This repository is a folk of multisepectral deepnet for pedetstrian detection code. For how to install the required softwares and set up the code in right configuration, e.g., Caffe, pycaffe, please refer to the most original README.md.
VGG16 model on caltech trained on Caltech pedestrian dataset.
VGG16 model on kaist (RGB input) trained on Kaist pedestrian dataset.
VGG16 model on kaist (multispectral input) trained on Kaist multispectral dataset.
Save these models to models/caltech/VGG16/, models/kaist/VGG16/, and models/kaist_fusion/VGG16/, respectively.
Run sh ./run_demo.sh caltech for images from Caltech.
Run sh ./run_demo.sh kaist-color for images from Kaist.
Run sh ./run_demo.sh kaist-fusion for multispectral images from Kaist.
Save the test data in data/kaist/test_all/.
In the root directory, Run ./tools/test_net.py --gpu 0 --def models/kaist_fusion/VGG16/faster_rcnn_test.pt --net models/kaist_fusion/VGG16/VGG16_faster_rcnn_final_kaist_fusion.caffemodel --cfg experiments/cfgs/faster_rcnn_end2end_fusion.yml --imdb kaist_test-all
for test the pretrianed kaist_fusion model.