Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.
A caffe implementation of MobileNet-SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.
Network | mAP | Download | Download |
---|---|---|---|
MobileNet-SSD | 72.7 | train | deploy |
cd create_lmdb/code
bash create_list.sh
, which will create trainval.txt, test.txt and test_name_size.txtbash create_data.sh
, which will generate the LMDB in Dataset directory.
- LMDB Creation part is taken from https://github.com/jinfagang/kitti-ssd
ln -s PATH_TO_YOUR_TRAIN_LMDB trainval_lmdb
ln -s PATH_TO_YOUR_TEST_LMDB test_lmdb
python merge_bn.py --model example/MobileNetSSD_deploy.prototxt --weights snapshot/mobilenet_iter_xxxxxx.caffemodel
There are 2 primary differences between this model and MobileNet-SSD on tensorflow:
I trained this model from a MobileNet classifier(caffemodel and prototxt) converted from tensorflow. I first trained the model on MS-COCO and then fine-tuned on VOC0712. Without MS-COCO pretraining, it can only get mAP=0.68.
You can run it on Android with my another project rscnn.