Skip to content
Pelee implement with pytorch
Python C Cuda Other
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.
configs finish voc train and test Apr 29, 2019

Pelee: A Real-Time Object Detection System on Mobile Devices, in PyTorch

A PyTorch implementation of Pelee: A Real-Time Object Detection System on Mobile Devices The official and original Caffe code can be found here.


I train Pelee with pytorch and the result is better than the original paper result,the pretrained model can be downloaded in peleenet.pth.

MAP in VOC2007

Method 07+12 07+12+coco
SSD300 77.2 81.2
SSD+MobileNet 68 72.7
Original Pelee 70.9 76.4
Ours Pelee 71.76 ---


the supported version is pytorch-0.4.1 or pytorch-1.0

  • tqdm
  • opencv
  • addict
  • pytorch>=0.4
  • Clone this repository.
git clone
  • Compile the nms and coco tools:
  • Prepare dataset (e.g., VOC, COCO), refer to ssd.pytorch for detailed instructions.


you can train different set according to configs/*,First, you should download the pretrained model peleenet.pth,then,move the file to weights/

python --dataset VOC\COCO --config ./configs/  

if you train with multi gpu

CUDA_VISIBLE_DEVICES=0,1 python --dataset VOC\COCO --config ./configs/   --ngpu 2


you can evaluate your model in voc and coco

python --dataset VOC\COCO  --config ./configs/ --trained_model ./weights/Pelee_VOC.pth 


you can test your image, First, download the trained model Pelee_VOC.pth file. Then, move the file to weights/.

python --dataset VOC\COCO  --config ./configs/ --trained_model ./weights/Pelee_VOC.pth --show  

You can see the image with drawed boxes as:


the code support:

  • Support for the MS COCO dataset and VOC PASCAL dataset
  • Support for Pelee304_VOC、Pelee304_COCO training and testing
  • Support for mulltigpu training
  • Support training and and testing in VOC and COCO


You can’t perform that action at this time.