frcnn

frcnn copied to clipboard

why comment the frcnn_proposal_layer's Forward GPU implementation？

5

Hello, I understand that this is a quite old repo, but I would like to know if the GPU implementation has some bug, since it is commented out. Thanks

sigfrid696

undefined reference to `Blowfish::Blowfish`

1

Hi, I compile follow the steps： 1. cd $CAFFE_ROOT 2. cp Makefile.config.example Makefile.config 3. uncomment the line: USE_CUDNN := 1 4. comment the *_20 and *_21 lines 5. make -j7...

zjbaby

res101 inference result zero

7

看Owner是中国人就用中文了(小声BB...) 我直接用caffe.exe训练了 resnet101 (models/FRCNN/res101/solver.proto VOC2007) 我一开始训练了10000步发现推理结果为0 (使用test_frcnn.exe, 直接用训练集当做测试集) 于是我继续训练到20000发现推理结果还是为0 详细调试后发现score肥肠肥肠低都是0.00x,最高的我看到也就0.05... 我浏览了其他问题, 你说可以不用convert_model.py 于是我就直接训练完的模型直接test_frcnn也不行.输出结果如下 > I0828 13:00:15.272047 19684 FRCNNtest.cpp:210] Handle 97 th image : 000193.jpg, with image_thresh : 0, 0 ->...

SuperPowerLF2

rfcn convert_model.py problem

8

I can train the rfcn_res50,but when I run the convert_model.py,I got a problem:"Key error,bbox_pred_pre",And there isn't 'bbox_pred_pre' layer in test.protext.

wushilian

Loss NAN

10

Try to train on Resnet50 FasterRCNN on VOC, got nan loss in the begin of training process: ``` I0812 13:02:23.224562 15010 caffe.cpp:248] Starting Optimization I0812 13:02:23.224596 15010 solver.cpp:292] Solving ResNet-50...

lucasjinreal

How to train on coco?

8

How to train on coco anyway?

lucasjinreal

Using r-frcnn

9

I want to use the r-frcnn(rotation) to train my own datasets, What should my data format be ? (cx,cy,w,h,angle) or (x0,y0,x1,y1,x2,y2,x3,y3)? But if it is the former, What is the...

XWalways

hi，where the pre-train caffemodel can download,thanks

1

runauto

.build_release/lib/libmodules.so: cannot open shared object file: No such file or directory

1

@makefile hi，I have successfully run rfcn-resnet50 code, when I use fpn-resnet50(both master branches and fpn branches have tried) get this erro.

moyans

run yolov3-tiny completed!

3

I find the reason why yolov3-tiny model failed with current code. ## There are two questions need to be solved. * change pooling reshape rule in pooling_layer.cpp ```c++ if (ceil_mode)...

a-little-cat