mingfeima Goto Github PK

adain-style

Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

artistic-videos

Torch implementation for the paper "Artistic style transfer for videos"

audio

simple audio I/O for pytorch

bench_sdpa

smoke test and benchmark for sdpa

chatrwkv

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

convnet-benchmark-py

PyTorch convnet performance benchmark

convnet-benchmarks

Easy benchmarking of all publicly accessible implementations of convnets with pytorch support

cpuinfo

CPU INFOrmation library (x86/x86-64/ARM/ARM64, Linux/Windows/Android/macOS/iOS)

crnn.pytorch

Convolutional recurrent network in pytorch

deep-learning-math-kernel-research

deepspeech.pytorch

Speech Recognition using DeepSpeech2.

deepspeech.torch

Speech Recognition using DeepSpeech2 network and the CTC activation function.

detectron2

Detectron2 is FAIR's next-generation platform for object detection and segmentation.

dlrm

An implementation of a deep learning recommendation model (DLRM)

espnet

End-to-End Speech Processing Toolkit

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

extension-cpp

C++ extensions in PyTorch

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

fast-neural-style

Feedforward style transfer

gen-efficientnet-pytorch

Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

horovod

Distributed training framework for TensorFlow, Keras, and PyTorch.

ideep

Intel® Optimization for Chainer*, a Chainer module providing numpy like API and DNN acceleration using MKL-DNN.

inference

Reference implementations of inference benchmarks

informer2020

The GitHub repository for the paper "Informer" accepted by AAAI 2021.

lite-transformer

[ICLR 2020] Lite Transformer with Long-Short Range Attention

llama.cpp

Port of Facebook's LLaMA model in C/C++

llm.c

LLM training in simple, raw C/CUDA

mmdetection

Open MMLab Detection Toolbox and Benchmark

mmdnn

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.