Inference code for Llama models

An alternative to convolution in neural networks

Prevent PyTorch's `CUDA error: out of memory` in just 1 line of code.

ARMORY Adversarial Robustness Evaluation Test Bed

This repository contains an extension of fairseq for pixel / visual representations for machine translation.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Evaluation Pipeline for our ECCV2020: Journey Towards Tiny Perceptual Super-Resolution.

Side Channels Analysis and Deep Learning

My project skeleton for various other projects in machine learning

NASBench: A Neural Architecture Search Dataset and Benchmark

Code for the Million Song Dataset, the dataset contains metadata and audio analysis for a million tracks, a collaboration between The Echo Nest and LabROSA. See website for details.

The PyTorch implement of the paper "Super-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs"

A PyTorch reimplementation for paper Generative Image Inpainting with Contextual Attention (https://arxiv.org/abs/1801.07892)

Code for paper "StructureFlow: Image Inpainting via Structure-aware Appearance Flow"

Official implementation of "Global and local attention-based free-form image inpainting"

Ultrasound communication between Android phones

Image Fine-grained Inpainting (Winner Award of ECCVW AIM 2020 Extreme Inpainting Track1&Track2)

3D point cloud datasets in HDF5 format, containing uniformly sampled 2048 points per shape.

Upscale an image by a factor of 4, while generating photo-realistic details.

Coherent Semantic Attention for image inpainting(ICCV 2019)

Flops counter for convolutional networks in pytorch framework

Pytorch implementation of Shift-Net: Image Inpainting via Deep Feature Rearrangement (ECCV, 2018)

End-to-End Object Detection with Transformers

High-Resolution 3D Human Digitization from A Single Image.

[ICLR 2020] A repository for extremely fast adversarial training using FGSM

An open source library for interacting with and processing radar data, specialized for MIMO mmWave radars

Ersin

Mayo: Auto-generation of hardware-friendly deep neural networks. Dynamic Channel Pruning: Feature Boosting and Suppression.