)
TensorFlow vs PyTorch: "Tensorflow is much better for production models and scalability. It was built to be production ready. Whereas, PyTorch is easier to learn and lighter to work with, and hence, is relatively better for passion projects and building rapid prototypes.“