/ymir-executor-fork-1

docker images for training, mining annd infer for ymir

Primary LanguagePythonApache License 2.0Apache-2.0

ymir-executor documentation English | 简体中文

ymir-1.1.0 official image

  • yolov4

    docker pull youdaoyzbx/ymir-executor:ymir1.1.0-yolov4-cu112-tmi

docker pull youdaoyzbx/ymir-executor:ymir1.1.0-yolov4-cu101-tmi

  • yolov5

    docker pull youdaoyzbx/ymir-executor:ymir1.1.0-yolov5-cu111-tmi

docker pull youdaoyzbx/ymir-executor:ymir1.1.0-yolov5-cu102-tmi

  • mmdetection

    docker pull youdaoyzbx/ymir-executor:ymir1.1.0-mmdet-cu111-tmi

docker pull youdaoyzbx/ymir-executor:ymir1.1.0-mmdet-cu102-tmi

  • detectron2

    docker pull youdaoyzbx/ymir-executor:ymir1.1.0-detectron2-cu111-tmi

  • yolov7

    docker pull youdaoyzbx/ymir-executor:ymir1.1.0-yolov7-cu111-tmi

  • vidt

    docker pull youdaoyzbx/ymir-executor:ymir1.1.0-vidt-cu111-tmi

  • nanodet

    docker pull youdaoyzbx/ymir-executor:ymir1.1.0-nanodet-cu111-tmi

overview

docker image finetune tensorboard args/cfg options framework onnx pretrained weights
yolov4 ? ✔️ ❌ darknet + mxnet ❌ local
yolov5 ✔️ ✔️ ✔️ pytorch ✔️ local+online
yolov7 ✔️ ✔️ ✔️ pytorch ❌ local+online
mmdetection ✔️ ✔️ ✔️ pytorch ❌ online
detectron2 ✔️ ✔️ ✔️ pytorch ❌ online
vidt ? ✔️ ✔️ pytorch ❌ online
nanodet ✔️ ✔️ ❌ pytorch_lightning ❌ online

  • online pretrained weights may download through network

  • local pretrained weights have copied to docker images when building image

benchmark

  • training dataset: voc2012-train 5717 images
  • validation dataset: voc2012-val 5823 images
  • image size: 640

gpu: single Tesla P4

docker image batch size epoch number model voc2012 val map50 training time note
yolov5 16 100 yolov5s 70.05% 9h coco-pretrained
vidt 2 100 swin-nano 54.13% 2d imagenet-pretrained
yolov4 4 20000 steps yolov4 66.18% 2d imagenet-pretrained
yolov7 16 100 yolov7-tiny 70% 8h coco-pretrained

gpu: single GeForce GTX 1080 Ti

docker image batch size epoch number model voc2012 val map50 training time note
yolov5 16 100 yolov5s 70.35% 2h coco-pretrained
yolov7 16 100 yolov7-tiny 70.4% 5h coco-pretrained
mmdetection 16 100 yolox_tiny 66.2% 5h coco-pretrained
detectron2 2 20000 steps retinanet_R_50_FPN_1x 53.54% 2h imagenet-pretrained
nanodet 16 100 nanodet-plus-m_416 58.63% 5h imagenet-pretrained

det-yolov4-tmi

  • yolov4 training, mining and infer docker image, use mxnet and darknet framework

    cd det-yolov4-tmi
docker build -t ymir-executor/yolov4:cuda101-tmi -f cuda101.dockerfile .

docker build -t ymir-executor/yolov4:cuda112-tmi -f cuda112.dockerfile .

det-yolov5-tmi

  • yolov5 training, mining and infer docker image, use pytorch framework
cd det-yolov5-tmi
docker build -t ymir-executor/yolov5:cuda102-tmi -f cuda102.dockerfile .

docker build -t ymir-executor/yolov5:cuda111-tmi -f cuda111.dockerfile .

det-mmdetection-tmi

cd det-mmdetection-tmi
docker build -t ymir-executor/mmdet:cu102-tmi -f docker/Dockerfile.cuda102 .

docker build -t ymir-executor/mmdet:cu111-tmi -f docker/Dockerfile.cuda111 .

how to custom ymir-executor

how to import pretrained model weights

reference