NumPy

An open-source Python library on which most numerical computing in that language rests. Its core is the ndarray, an n-dimensional array whose elements share one data type and sit in a single memory buffer, manipulated by vectorized operations compiled in C: elementwise arithmetic, broadcasting between arrays of different shapes, indexing and slicing and reductions, with submodules for linear algebra, Fourier transforms and random numbers. Expressing computations as whole-array operations instead of Python loops gives large speedups and a concise mathematical style. NumPy's array model underlies scientific Python — SciPy, pandas, scikit-learnscikit-learn, prop. n.: A free, widely taught Python library of classic machine-learning methods — such as decision trees, regression and clustering — that all work in the same simple way., Matplotlib — and deep-learning libraries imitate it: PyTorchPyTorch, prop. n.: The most widely used free software toolkit for building and training neural networks, especially in research; programmers write ordinary Python and it handles the calculus and the graphics chips. tensors, JAXJAX, prop. n.: A free Google library that lets researchers write mathematics in familiar Python and automatically get derivatives and very fast code for graphics chips and Google's AI chips.'s jax.numpy and the GPU library CuPy follow its indexing and broadcasting conventions, and the Python array API standard formalizes their shared core. NumPy itself runs on CPUs only and has no automatic differentiationautomatic differentiation, n.: A technique that lets a computer work out exactly how a program's output would change if its inputs changed slightly, by tracking every arithmetic step. It lets AI software compute training updates automatically., which is what deep-learning frameworks add.

Convert the predictions to a NumPy array and compute the confusion matrix with one vectorized call.