pva-faster-rcnn
pva-faster-rcnn copied to clipboard
sanghoon
Demo code for PVANet
in the paper, the report run time for forward passing is
Hello @sanghoon I am not able to fix this error!!!! I am trying a batch size of 4 instead of 1! I know the problem is mismatch of rpn_cls_score ,...
PVA+RFCN
I read your paper and merge your base PVANet with RFCN. Have you tried using PVANet with RFCN? I found it hard to train and the accuracy(ignore_label=0) gets improved slowly....
I test it with my own data with 640x1000. It give following error: > I1020 22:34:11.216954 7221 net.cpp:91] Creating Layer conv4_1/incep > I1020 22:34:11.216960 7221 net.cpp:425] conv4_1/incep I1020 22:34:11.216967 7221...
Hi@sanghoon： I can train and test my own net with my own data by the models/example_train_384.Now I want to run the demo.py, but it has the error like this: Traceback...
Is there a training example of lite model? I tried an example in lite training model from below and is not able to get a meaningful result (all objects have...
cannot download models， could anyone share this on the baidudisk or email to me？ thanks！
# when I train with the pretrained model,it comes like this: I0103 20:21:01.434712 28289 layer_factory.hpp:77] Creating layer proposal AttributeError: 'module' object has no attribute 'ProposalLayer2' Traceback (most recent call last):...
hi,@sanghoon,there is a question when i trained your net,i using the 'pvanet_obsolete'version ,when i funetuning the net using the VOC07 dataset, i found the loss is very big,but when i...
Going through the demo walk through (and ubuntu caffe instructions. http://caffe.berkeleyvision.org/install_apt.html) and can't seem to figure this out:  Thank you! Excited to try this out.
