We 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

• DW and Slim denote depthwise separable convolution and a thiner model with half the channel size, respectively.

Using this command with --num-gpus 1

python /path/to/vovnet_sku110/train_net.py --config-file /path/to/vovnet_sku110/configs/<config.yaml> --eval-only --num-gpus 1 MODEL.WEIGHTS <model.pth>

As this vovnet-detectron2 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

To train a model, run

python /path/to/vovnet_sku110/train_net.py --config-file /path/to/vovnet_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/vovnet_sku110/train_net.py --config-file /path/to/vovnet_sku110/configs/faster_rcnn_V_39_FPN_3x.yaml --num-gpus 8

Model evaluation can be done similarly:

python /path/to/vovnet_sku110/train_net.py --config-file /path/to/vovnet_sku110/configs/faster_rcnn_V_39_FPN_3x.yaml --eval-only MODEL.WEIGHTS <model.pth>

To visual the result, run

python /path/to/vovnet_sku110/demo.py --config-file /path/to/vovnet_sku110/configs/faster_rcnn_V_39_FPN_3x.yaml --input image.jpg --output image.jpg MODEL.WEIGHTS <model.pth>

If 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}
}