This repository contains Detectron with VoVNet (CVPRW'19) Backbone Networks. This code based on pytorch imeplementation of Detectron (maskrcnn-benchmark)

• Memory efficient
• Better performance, especially for small objects
• Faster speed

• 2x schedule
• same hyperparameters
• same training protocols ( max epoch, learning rate schedule, etc)
• NOT multi-scale training augmentation
• 8 x TITAN Xp GPU
• pytorch1.1
• CUDA v9
• cuDNN v7.2

'*' indicates ResNeXt models from Detectron official caffe2 page.

• VoVNet-39
• VoVNet-57
• VoVNet-75
• VoVNet-93

Check INSTALL.md for installation instructions which is orginate from maskrcnn-benchmark

Follow the instructions maskrcnn-benchmark guides

For example,

export NGPUS=8
python -m torch.distributed.launch --nproc_per_node=$NGPUS tools/train_net.py --config-file "configs/vovnet/e2e_faster_rcnn_V_39_FPN_2x.yaml" 

Follow the instruction

First of all, you have to download the weight file you want to inference.

For examaple,

wget https://dl.dropbox.com/s/f1per2rj4pi8t71/FRCN-V-39-FPN-2x-norm.pth
export NGPUS=8
python -m torch.distributed.launch --nproc_per_node=$NGPUS tools/test_net.py --config-file "configs/vovnet/e2e_faster_rcnn_V_39_FPN_2x.yaml"   TEST.IMS_PER_BATCH 16 MODEL.WEIGHT FRCN-V-39-FPN-2x-norm.pth

wget https://dl.dropbox.com/s/f1per2rj4pi8t71/FRCN-V-39-FPN-2x-norm.pth
CUDA_VISIBLE_DEVICES=0
python tools/test_net.py --config-file "configs/vovnet/e2e_faster_rcnn_V_39_FPN_2x.yaml" TEST.IMS_PER_BATCH 1 MODEL.WEIGHT FRCN-V-39-FPN-2x-norm.pth

• super slim models
• slim models
• Larger models
• Multi-scale training & test