kakusikun / deep-learning-works

my personal work on deep learning using pytorch

deep-learning-works

Work in deep learning via Pytorch.

Installation

• CUDA 9.2
• cudnn 7.3.1
• inplace-abn
• Pytorch 1.4.0, torchvision 0.5.0

  pip install torch==1.4.0+cu92 torchvision==0.5.0+cu92 -f https://download.pytorch.org/whl/torch_stable.html
  

• Cython

  pip install Cython
  

• python packages in requirement.txt

Overview

Fork from following task

Person Re-identification

• (SSG) Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification
• (MAR) Unsupervised Person Re-identification by Soft Multilabel Learning
• (BNNeck) Bag of Tricks and A Strong Baseline for Deep Person Re-identification
• (OSNet) Omni-Scale Feature Learning for Person Re-Identification
• (OSNet-IAP) Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning
• (OSNet-AIN) Learning Generalisable Omni-Scale Representations for Person Re-Identification

Pedestrian Attribute Recognition

• Multitask Learning using fully connected layer

Object Detection

• (CenterNet) Objects as Points + (CornerNet-Lite) CornerNet-Lite: Efficient Keypoint Based Object Detection

Clothing Detection, Keypoints

• (DeepFashion2) A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images

Result

working on it