Tensors and Dynamic neural networks in Python with strong GPU acceleration

Tensorflow model that classifies dogs by breed.

Convolution of a tensor using any filter - Python

Github repository of VerHem project source tree. A tensor-valued (up to 18 components) solving, post-processing and visualization parallel suite for 3D GL equations and complex geometries with adaptive mesh.

SymProp is a C++ software tool for computing the Tucker decomposition of high-order sparse symmetric tensors.

Fill an input ndarray with a specified value.

Repository for ML study

Generic header-only tensor library, intended be use as a middle layer between GPU and CPU devices in heterogeneous applications.

Why build ML models when you can just build ML framework and build your models on top of it? PyTorch (from scratch) but for GigaChads, GigaTorch.

This Deep Learning Model Predicts that from which disease you are suffering.

A Python app using SymPy to compute core differential geometry tensors (metric, Christoffel, Riemann, Ricci, Einstein, and Weyl). It features a custom simplification module that combines built‑in methods with regex-based replacements to reduce expressions and auto-nullifies Weyl components when FLRW patterns are detected.

Alien Ship Invasion.

Economic analysis tool using tensor PCA modeling to interpolate GNP values, integrating tensor product, PCA, and linear regression for better interpolation.

Personal Project: Computer Vision

Sample to show how input dim(input_dim for FC layer, for CNN, it's prod(tensor.shape[1:])) reciprocal could be used for initialize NN weights rather than sqrt(input_dim_reciprocal) hinted by Xavier:dragon:

Benchmark for basic operations of torch.tensor

Contract programming for Pytorch, Numpy

Python deep learning library focused on transparency and readability