https://github.com/oneflow-inc/models
Models and examples built with OneFlow
https://github.com/oneflow-inc/models
Last synced: about 1 year ago
JSON representation
Models and examples built with OneFlow
- Host: GitHub
- URL: https://github.com/oneflow-inc/models
- Owner: Oneflow-Inc
- License: apache-2.0
- Created: 2020-12-14T09:59:52.000Z (over 5 years ago)
- Default Branch: main
- Last Pushed: 2024-10-16T09:41:54.000Z (over 1 year ago)
- Last Synced: 2025-03-28T21:05:22.006Z (about 1 year ago)
- Language: Python
- Size: 154 MB
- Stars: 97
- Watchers: 40
- Forks: 38
- Open Issues: 50
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# OneFlow-Models
**Models and examples implement with OneFlow(version >= 0.5.0).**
## Introduction
**English** | [简体中文](/README_zh-CN.md)
OneFlow-Models is an open source repo which contains official implementation of different models built on OneFlow. In each model, we provide at least two scripts `train.sh` and `infer.sh` for a quick start. For each model, we provide a detailed `README` to introduce the usage of this model.
## Features
- various models and pretrained weight
- easy use for beginners
## Quick Start
Please check our the following **demos** for a quick start
- **image classification** [quick start lenet demo](Demo/quick_start_demo_lenet/lenet.py)
- **speaker recognition** [speaker identification demo](Demo/speaker_identification_demo)
## Model List
Image Classification
- [Lenet](https://github.com/Oneflow-Inc/models/blob/main/Demo/quick_start_demo_lenet/lenet.py)
- [Alexnet](https://github.com/Oneflow-Inc/models/tree/main/Vision/classification/image/alexnet)
- [VGG16/19](https://github.com/Oneflow-Inc/models/tree/main/Vision/classification/image/vgg)
- [Resnet50](https://github.com/Oneflow-Inc/models/tree/main/Vision/classification/image/resnet50)
- [InceptionV3](https://github.com/Oneflow-Inc/models/tree/main/Vision/classification/image/inception_v3)
- [Densenet](https://github.com/Oneflow-Inc/models/tree/main/Vision/classification/image/densenet)
- [Resnext50_32x4d](https://github.com/Oneflow-Inc/models/tree/main/Vision/classification/image/resnext50_32x4d)
- [Shufflenetv2](https://github.com/Oneflow-Inc/models/tree/main/Vision/classification/image/shufflenetv2)
- [MobilenetV2](https://github.com/Oneflow-Inc/models/tree/main/Vision/classification/image/mobilenetv2)
- [mobilenetv3](https://github.com/Oneflow-Inc/models/tree/main/Vision/classification/image/mobilenetv3)
- [Ghostnet](https://github.com/Oneflow-Inc/models/tree/main/Vision/classification/image/ghostnet)
- [RepVGG](https://github.com/Oneflow-Inc/models/tree/main/Vision/classification/image/repvgg)
- [DLA](https://github.com/Oneflow-Inc/models/tree/main/Vision/classification/image/DLA)
- [PoseNet](https://github.com/Oneflow-Inc/models/tree/main/Vision/classification/image/poseNet)
- [Scnet](https://github.com/Oneflow-Inc/models/tree/main/Vision/classification/image/scnet)
- [Mnasnet](https://github.com/Oneflow-Inc/models/tree/main/Vision/classification/image/mnasnet)
- [ViT](https://github.com/Oneflow-Inc/models/tree/main/Vision/classification/image/ViT)
Video Classification
- [TSN](https://github.com/Oneflow-Inc/models/tree/main/Vision/classification/video/TSN)
Object Detection
- [CSRNet](https://github.com/Oneflow-Inc/models/tree/main/Vision/detection/CSRNet)
Semantic Segmentation
- [FODDet](https://github.com/Oneflow-Inc/models/tree/main/Vision/segmentation/FODDet)
- [FaceSeg](https://github.com/Oneflow-Inc/models/tree/main/Vision/segmentation/FaceSeg)
- [U-Net](https://github.com/Oneflow-Inc/models/tree/main/Vision/segmentation/U-Net)
Generative Adversarial Networks
- [DCGAN](https://github.com/Oneflow-Inc/models/tree/main/Vision/gan/DCGAN)
- [SRGAN](https://github.com/Oneflow-Inc/models/tree/main/Vision/gan/SRGAN)
- [Pix2Pix](https://github.com/Oneflow-Inc/models/tree/main/Vision/gan/Pix2Pix)
- [CycleGAN](https://github.com/Oneflow-Inc/models/tree/main/Vision/gan/CycleGAN)
Neural Style Transform
- [FastNeuralStyle](https://github.com/Oneflow-Inc/models/tree/main/Vision/style_transform/fast_neural_style)
Person Re-identification
- [BoT](https://github.com/Oneflow-Inc/models/tree/main/Vision/reid/BoT)
Natural Language Processing
- [RNN](https://github.com/Oneflow-Inc/models/tree/main/NLP/rnn)
- [Seq2Seq](https://github.com/Oneflow-Inc/models/tree/main/NLP/seq2seq)
- [LSTMText](https://github.com/Oneflow-Inc/models/tree/main/NLP/LSTMText)
- [TextCNN](https://github.com/Oneflow-Inc/models/tree/main/NLP/TextCNN)
- [Transformer](https://github.com/Oneflow-Inc/models/tree/main/NLP/Transformer)
- [Bert](https://github.com/Oneflow-Inc/models/tree/main/NLP/bert-oneflow)
- [CPT](https://github.com/Oneflow-Inc/models/tree/main/NLP/CPT)
- [Roberta](https://github.com/Oneflow-Inc/models/tree/main/NLP/roberta)
- [MoE](https://github.com/Oneflow-Inc/models/tree/main/NLP/MoE)
Audio
- [SincNet](https://github.com/Oneflow-Inc/models/tree/main/Audio/SincNet)
- [Wav2Letter](https://github.com/Oneflow-Inc/models/tree/main/Audio/Wav2Letter)
- [AM_MobileNet1D](https://github.com/Oneflow-Inc/models/tree/main/Audio/AM-MobileNet1D)
- [Speech-Emotion-Analyer](https://github.com/Oneflow-Inc/models/tree/main/Audio/Speech-Emotion-Analyzer)
- [Speech-Transformer](https://github.com/Oneflow-Inc/models/tree/main/Audio/Speech-Transformer)
- [CycleGAN-VC2](https://github.com/Oneflow-Inc/models/tree/main/Audio/CycleGAN-VC2)
- [MaskCycleGAN-VC](https://github.com/Oneflow-Inc/models/tree/main/Audio/MaskCycleGAN-VC)
- [StarGAN-VC](https://github.com/Oneflow-Inc/models/tree/main/Audio/StarGAN-VC)
- [Adaptive_Voice_Conversion](https://github.com/Oneflow-Inc/models/tree/main/Audio/Adaptive_Voice_Conversion)
Deep Reinforcement Learning
- [FlappyBird](https://github.com/Oneflow-Inc/models/tree/main/DeepReinforcementLearning/FlappyBird)
Quantization Aware Training
- [Quantization](https://github.com/Oneflow-Inc/models/tree/main/Quantization)
Knowledge Distillation
- [KnowledgeDistillation](https://github.com/Oneflow-Inc/models/tree/main/KnowledgeDistillation/KnowledgeDistillation)
## Installation and Environment setup
**Install Oneflow**
https://github.com/Oneflow-Inc/oneflow#install-with-pip-package
**Build custom ops from source**
In the root directory, run:
```bash
mkdir build
cd build
cmake ..
make -j$(nrpoc)
```
Example of using ops:
```bash
from ops import RoIAlign
pooler = RoIAlign(output_size=(14, 14), spatial_scale=2.0, sampling_ratio=2)
```