Fartash Faghri

vsepp. PyTorch Code for the paper "VSE++: Improving Visual-Semantic Embeddings with Hard Negatives"

under_convnet. Caffe code for the paper "Adversarial Manipulation of Deep Representations"

gvar_code. Code for the paper "A Study of Gradient Variance in Deep Learning" and a number of other ideas.

nuqsgd. PyTorch Code for the paper "NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization"

robust_bias. JAX code for paper "Bridging the Gap Between Adversarial Robustness and Optimization Bias"

hog.torch. A Cuda implementation of Histogram of Oriented Gradients (HOG) for Torch

boost_numpy_wrapper. Examples of wrapping C++ code for Python with NumPy support

google-research. Google Research

cuimage.torch. A Cuda implementation of some functions in the image package

tensorboard-pytorch. tensorboard for pytorch (and chainer, mxnet, numpy, ...)

foptim. Benchmark Framework for Mini-batch Optimization Methods