Image, GIF and Video enlarger/upscaler(super-resolution) achieved with Waifu2x, SRMD, RealSR, Anime4K and ACNet.
-
Updated
Jul 8, 2020 - C++
Image, GIF and Video enlarger/upscaler(super-resolution) achieved with Waifu2x, SRMD, RealSR, Anime4K and ACNet.
Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP
Face recognition system for ID photos
Code for training py-faster-rcnn and py-R-FCN on multiple GPUs in caffe
Describe building QUDA with cmake, getting cmake if not available and currently available options in cmake.
Particularly MPI detection.
Multi-device OpenCL kernel load balancer and pipeliner API for C#. Uses shared-distributed memory model to keep GPUs updated fast while using same kernel on all devices(for simplicity).
A PyTorch implementation of Google's FaceNet [1] paper for training a facial recognition model with Triplet Loss and an implementation of the Shenzhen Institutes of Advanced Technology's 'Center Loss' [2] combined with Cross Entropy Loss using the VGGFace2 dataset. A pre-trained model using Triplet Loss is available for download.
Neutron: A pytorch based implementation of Transformer and its variants.
Co-attending Regions and Detections for VQA.
Deep Learning Toolbox for Torch
GPU Framework for Radio Astronomical Image Synthesis
Deep Neural Network Compression based on Student-Teacher Network
MelGAN Multi GPU Implementation.
Extract features from raw videos using multiple GPUs in parallel
A CUDA-based multi-GPU vertex-centric graph processing framework based on Warp Segmentation and Vertex Refinement techniques.
Densenet, based on the code at "https://github.com/LaurentMazare/deep-models/tree/master/densenet", using tfrecords format data and either single cpu or multiple gpus if possible.
Utilities for making TensorFlow easier
image retrieval with cosine metric learning
Almost trivial distributed parallelization of stencil-based GPU and CPU applications on a regular staggered grid
Experimental utility to build stateful RNN models for multi GPU training.
This project aims to help people implement tensorflow model pipelines quickly for different nlp tasks.
Frustum PointNets for 3D Object Detection from RGB-D Data
Graphic Techniques Implemented on The Forge API, a cross-platform rendering framework on top of Vulkan, DirectX, Metal
running multiple darknet models in parallel in multi-gpu setup
Multi-GPU version of BERT, implemented with Tensorflow 1.9
Measure bandwidth of multiple simultaneously started cudaMemcpyAsync
Add a description, image, and links to the multi-gpu topic page so that developers can more easily learn about it.
To associate your repository with the multi-gpu topic, visit your repo's landing page and select "manage topics."
The Forge sounds pretty great but there does not seem to be much in the way of documentation.
I don't even see simple "How to compile" or build instructions. Which seems like a good place to start.
The description talks about it being like "Legos" where you can use the different parts of the system as needed. So does that mean it can be built in sections and integrated into other projects pi