I tried to run training example on Pascal VOC 2007 dataset with VGGnet. After getting the result .cktp files(checkpoint file, model.ckpt.data-00000-of-00001, ckpt.index, ckpt.meta), I ran demo.py with my ckpt file, but I got only pictures without any bounding box. I just used the script
python ./faster_rcnn/train_net.py --gpu 0 --weights ./data/pretrain_model/VGG_imagenet.npy --imdb voc_2007_trainval --iters 70000 --cfg ./experiments/cfgs/faster_rcnn_end2end.yml --network VGGnet_train - --restore 0
I tried to run training example on Pascal VOC 2007 dataset with VGGnet. After getting the result .cktp files(checkpoint file, model.ckpt.data-00000-of-00001, ckpt.index, ckpt.meta), I ran demo.py with my ckpt file, but I got only pictures without any bounding box. I just used the script
python ./faster_rcnn/train_net.py --gpu 0 --weights ./data/pretrain_model/VGG_imagenet.npy --imdb voc_2007_trainval --iters 70000 --cfg ./experiments/cfgs/faster_rcnn_end2end.yml --network VGGnet_train - --restore 0
Why this happened? Thanks a lot.