This repository is based on VoVNet-v2 Faster R-CNN on SKU-110K dataset NoteWe measure the inference time of all models with batch size 1 on the same RTX2080Ti GPU machine.
pytorch1.4.0
CUDA 10.2
cuDNN 7.3
Lightweight with FPNLite FPN Backbone Param. lr sched inference time AP AP75 AP50 download V2-19-FPN 37.6M 3x N/A N/A N/A N/A model | metrics R-50-FPN 51.2M 3x N/A N/A N/A N/A model | metrics V2-39-FPN 52.6M 3x 0.071 51.47 57.5 85.5 model | metrics
Using this command with --num-gpus 1
python /path/to/sku110/train_net.py --config-file /path/to/sku110/configs/<config.yaml> --eval-only --num-gpus 1 MODEL.WEIGHTS <model.pth> InstallationAs this repository is implemented as a extension form (detectron2/projects) upon detectron2, you just install detectron2 following INSTALL.md .
Prepare for SKU-110K dataset:
To download dataset, please visit here
Extract the file downloaded to datasets/sku110/images
Extract datasets/sku110/Annotations.zip
, there are 2 folders Annotations
and ImageSets
TrainingTo train a model, run
python /path/to/sku110/train_net.py --config-file /path/to/sku110/configs/<config.yaml> For example, to launch end-to-end Faster R-CNN training with VoVNetV2-39 backbone on 8 GPUs, one should execute:
python /path/to/sku110/train_net.py --config-file /path/to/sku110/configs/faster_rcnn_V_39_FPN_3x.yaml --num-gpus 8 EvaluationModel evaluation can be done similarly:
python /path/to/sku110/train_net.py --config-file /path/to/sku110/configs/faster_rcnn_V_39_FPN_3x.yaml --eval-only MODEL.WEIGHTS <model.pth> VisualizationTo visual the result, run
python /path/to/sku110/demo.py --config-file /path/to/sku110/configs/faster_rcnn_V_39_FPN_3x.yaml --input image.jpg --output image.jpg MODEL.WEIGHTS <model.pth> Citing VoVNetIf you use VoVNet, please use the following BibTeX entry.
@inproceedings{lee2019energy, title = {An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection}, author = {Lee, Youngwan and Hwang, Joong-won and Lee, Sangrok and Bae, Yuseok and Park, Jongyoul}, booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops}, year = {2019}}