• CVpods简介


    cvpods, a versatile and efficient codebase for many computer vision tasks: classification, segmentation, detection, self-supervised learning, keypoints and 3D(classification / segmentation / detection / representation learing), etc. The aim of cvpods is to achieve efficient experiments management and smooth tasks-switching.

    Build cvpods from source

    Make sure GPU is available on your local machine.

    # Install cvpods with GPU directly 
    pip install 'git+https://github.com/Megvii-BaseDetection/cvpods.git' --user
    
    # Or, to install it with GPU from a local clone:
    git clone https://github.com/Megvii-BaseDetection/cvpods.git
    pip install -e cvpods --user 
    
    # Or, to build it without GPU from a local clone:
    FORCE_CUDA=1 pip install -e cvpods --user
    

    Get Start

    Here we use coco object detection task as an example.

    # Preprare data path
    ln -s /path/to/your/coco/dataset datasets/coco
    
    # Enter a specific experiment dir 
    cd playground/retinanet/retinanet.res50.fpn.coco.multiscale.1x
    
    # Train
    pods_train --num-gpus 8
    # Test
    pods_test --num-gpus 8 \
        MODEL.WEIGHTS /path/to/your/save_dir/ckpt.pth # optional
        OUTPUT_DIR /path/to/your/save_dir # optional
    
    # Multi node training
    ## sudo apt install net-tools ifconfig
    pods_train --num-gpus 8 --num-machines N --machine-rank 0/1/.../N-1 --dist-url "tcp://MASTER_IP:port"

    教程和API链接:

    We provide a detailed tutorial, which covers introduction, usage, and extend guides in cvpods_tutorials. For all API usages, please refer to our documentation.




    如果这篇文章帮助到了你,你可以请作者喝一杯咖啡

  • 相关阅读:
    [转] CNN工作步骤解析
    [转] Attention模型结构
    [转] Boost算法
    [转] GDBT详解
    [转] Noise Contrastive Estimation 噪声对比估计 资料
    [转] 对数似然与交叉熵
    [转] ELMO
    [转] Batch Normalization
    强化学习总结
    MySQL 与 Hive 逻辑相关
  • 原文地址:https://www.cnblogs.com/sddai/p/15682008.html
Copyright © 2020-2023  润新知