Yang Zhang

Ok i fixed it, my caffe version was not correctly built, so layers were missing

if you specify --imdb voc_2007_trainval you are training on voc 2007 (that means you try to use the voc data with 21 classes but with a different net topology, they...

python tools/train_net.py --gpu 0 --solver models/pvanet/example_train/solver.prototxt  --weight models/pvanet/pretrained/pva9.1_pretrained_no_fc6.caffemodel --iters 100000 --cfg models/pvanet/cfgs/train.yml --imdb voc_2007_trainval

I have been wondering myself. I used the solver in models/pvanet/example_train/solver.txt but is the difference between pvanet and pvanet_obsolete, and which should you use?

@chengshuai after running python tools/train_net.py --gpu 0 --solver models/pvanet_obsolete/example_train_384/solver_voc.prototxt --weights models/pvanet/pretrained/pva9.1_pretrained_no_fc6.caffemodel --iters 100000 --cfg models/pvanet_obsolete/cfgs/train.yml --imdb voc_2007_trainval+voc_2012_trainval I get the error: I0601 20:53:51.431869 10026 solver.cpp:60] Solver scaffolding done. Loading pretrained...

@VanitarNordic Coco has 80 labels and contains all labels of Voc. you can train using python tools/train_net.py --gpu 0 --solver models/pvanet/example_train/solver.prototxt  --weight models/pvanet/pretrained/pva9.1_pretrained_no_fc6.caffemodel --iters 100000 --cfg models/pvanet/cfgs/train.yml --imdb coco_2014_train+voc_2012_trainval

maybe the OBSOLETE version was created without the intention of a bbox regression

install libgflags-dev

you have to uncomment USE_OPENCV:=3 in Makefile.config in the caffe-fast-rcnn folder

you have to create an imdb_wrapper that substitutes the default pascal_voc.py that is imdb_wrapper is a subclass of imdb, and there you have to load your own data in _load_image_index...