faster-rcnn-resnet
faster-rcnn-resnet copied to clipboard
Eniac-Xie
ResNet Implementation for Faster-rcnn
Hello, I want to train my custom data in PASCAL VOC format using faster rcnn resnet? How can I use this project?
My dataset calsses number is 5 and I change *.prototxt files into 5 classes number, I can get the train model. But when I run ./tools/demo.py -- net resnet50 ,...
Hi, I'm using ResNet101_BN_SCALE_Merged_OHEM on my own dataset. Some of the output losses (loss_bbox and loss_cls) are always 0. Update: seems there are something wrong with OHEM. When I turn...
is this resnet-v1 or v2? if it is v1, so how can I modify it to v2?
Hi,Xie: I've seen that in your released model repository that (faster-rcnn-resnet without ohem) discriminator part is resnet-101,can you please release the pretrained model of resnet-50 version, it would very helpful....
when i run ./experiments/scripts/faster_rcnn_end2end.sh 0 ResNet-50 pascal_voc,i got a error:  i did not change the original code,but only replace the "num_classes" and "num_output", is there anyone...
Hi，you link provides *.caffemodel, but I do not find solver.prototxt in root directory(like faster_rcnc_test.pt in py-faster-rcnn). By the way, Should I use tools/demo.py(like py-faster-rcnn) to detect objects?
**# I followed the steps on your website and installed the project successfully. However, I got the nan loss as follow (both OHEM and no OHEM model). How to fix...
Hi~ What is the number 0.5 mean in your result table? Did you change any thresholds in .yml file when testing? Thanks,
I don't understand why there is this line : `top[0].reshape(1, 5)` in [this file](https://github.com/Eniac-Xie/faster-rcnn-resnet/blob/master/lib/rpn/proposal_layer.py#L41). According to what I have understand, and according to the comment juste before this line :...
