OneRaynyDay / autodiff
Symbolic differentiation engine for optimization-based machine learning models.
☆42Updated 7 years ago
Alternatives and similar repositories for autodiff:
Users that are interested in autodiff are comparing it to the libraries listed below
- Direct C++ Interface to PyTorch☆80Updated 6 years ago
- Deep neural network framework (C/C++/CUDA).☆31Updated 9 years ago
- OpenCL Inference Engine for pytorch☆51Updated 7 years ago
- MXNet Model Serving☆25Updated 7 years ago
- Lightweight C++11 library for building deep recurrent neural networks☆41Updated 7 years ago
- Sublinear memory optimization for deep learning, reduce GPU memory cost to train deeper nets☆28Updated 8 years ago
- This project is a simple deep neural network trained using only TensorFlow C++.☆118Updated last year
- Matrix Shadow:Lightweight CPU/GPU Matrix and Tensor Template Library in C++/CUDA for (Deep) Machine Learning☆33Updated 8 years ago
- ArrayFire's Machine Learning Library.☆103Updated 6 years ago
- This demo shows how to learn a neural network on top of decision trees☆32Updated 7 years ago
- The "CUDA templates" are a collection of C++ template classes and functions which provide a consistent interface to NVIDIA's "Compute Uni…☆27Updated 13 years ago
- Simple example of implementing a new Tensorflow operation and its gradient in C++.☆56Updated 5 years ago
- Workshop on the future of gradient-based machine learning software, NIPS 2017, 2016☆15Updated 7 years ago
- GPU/CPU (CUDA) Implementation of "Recurrent Memory Array Structures", Simple RNN, LSTM, Array LSTM..☆25Updated 4 years ago
- Slides and code for my talk at MeetingC++ 2017☆48Updated 7 years ago
- ☆30Updated 7 years ago
- ☆16Updated 7 years ago
- The SimNets Architecture's Implementation in Caffe☆13Updated 8 years ago
- Implementing (parts of) TensorFlow (almost) from Scratch☆30Updated 7 years ago
- Python Binding to NVRTC☆79Updated 4 months ago
- Simple MXNet sequence-to-sequence model (neural machine translation)☆24Updated 7 years ago
- Minimal Deep Learning library is written in Python/Cython/C++ and Numpy/CUDA/cuDNN.☆102Updated 6 years ago
- Demos interesting image-in, image-out networks running on both NVIDIA and AMD GPUs, with NNVM☆49Updated 7 years ago
- a C++ wrapper of Caffe and mxnet to make predictions☆50Updated 6 years ago
- Fast binary matrix product on CPU☆10Updated 9 years ago
- Torch FFI-bindings for NNPACK☆30Updated 7 years ago
- (Spring 2017) Assignment 2: GPU Executor☆63Updated 7 years ago
- A very simple variant of adversarial training that yields excellent results on MNIST☆12Updated 8 years ago
- MXNet implementation of Deep Q-learning☆34Updated 7 years ago
- PyTorch Framework Integration for Tensor Comprehensions☆14Updated 6 years ago