Home

Awesome

OneFlow-Models

Models and examples implement with OneFlow(version >= 0.5.0).

Introduction

English | 简体中文

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

Quick Start

Please check our the following demos for a quick start

Model List

<details> <summary> <b> Image Classification </b> </summary> </details> <details> <summary> <b> Video Classification </b> </summary> </details> <details> <summary> <b> Object Detection </b> </summary> </details> <details> <summary> <b> Semantic Segmentation </b> </summary> </details> <details> <summary> <b> Generative Adversarial Networks </b> </summary> </details> <details> <summary> <b> Neural Style Transform </b> </summary> </details> <details> <summary> <b> Person Re-identification </b> </summary> </details> <details> <summary> <b> Natural Language Processing </b> </summary> </details> <details> <summary> <b> Audio </b> </summary> </details> <details> <summary> <b> Deep Reinforcement Learning </b> </summary> </details> <details> <summary> <b> Quantization Aware Training </b> </summary> </details> <details> <summary> <b> Knowledge Distillation </b> </summary> </details>

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:

mkdir build
cd build
cmake ..
make -j$(nrpoc)

Example of using ops:

from ops import RoIAlign
pooler = RoIAlign(output_size=(14, 14), spatial_scale=2.0, sampling_ratio=2)