py-R-FCN

py-R-FCN copied to clipboard

training error

6

Hello, While training I am getting the following error I0204 03:08:08.855443 21819 solver.cpp:228] Iteration 920, loss = 0.266415 I0204 03:08:08.855478 21819 solver.cpp:244] Train net output #0: accuarcy = 0.941176 I0204...

sandeepangara

Hi, I find in the implementation the RPN's input is from resnet layer4 not layer5+new conv(see protxt file) but origin paper said depth of RoI-wise subnetwork is 0. I am...

sjtuxcx

when I compile my c++ program with import libcaffe.so,it occur this :py-R-FCN/caffe/build/lib/libcaffe.so: undefined reference to symbol 'cudaSetDevice' /usr/local/cuda/lib64/libcudart.so.8.0: error adding symbols: DSO missing from command line . has tried many...

ihg1992

It is goning wrong when i load the pre_train model!!!

1

hello： when i train the R-FCN use: python ./tools/train_net.py --gpu 0 \ --solver models/pascal_voc/ResNet-50/rfcn_end2end/solver_ohem.prototxt \ --weights data/imagenet_models/ResNet-50-model.caffemodel \ --imdb "voc_2007_trainval" \ --iters 100000 \ --cfg experiments/cfgs/rfcn_end2end_ohem.yml i got an err!!!!!!!!!!!!!!!!!!!!!!!!!...

Zzmc

train ResNet-50 Alternating training Erroe

3

Hi， I want to traing ResNet-50 using Alternating training but meet a error I do not know how solve it,could somebody help?thank you! ### Cannot copy param 0 weights from...

chenxu93

I change with py-rfcn with FPN .I just use 6 feature map (res2\res3\res4\res5 and pooling 6) to proposal anchors,and the rest part unchanged. The net work normal until sloving....the error...

daiwenjun2017

File "/media/hp208/4t/yangxueyuan/R-FCN/py-R-FCN/tools/train_net.py", line 112, in max_iters=args.max_iters) File "/media/hp208/4t/yangxueyuan/R-FCN/py-R-FCN/tools/../lib/fast_rcnn/train.py", line 205, in train_net model_paths = sw.train_model(max_iters) File "/media/hp208/4t/yangxueyuan/R-FCN/py-R-FCN/tools/../lib/fast_rcnn/train.py", line 146, in train_model self.solver.step(1) File "/media/hp208/4t/yangxueyuan/R-FCN/py-R-FCN/tools/../lib/rpn/proposal_target_layer.py", line 51, in forward (all_rois, np.hstack((zeros,...

zhaowujie

Implement Light-Head RCNN by modifying the src of RFCN

2

Because the structure of the RFCN and light-head rcnn is pretty similar, I just tried to implement the light-head rcnn by modifying the py-R-FCN on caffe. I only changed the...

sherryxie1

I just modify the train_agnostic.protxt and test_agnostic.protxt. The net seems been trained on my own dataset well. But it has a low mAP (0.07). Anyone meets the same problem??

ZhiHuaYin

How to implement R-FCN using ZF or VGG base model

1

I tried to implement R-FCN for my own dataset. But my dataset contains lots of tiny objects and I think a relative shallow base network could be better for tiny...

liuliu66