CubertFast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL
Stars: ✭ 395 (-21.16%)
Image-CaptionUsing LSTM or Transformer to solve Image Captioning in Pytorch
Stars: ✭ 36 (-92.81%)
ForwardA library for high performance deep learning inference on NVIDIA GPUs.
Stars: ✭ 136 (-72.85%)
Tensorflow CmakeTensorFlow examples in C, C++, Go and Python without bazel but with cmake and FindTensorFlow.cmake
Stars: ✭ 418 (-16.57%)
Turbotransformersa fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.
Stars: ✭ 826 (+64.87%)
Onnxt5Summarization, translation, sentiment-analysis, text-generation and more at blazing speed using a T5 version implemented in ONNX.
Stars: ✭ 143 (-71.46%)
fastT5⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
Stars: ✭ 421 (-15.97%)
transformerNeutron: A pytorch based implementation of Transformer and its variants.
Stars: ✭ 60 (-88.02%)
Pytorch Pwc a reimplementation of PWC-Net in PyTorch that matches the official Caffe version
Stars: ✭ 402 (-19.76%)
Warp CtcFast parallel CTC.
Stars: ✭ 3,954 (+689.22%)
Model serverA scalable inference server for models optimized with OpenVINO™
Stars: ✭ 431 (-13.97%)
Jetson InferenceHello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
Stars: ✭ 5,191 (+936.13%)
Deepsvg[NeurIPS 2020] Official code for the paper "DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation". Includes a PyTorch library for deep learning with SVG data.
Stars: ✭ 403 (-19.56%)
Tsdf FusionFuse multiple depth frames into a TSDF voxel volume.
Stars: ✭ 426 (-14.97%)
Nlp TutorialsSimple implementations of NLP models. Tutorials are written in Chinese on my website https://mofanpy.com
Stars: ✭ 394 (-21.36%)
Cudanative.jlJulia support for native CUDA programming
Stars: ✭ 393 (-21.56%)
GanetGA-Net: Guided Aggregation Net for End-to-end Stereo Matching
Stars: ✭ 393 (-21.56%)
Neuralnetwork.netA TensorFlow-inspired neural network library built from scratch in C# 7.3 for .NET Standard 2.0, with GPU support through cuDNN
Stars: ✭ 392 (-21.76%)
AmgclC++ library for solving large sparse linear systems with algebraic multigrid method
Stars: ✭ 390 (-22.16%)
Seq2seqchatbotsA wrapper around tensor2tensor to flexibly train, interact, and generate data for neural chatbots.
Stars: ✭ 466 (-6.99%)
Open3dOpen3D: A Modern Library for 3D Data Processing
Stars: ✭ 5,860 (+1069.66%)
Transformer TtsA Pytorch Implementation of "Neural Speech Synthesis with Transformer Network"
Stars: ✭ 418 (-16.57%)
CudfcuDF - GPU DataFrame Library
Stars: ✭ 4,370 (+772.26%)
Music TranslationA UNIVERSAL MUSIC TRANSLATION NETWORK - a method for translating music across musical instruments and styles.
Stars: ✭ 385 (-23.15%)
Ai LabAll-in-one AI container for rapid prototyping
Stars: ✭ 406 (-18.96%)
Bert PytorchGoogle AI 2018 BERT pytorch implementation
Stars: ✭ 4,642 (+826.55%)
GocvGo package for computer vision using OpenCV 4 and beyond.
Stars: ✭ 4,511 (+800.4%)
Io TsRuntime type system for IO decoding/encoding
Stars: ✭ 5,086 (+915.17%)
H2o4gpuH2Oai GPU Edition
Stars: ✭ 416 (-16.97%)
HipsyclImplementation of SYCL for CPUs, AMD GPUs, NVIDIA GPUs
Stars: ✭ 377 (-24.75%)
TrainyourownyoloTrain a state-of-the-art yolov3 object detector from scratch!
Stars: ✭ 399 (-20.36%)
Xray Oxygen🌀 Oxygen Engine 2.0. [Preview] Discord: https://discord.gg/P3aMf66
Stars: ✭ 481 (-3.99%)
JoeynmtMinimalist NMT for educational purposes
Stars: ✭ 420 (-16.17%)
CaerHigh-performance Vision library in Python. Scale your research, not boilerplate.
Stars: ✭ 452 (-9.78%)
Pvt Stars: ✭ 379 (-24.35%)
Accel(Mirror of GitLab) GPGPU Framework for Rust
Stars: ✭ 420 (-16.17%)
Tf Seq2seqSequence to sequence learning using TensorFlow.
Stars: ✭ 387 (-22.75%)
Awesome Visual TransformerCollect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)
Stars: ✭ 475 (-5.19%)
Gpt2 ChineseChinese version of GPT2 training code, using BERT tokenizer.
Stars: ✭ 4,592 (+816.57%)
IcpcudaSuper fast implementation of ICP in CUDA for compute capable devices 3.5 or higher
Stars: ✭ 416 (-16.97%)
OmninetOfficial Pytorch implementation of "OmniNet: A unified architecture for multi-modal multi-task learning" | Authors: Subhojeet Pramanik, Priyanka Agrawal, Aman Hussain
Stars: ✭ 448 (-10.58%)
Pytorch Original TransformerMy implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.
Stars: ✭ 411 (-17.96%)
IlgpuILGPU JIT Compiler for high-performance .Net GPU programs
Stars: ✭ 374 (-25.35%)
Cuda.jlCUDA programming in Julia.
Stars: ✭ 370 (-26.15%)
Tsdf Fusion PythonPython code to fuse multiple RGB-D images into a TSDF voxel volume.
Stars: ✭ 464 (-7.39%)
CausaldiscoverytoolboxPackage for causal inference in graphs and in the pairwise settings. Tools for graph structure recovery and dependencies are included.
Stars: ✭ 447 (-10.78%)
Gpu Rest EngineA REST API for Caffe using Docker and Go
Stars: ✭ 412 (-17.76%)
GfocalGeneralized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection, NeurIPS2020
Stars: ✭ 376 (-24.95%)
Flow ForecastDeep learning PyTorch library for time series forecasting, classification, and anomaly detection (originally for flood forecasting).
Stars: ✭ 368 (-26.55%)
TsaiTime series Timeseries Deep Learning Pytorch fastai - State-of-the-art Deep Learning with Time Series and Sequences in Pytorch / fastai
Stars: ✭ 407 (-18.76%)
NvpipeNVIDIA-accelerated zero latency video compression library for interactive remoting applications
Stars: ✭ 376 (-24.95%)
VudaVUDA is a header-only library based on Vulkan that provides a CUDA Runtime API interface for writing GPU-accelerated applications.
Stars: ✭ 373 (-25.55%)
CtcdecodePyTorch CTC Decoder bindings
Stars: ✭ 442 (-11.78%)